diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..be5f91ce78e32fbbe28eaa9363fff7e659f2ee6c --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,135 @@ +{% macro render_extra_keys(json_dict, handled_keys) %} + {%- if json_dict is mapping %} + {%- for json_key in json_dict if json_key not in handled_keys %} + {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %} + {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '' }} + {%- else %} + {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '' }} + {%- endif %} + {%- endfor %} + {%- endif %} +{% endmacro %} + +{%- if messages[0]["role"] == "system" %} + {%- set system_message = messages[0]["content"] %} + {%- set loop_messages = messages[1:] %} +{%- else %} + {%- set loop_messages = messages %} +{%- endif %} + +{%- if not tools is defined %} + {%- set tools = [] %} +{%- endif %} + +{%- if system_message is defined %} + {{- "<|im_start|>system\n" + system_message }} +{%- else %} + {%- if tools is iterable and tools | length > 0 %} + {{- "<|im_start|>system\nYou are INTELLECT-3, a helpful assistant developed by Prime Intellect, that can interact with a computer to solve tasks." }} + {%- endif %} +{%- endif %} +{%- if tools is iterable and tools | length > 0 %} + {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }} + {{- "" }} + {%- for tool in tools %} + {%- if tool.function is defined %} + {%- set tool = tool.function %} + {%- endif %} + {{- "\n\n" ~ tool.name ~ "" }} + {%- if tool.description is defined %} + {{- '\n' ~ (tool.description | trim) ~ '' }} + {%- endif %} + {{- '\n' }} + {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %} + {%- for param_name, param_fields in tool.parameters.properties|items %} + {{- '\n' }} + {{- '\n' ~ param_name ~ '' }} + {%- if param_fields.type is defined %} + {{- '\n' ~ (param_fields.type | string) ~ '' }} + {%- endif %} + {%- if param_fields.description is defined %} + {{- '\n' ~ (param_fields.description | trim) ~ '' }} + {%- endif %} + {%- set handled_keys = ['name', 'type', 'description'] %} + {{- render_extra_keys(param_fields, handled_keys) }} + {{- '\n' }} + {%- endfor %} + {%- endif %} + {% set handled_keys = ['type', 'properties'] %} + {{- render_extra_keys(tool.parameters, handled_keys) }} + {{- '\n' }} + {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %} + {{- render_extra_keys(tool, handled_keys) }} + {{- '\n' }} + {%- endfor %} + {{- "\n" }} + {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }} +{%- endif %} +{%- if system_message is defined %} + {{- '<|im_end|>\n' }} +{%- else %} + {%- if tools is iterable and tools | length > 0 %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in loop_messages %} + {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %} + {{- '<|im_start|>' + message.role }} + {%- if message.content is defined and message.content is string %} + {%- if message.reasoning_content -%} + {{ '\n' + message.reasoning_content.strip() + '' }} + {%- else -%} + {{ '\n' }} + {%- endif -%} + {{- '\n' + message.content | trim + '\n' }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n\n' }} + {%- if tool_call.arguments is defined %} + {%- for args_name, args_value in tool_call.arguments|items %} + {{- '\n' }} + {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %} + {{- args_value }} + {{- '\n\n' }} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.role == "assistant" and message.reasoning_content is defined %} + {%- if message.reasoning_content -%} + {{ '\n' + message.reasoning_content.strip() + '' }} + {%- else -%} + {{ '\n' }} + {%- endif -%} + {%- if message.content.strip() -%} + {{ '\n' + message.content.strip() }} + {%- endif -%} + {%- else %} + {{- '\n' + message.content }} + {%- endif %} + {{- '<|im_end|>' + '\n' }} + {%- elif message.role == "tool" %} + {%- if loop.previtem and loop.previtem.role != "tool" %} + {{- '<|im_start|>user\n' }} + {%- endif %} + {{- '\n' }} + {{- message.content }} + {{- '\n\n' }} + {%- if not loop.last and loop.nextitem.role != "tool" %} + {{- '<|im_end|>\n' }} + {%- elif loop.last %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..73efa6fb2d1b181a592f20dbe459dccf094de8cc --- /dev/null +++ b/config.json @@ -0,0 +1,48 @@ +{ + "architectures": [ + "Glm4MoeForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "auto_map": { + "AutoConfig": "configuration_glm4_moe.Glm4MoeConfig", + "AutoModel": "modeling_glm4_moe.Glm4MoeModel", + "AutoModelForCausalLM": "modeling_glm4_moe.Glm4MoeForCausalLM" + }, + "dtype": "bfloat16", + "eos_token_id": [ + 151334, + 151329 + ], + "first_k_dense_replace": 1, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 10944, + "max_position_embeddings": 131072, + "model_type": "glm4_moe", + "moe_intermediate_size": 1408, + "n_group": 1, + "n_routed_experts": 128, + "n_shared_experts": 1, + "norm_topk_prob": true, + "num_attention_heads": 96, + "num_experts_per_tok": 8, + "num_hidden_layers": 46, + "num_key_value_heads": 8, + "num_nextn_predict_layers": 1, + "pad_token_id": 151329, + "partial_rotary_factor": 0.5, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000, + "routed_scaling_factor": 1.0, + "tie_word_embeddings": false, + "topk_group": 1, + "transformers_version": "4.56.1", + "use_cache": false, + "use_grouped_mm": true, + "use_qk_norm": false, + "vocab_size": 151552 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d55c441b6d30971afacbc576e9cc07874730e5c1 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,10 @@ +{ + "_from_model_config": true, + "eos_token_id": [ + 151334, + 151329 + ], + "pad_token_id": 151329, + "transformers_version": "4.56.1", + "use_cache": false +} diff --git a/model-00002-of-00048.safetensors b/model-00002-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..797308be5413658e1cd380892df989d411dc4241 --- /dev/null +++ b/model-00002-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:104dbc355f326d6a70c160e8b266c4c98109bcdd8d0eb650306bb154174dbb1f +size 4899977872 diff --git a/model-00003-of-00048.safetensors b/model-00003-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4326b043539e7cbaf61d6a43cd8d4af93b3d9bbb --- /dev/null +++ b/model-00003-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9debee3ea4386e6f545f074ea6e69fb2a0dc03cbbde04bdac8243ffc3e53e054 +size 4498785360 diff --git a/model-00004-of-00048.safetensors b/model-00004-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e889341004cee1add66a748cde1817362b71ca0e --- /dev/null +++ b/model-00004-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e62b0dcb06b6aa9a98c44fb9ea9f87ac073ddb063b5834b05e8df3da27c7a0d9 +size 4464885360 diff --git a/model-00005-of-00048.safetensors b/model-00005-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b302732e8ed50c49dc76f95bb075ebc4907d7f01 --- /dev/null +++ b/model-00005-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56af24055de6046d10c4fcc54b11cbe7a137f06e0a7a8c6df449d22e1d559159 +size 4464885360 diff --git a/model-00006-of-00048.safetensors b/model-00006-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..57b0c1d4328641b93f5edbb0f85622ae588cfbcd --- /dev/null +++ b/model-00006-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a4566a94383cb393d44d99c0d1e8b49bfd91d8bbc113efedcf95d3545fbf63c +size 4464885360 diff --git a/model-00007-of-00048.safetensors b/model-00007-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f1ac5673e5ce8b3f522f11e67a37554d330fdc1e --- /dev/null +++ b/model-00007-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:432452d0f25a3fea281e94b2da22266d7cb47476d7145e9f68a6e57ec1b961ec +size 4464885360 diff --git a/model-00008-of-00048.safetensors b/model-00008-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ceca4121da6baa1d01f818041cfa84cb4b9eb5b9 --- /dev/null +++ b/model-00008-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5699235785308951f2d5ee479b68b933c3989b1990e6300555c837079bcab1eb +size 4464885360 diff --git a/model-00009-of-00048.safetensors b/model-00009-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2a66c82d12df99257228b6074413c9ac31ad0020 --- /dev/null +++ b/model-00009-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e37ed8c418d61086b4167d0b1bbe102b5a6b7803de42142e5de55206b6946cb5 +size 4464885360 diff --git a/model-00010-of-00048.safetensors b/model-00010-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..168c78fc3cec32146e636f803c0e59d0185251eb --- /dev/null +++ b/model-00010-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fd30917e176ddb179156fe9a623dd21a0bfd40fe8665f65f662a88894c1bdba +size 4464885360 diff --git a/model-00011-of-00048.safetensors b/model-00011-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..35ad8f03cf782d5086d62705f33b717c99bd2a2c --- /dev/null +++ b/model-00011-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f31cc1121ac2837c129fc939d1265e6dbcb6ef6571f5fe1b00a0653ae26293b9 +size 4464885360 diff --git a/model-00013-of-00048.safetensors b/model-00013-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..276e6348b5b254ab6bb09a8380b3a554437f1c96 --- /dev/null +++ b/model-00013-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e08f116251b18d83d5d1f73210055614625506b016fbfbb6f6559650e23cdad0 +size 4464885752 diff --git a/model-00014-of-00048.safetensors b/model-00014-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4200637f7c0794944e60681b2ab4fc4ee6ba8841 --- /dev/null +++ b/model-00014-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b36453f057961311953e344e634acdca99e37cab58344d4de0d5534fad3687b7 +size 4464885752 diff --git a/model-00015-of-00048.safetensors b/model-00015-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f94cadfebb268aa998576f05181ae8105a4fdc2a --- /dev/null +++ b/model-00015-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f676f394bb70ed21e6e544a1a0a342b96abf90b2bb9a8a2b7bcabdab4b15e18f +size 4464885752 diff --git a/model-00016-of-00048.safetensors b/model-00016-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..63807339446aadcea65656c18d773394183cee86 --- /dev/null +++ b/model-00016-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a994d53dbc0c8587425afd114d12a13f340c65ce88c9b4c346a465de0c5821b9 +size 4464885752 diff --git a/model-00017-of-00048.safetensors b/model-00017-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7f71289624f4ab111e9bd5cf711e66c3ab9e78b4 --- /dev/null +++ b/model-00017-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d172a36c1bcdfec32f981ea2e8dd4e5b5a74e2852b8010d1e31ed1ab8247a16c +size 4464885752 diff --git a/model-00018-of-00048.safetensors b/model-00018-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9cd5858239d2a1dd04e14be98402b055434d23a9 --- /dev/null +++ b/model-00018-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afba43349377a7a0c995d084673554141fd56c07ef4a38bab987d70988de12c5 +size 4464885752 diff --git a/model-00019-of-00048.safetensors b/model-00019-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c91e00842d5ccbce7698e04713ffd82517350174 --- /dev/null +++ b/model-00019-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab3ebec5fc6d6247e804b138b7c66f40f75b44b307ab92abe20e3342157a253a +size 4464885752 diff --git a/model-00020-of-00048.safetensors b/model-00020-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6dc987c55b5b9658ac4ac9adee15ec8f07df8bbf --- /dev/null +++ b/model-00020-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a989983e8bee1a28b4eb0b7c8843fbf2f395085dac2abb699e8829d8bab2ae12 +size 4464885752 diff --git a/model-00021-of-00048.safetensors b/model-00021-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f7ade5e20ba0837200ac5257e7d7b105a3474ff8 --- /dev/null +++ b/model-00021-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d56bf35d7f9440abe70edecef6bd77318ffa24a668c1e7cb3ad9ca4ed882ec92 +size 4464885752 diff --git a/model-00023-of-00048.safetensors b/model-00023-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..28ed6d8eedd2dc926a4af22f19b683d9bb5026cd --- /dev/null +++ b/model-00023-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:539302c591fac9e654e8ddd54dfab7f7171d6b9b5c6a1c86fa8a443b72966bd4 +size 4464885752 diff --git a/model-00024-of-00048.safetensors b/model-00024-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cbc943eb64c9cfe92e9cde4a3729e86ab807a355 --- /dev/null +++ b/model-00024-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a37cac3be07040a211db088dd67f007760a0ea2f7190e03268fcd070d17cda1b +size 4464885752 diff --git a/model-00026-of-00048.safetensors b/model-00026-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..89cb54765ce59bf44dc7f08108b9c2ad35de4cb9 --- /dev/null +++ b/model-00026-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21a69fbed91134bd076c25574a365f0e2d0b993c9c6d0581249871b68021e102 +size 4464885752 diff --git a/model-00027-of-00048.safetensors b/model-00027-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8dd76365ef25068cc71ffbba57ce40a436c10d1b --- /dev/null +++ b/model-00027-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de3440e7d3f97e0a4b11169c68c9eca44e508b138816c8ce5af818d809cef08a +size 4464885752 diff --git a/model-00028-of-00048.safetensors b/model-00028-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4a3c32399ae23ed7a0695b238b37e9c6228e4ed1 --- /dev/null +++ b/model-00028-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ee98d08c4e7519d07167c5b71fe8b8b5dc1e54825b2ae7a15c0f3d30f02878b +size 4464885752 diff --git a/model-00029-of-00048.safetensors b/model-00029-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dfd10782eed9d545317b48e9c5951aaa890245d6 --- /dev/null +++ b/model-00029-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d3ead910093bc8a1cdf3a92c07a628d5e62b73c87954d3900c30a265e664e55 +size 4464885752 diff --git a/model-00030-of-00048.safetensors b/model-00030-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2714587624051b3b4e2df6063d8f78a58a523183 --- /dev/null +++ b/model-00030-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c44b69124d5d272313fd3e4963c31b1b436a0e944d4e0cbc30c88301db6190a +size 4464885752 diff --git a/model-00031-of-00048.safetensors b/model-00031-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..63c8737be4ce1f2a6da8a24ccb9fbeb52a158bd8 --- /dev/null +++ b/model-00031-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c19568f447e969bb802da05f48fd084349127d38e7cdfcba8faf98e039820af2 +size 4464885752 diff --git a/model-00032-of-00048.safetensors b/model-00032-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..94df5674e01304836d17da93b1a5c8ca0316fddd --- /dev/null +++ b/model-00032-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63be798cd5c51e203caba0d0aa48b1a20074101b9959510dc9015b2d9c511e28 +size 4464885752 diff --git a/model-00033-of-00048.safetensors b/model-00033-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a960590fd90600f24ee19fe7c177014554528bf6 --- /dev/null +++ b/model-00033-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:146841938816268e56d07d087b9ee6311be09d55860266655059edb1d7a654c7 +size 4464885752 diff --git a/model-00034-of-00048.safetensors b/model-00034-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eccb9dfbf7bd8f14b3d3710f100666b8c2cc60cf --- /dev/null +++ b/model-00034-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:296a784a6582c6166b1269fc5053f31733756e46db054e98e083e41362d9ca17 +size 4464885752 diff --git a/model-00035-of-00048.safetensors b/model-00035-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3584652ea86ff0406529bae45304287f98280379 --- /dev/null +++ b/model-00035-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05a9dc213602b19ac2c869b7ea9c2d15a6fcf5ffb666146a049207b968d5eac5 +size 4464885752 diff --git a/model-00037-of-00048.safetensors b/model-00037-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e47224efca85a71b8b1c250d167165c09c451149 --- /dev/null +++ b/model-00037-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0644306d1e294f16787d1dfa51aa5eaadbe2341fb137c3170a3723094f7f64e1 +size 4464885752 diff --git a/model-00038-of-00048.safetensors b/model-00038-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..88504f42089ea7497bcdd9cfacf5663b5285ee1f --- /dev/null +++ b/model-00038-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afe05d538e5c1b1c815c2c24c02d5e18bb9a195029a0ed36e86773af53e408b0 +size 4464885752 diff --git a/model-00039-of-00048.safetensors b/model-00039-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1a7a5320409b5238535f8c7b1cb764edec6b08ae --- /dev/null +++ b/model-00039-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52e014c091cdc08e546e7265596e5f60b8adaad701aaf2cafa6b881b279614de +size 4464885752 diff --git a/model-00040-of-00048.safetensors b/model-00040-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..23b0281dfb2a591d359d8291f37609dad3710600 --- /dev/null +++ b/model-00040-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:129ed38e7210f6dabc32a24ee741d347a0042551acf720baf2342be03555df8f +size 4464885752 diff --git a/model-00041-of-00048.safetensors b/model-00041-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1ab5df7d1cd025a80cb1713fdd1e9f0b9519ba08 --- /dev/null +++ b/model-00041-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d1f3a894adeba12303193e3db63c4d57dc6f91cca8944a04bcc25b6c7820958 +size 4464885752 diff --git a/model-00042-of-00048.safetensors b/model-00042-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bbd3738b6d9b2c493bf7ffa538e9daec3d91ffb6 --- /dev/null +++ b/model-00042-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:760ca9d524890b53d997a96d6922cf2eb2e86f9a6c02ad19fa9c9f1b51dbe7ca +size 4464885752 diff --git a/model-00043-of-00048.safetensors b/model-00043-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6bda1e302408904e48e3e20485efe4cd406799a6 --- /dev/null +++ b/model-00043-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:976d187f1617f76ec28b6ecc691519dc04076cd9924c3dd9e222c448f1862e2a +size 4464885752 diff --git a/model-00044-of-00048.safetensors b/model-00044-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6a28e7e89b967992b3d94e19eda9951b32c11a25 --- /dev/null +++ b/model-00044-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b313e5345c2824779635ac083165bbe3e5036c0086b3a0441d3f850c5ddb6a9d +size 4464885752 diff --git a/model-00045-of-00048.safetensors b/model-00045-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1dca05b63b253769bee3d22048d2b5f148959293 --- /dev/null +++ b/model-00045-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baa476468987c6de46dd87098e4b6b611f00551d7564fea35beb6713ab36300a +size 4464885752 diff --git a/model-00046-of-00048.safetensors b/model-00046-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..960c1fa2bf37c2ded87ec7818ab993ed02b356c7 --- /dev/null +++ b/model-00046-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5619708ccbf82b4642c68f5bdf2ee420aafe9a3ee001de327031d3af9e240295 +size 4464885752 diff --git a/model-00047-of-00048.safetensors b/model-00047-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9b6f83dd469f2b545a9dce4a23c7860315dff6c1 --- /dev/null +++ b/model-00047-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0de71ee00821df877e97eafd981f07eda614790236158e81100561d9cae3497 +size 4464885752 diff --git a/model-00048-of-00048.safetensors b/model-00048-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..33e1acacd6240d3674a82f7ff9956f82bf2fff4e --- /dev/null +++ b/model-00048-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e48631a2945b8c3f7c1a722832dd261ab2c85c3c043df8cceaa7dc8c779c7c09 +size 2952821896 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..834d515870f7cc29f01a58ff380a0e8111f1b32b --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,17932 @@ +{ + "metadata": { + "total_size": 213704514048 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00048.safetensors", + "model.embed_tokens.weight": "model-00001-of-00048.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.1.mlp.experts.0.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.0.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.1.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.1.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.10.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.10.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.100.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.100.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.100.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.101.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.101.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.101.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.102.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.102.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.102.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.103.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.103.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.103.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.104.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.104.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.104.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.105.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.105.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.105.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.106.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.106.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.106.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.107.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.107.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.107.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.108.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.108.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.108.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.109.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.109.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.109.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.11.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.11.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.110.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.110.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.110.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.111.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.111.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.111.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.112.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.112.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.112.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.113.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.113.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.113.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.114.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.114.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.114.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.115.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.115.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.115.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.116.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.116.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.116.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.117.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.117.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.117.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.118.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.118.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.118.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.119.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.119.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.119.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.12.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.12.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.120.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.120.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.120.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.121.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.121.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.121.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.122.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.122.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.122.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.123.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.123.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.123.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.124.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.124.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.124.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.125.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.125.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.125.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.126.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.126.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.126.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.127.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.127.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.127.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.13.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.13.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.14.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.14.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.15.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.15.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.16.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.16.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.17.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.17.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.18.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.18.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.19.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.19.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.2.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.2.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.20.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.20.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.21.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.21.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.22.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.22.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.23.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.23.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.24.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.24.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.25.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.25.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.26.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.26.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.27.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.27.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.28.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.28.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.29.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.29.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.3.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.3.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.30.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.30.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.31.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.31.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.32.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.32.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.33.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.33.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.34.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.34.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.35.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.35.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.36.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.36.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.37.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.37.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.38.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.38.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.39.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.39.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.4.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.4.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.40.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.40.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.41.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.41.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.42.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.42.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.43.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.43.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.44.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.44.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.45.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.45.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.46.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.46.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.47.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.47.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.48.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.48.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.49.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.49.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.5.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.5.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.50.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.50.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.51.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.51.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.52.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.52.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.53.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.53.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.54.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.54.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.55.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.55.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.56.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.56.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.57.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.57.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.58.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.58.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.59.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.59.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.6.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.6.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.60.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.60.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.61.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.61.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.62.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.62.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.63.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.63.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.64.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.64.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.64.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.65.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.65.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.65.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.66.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.66.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.66.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.67.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.67.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.67.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.68.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.68.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.68.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.69.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.69.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.69.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.7.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.7.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.70.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.70.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.70.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.71.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.71.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.71.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.72.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.72.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.72.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.73.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.73.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.73.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.74.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.74.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.74.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.75.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.75.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.75.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.76.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.76.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.76.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.77.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.77.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.77.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.78.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.78.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.78.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.79.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.79.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.79.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.8.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.8.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.80.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.80.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.80.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.81.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.81.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.81.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.82.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.82.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.82.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.83.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.83.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.83.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.84.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.84.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.84.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.85.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.85.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.85.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.86.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.86.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.86.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.87.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.87.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.87.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.88.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.88.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.88.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.89.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.89.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.89.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.9.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.9.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.90.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.90.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.90.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.91.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.91.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.91.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.92.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.92.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.92.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.93.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.93.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.93.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.94.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.94.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.94.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.95.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.95.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.95.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.96.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.96.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.96.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.97.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.97.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.97.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.98.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.98.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.98.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.99.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.99.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.99.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.gate.e_score_correction_bias": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.gate.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.10.mlp.experts.0.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.0.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.1.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.1.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.10.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.10.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.100.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.100.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.100.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.101.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.101.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.101.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.102.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.102.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.102.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.103.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.103.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.103.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.104.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.104.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.104.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.105.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.105.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.105.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.106.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.106.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.106.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.107.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.107.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.107.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.108.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.108.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.108.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.109.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.109.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.109.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.11.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.11.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.110.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.110.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.110.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.111.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.111.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.111.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.112.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.112.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.112.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.113.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.113.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.113.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.114.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.114.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.114.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.115.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.115.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.115.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.116.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.116.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.116.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.117.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.117.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.117.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.118.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.118.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.118.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.119.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.119.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.119.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.12.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.12.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.120.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.120.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.120.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.121.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.121.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.121.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.122.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.122.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.122.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.123.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.123.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.123.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.124.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.124.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.124.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.125.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.125.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.125.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.126.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.126.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.126.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.127.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.127.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.127.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.13.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.13.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.14.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.14.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.15.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.15.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.16.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.16.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.17.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.17.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.18.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.18.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.19.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.19.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.2.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.2.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.20.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.20.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.21.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.21.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.22.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.22.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.23.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.23.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.24.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.24.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.25.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.25.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.26.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.26.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.27.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.27.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.28.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.28.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.29.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.29.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.3.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.3.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.30.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.30.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.31.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.31.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.32.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.32.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.33.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.33.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.34.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.34.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.35.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.35.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.36.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.36.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.37.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.37.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.38.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.38.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.39.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.39.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.4.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.4.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.40.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.40.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.41.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.41.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.42.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.42.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.43.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.43.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.44.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.44.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.45.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.45.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.46.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.46.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.47.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.47.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.48.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.48.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.49.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.49.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.5.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.5.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.50.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.50.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.51.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.51.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.52.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.52.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.53.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.53.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.54.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.54.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.55.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.55.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.56.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.56.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.57.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.57.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.58.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.58.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.59.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.59.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.6.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.6.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.60.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.60.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.61.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.61.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.62.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.62.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.63.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.63.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.64.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.64.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.64.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.65.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.65.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.65.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.66.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.66.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.66.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.67.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.67.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.67.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.68.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.68.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.68.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.69.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.69.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.69.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.7.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.7.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.70.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.70.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.70.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.71.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.71.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.71.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.72.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.72.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.72.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.73.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.73.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.73.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.74.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.74.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.74.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.75.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.75.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.75.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.76.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.76.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.76.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.77.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.77.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.77.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.78.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.78.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.78.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.79.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.79.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.79.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.8.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.8.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.80.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.80.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.80.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.81.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.81.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.81.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.82.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.82.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.82.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.83.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.83.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.83.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.84.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.84.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.84.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.85.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.85.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.85.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.86.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.86.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.86.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.87.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.87.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.87.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.88.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.88.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.88.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.89.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.89.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.89.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.9.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.9.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.90.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.90.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.90.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.91.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.91.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.91.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.92.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.92.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.92.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.93.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.93.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.93.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.94.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.94.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.94.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.95.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.95.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.95.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.96.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.96.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.96.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.97.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.97.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.97.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.98.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.98.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.98.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.99.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.99.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.99.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.gate.e_score_correction_bias": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.gate.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.11.mlp.experts.0.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.0.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.1.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.1.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.10.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.10.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.100.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.100.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.100.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.101.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.101.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.101.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.102.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.102.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.102.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.103.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.103.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.103.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.104.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.104.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.104.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.105.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.105.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.105.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.106.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.106.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.106.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.107.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.107.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.107.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.108.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.108.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.108.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.109.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.109.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.109.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.11.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.11.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.110.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.110.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.110.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.111.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.111.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.111.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.112.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.112.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.112.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.113.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.113.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.113.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.114.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.114.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.114.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.115.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.115.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.115.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.116.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.116.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.116.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.117.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.117.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.117.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.118.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.118.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.118.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.119.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.119.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.119.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.12.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.12.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.120.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.120.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.120.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.121.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.121.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.121.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.122.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.122.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.122.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.123.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.123.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.123.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.124.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.124.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.124.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.125.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.125.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.125.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.126.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.126.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.126.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.127.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.127.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.127.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.13.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.13.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.14.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.14.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.15.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.15.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.16.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.16.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.17.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.17.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.18.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.18.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.19.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.19.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.2.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.2.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.20.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.20.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.21.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.21.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.22.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.22.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.23.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.23.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.24.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.24.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.25.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.25.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.26.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.26.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.27.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.27.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.28.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.28.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.29.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.29.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.3.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.3.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.30.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.30.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.31.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.31.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.32.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.32.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.33.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.33.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.34.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.34.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.35.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.35.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.36.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.36.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.37.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.37.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.38.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.38.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.39.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.39.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.4.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.4.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.40.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.40.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.41.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.41.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.42.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.42.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.43.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.43.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.44.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.44.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.45.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.45.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.46.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.46.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.47.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.47.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.48.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.48.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.49.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.49.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.5.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.5.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.50.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.50.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.51.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.51.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.52.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.52.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.53.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.53.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.54.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.54.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.55.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.55.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.56.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.56.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.57.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.57.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.58.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.58.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.59.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.59.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.6.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.6.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.60.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.60.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.61.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.61.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.62.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.62.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.63.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.63.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.64.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.64.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.64.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.65.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.65.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.65.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.66.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.66.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.66.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.67.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.67.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.67.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.68.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.68.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.68.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.69.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.69.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.69.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.7.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.7.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.70.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.70.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.70.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.71.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.71.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.71.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.72.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.72.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.72.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.73.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.73.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.73.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.74.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.74.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.74.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.75.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.75.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.75.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.76.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.76.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.76.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.77.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.77.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.77.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.78.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.78.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.78.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.79.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.79.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.79.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.8.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.8.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.80.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.80.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.80.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.81.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.81.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.81.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.82.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.82.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.82.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.83.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.83.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.83.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.84.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.84.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.84.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.85.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.85.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.85.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.86.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.86.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.86.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.87.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.87.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.87.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.88.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.88.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.88.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.89.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.89.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.89.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.9.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.9.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.90.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.90.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.90.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.91.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.91.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.91.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.92.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.92.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.92.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.93.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.93.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.93.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.94.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.94.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.94.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.95.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.95.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.95.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.96.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.96.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.96.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.97.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.97.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.97.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.98.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.98.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.98.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.99.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.99.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.99.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.gate.e_score_correction_bias": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.gate.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.12.mlp.experts.0.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.0.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.1.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.1.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.10.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.10.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.100.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.100.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.100.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.101.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.101.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.101.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.102.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.102.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.102.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.103.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.103.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.103.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.104.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.104.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.104.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.105.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.105.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.105.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.106.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.106.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.106.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.107.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.107.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.107.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.108.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.108.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.108.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.109.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.109.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.109.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.11.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.11.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.110.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.110.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.110.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.111.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.111.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.111.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.112.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.112.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.112.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.113.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.113.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.113.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.114.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.114.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.114.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.115.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.115.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.115.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.116.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.116.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.116.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.117.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.117.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.117.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.118.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.118.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.118.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.119.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.119.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.119.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.12.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.12.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.120.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.120.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.120.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.121.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.121.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.121.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.122.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.122.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.122.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.123.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.123.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.123.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.124.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.124.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.124.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.125.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.125.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.125.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.126.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.126.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.126.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.127.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.127.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.127.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.13.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.13.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.14.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.14.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.15.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.15.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.16.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.16.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.17.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.17.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.18.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.18.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.19.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.19.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.2.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.2.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.20.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.20.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.21.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.21.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.22.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.22.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.23.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.23.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.24.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.24.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.25.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.25.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.26.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.26.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.27.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.27.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.28.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.28.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.29.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.29.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.3.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.3.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.30.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.30.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.31.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.31.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.32.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.32.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.33.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.33.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.34.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.34.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.35.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.35.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.36.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.36.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.37.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.37.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.38.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.38.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.39.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.39.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.4.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.4.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.40.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.40.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.41.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.41.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.42.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.42.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.43.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.43.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.44.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.44.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.45.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.45.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.46.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.46.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.47.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.47.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.48.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.48.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.49.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.49.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.5.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.5.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.50.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.50.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.51.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.51.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.52.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.52.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.53.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.53.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.54.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.54.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.55.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.55.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.56.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.56.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.57.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.57.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.58.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.58.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.6.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.6.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.60.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.60.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.61.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.61.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.62.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.62.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.63.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.63.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.64.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.64.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.64.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.65.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.65.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.65.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.66.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.66.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.66.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.67.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.67.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.67.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.68.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.68.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.68.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.69.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.69.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.69.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.7.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.7.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.70.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.70.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.70.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.71.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.71.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.71.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.72.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.72.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.72.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.73.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.73.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.73.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.74.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.74.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.74.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.75.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.75.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.75.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.76.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.76.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.76.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.77.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.77.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.77.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.78.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.78.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.78.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.79.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.79.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.79.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.8.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.8.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.80.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.80.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.80.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.81.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.81.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.81.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.82.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.82.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.82.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.83.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.83.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.83.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.84.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.84.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.84.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.85.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.85.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.85.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.86.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.86.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.86.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.87.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.87.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.87.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.88.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.88.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.88.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.89.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.89.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.89.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.9.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.9.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.90.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.90.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.90.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.91.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.91.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.91.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.92.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.92.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.92.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.93.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.93.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.93.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.94.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.94.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.94.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.95.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.95.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.95.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.96.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.96.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.96.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.97.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.97.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.97.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.98.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.98.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.98.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.99.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.99.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.99.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.gate.e_score_correction_bias": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.gate.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.100.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.100.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.100.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.101.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.101.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.101.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.102.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.102.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.102.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.103.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.103.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.103.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.104.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.104.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.104.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.105.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.105.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.105.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.106.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.106.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.106.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.107.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.107.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.107.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.108.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.108.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.108.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.109.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.109.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.109.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.110.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.110.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.110.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.111.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.111.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.111.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.112.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.112.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.112.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.113.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.113.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.113.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.114.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.114.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.114.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.115.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.115.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.115.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.116.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.116.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.116.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.117.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.117.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.117.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.118.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.118.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.118.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.119.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.119.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.119.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.120.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.120.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.120.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.121.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.121.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.121.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.122.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.122.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.122.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.123.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.123.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.123.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.124.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.124.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.124.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.125.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.125.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.125.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.126.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.126.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.126.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.127.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.127.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.127.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.60.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.60.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.61.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.61.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.62.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.62.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.63.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.63.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.64.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.64.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.64.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.65.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.65.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.65.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.66.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.66.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.66.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.67.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.67.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.67.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.68.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.68.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.68.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.69.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.69.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.69.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.70.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.70.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.70.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.71.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.71.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.71.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.72.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.72.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.72.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.73.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.73.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.73.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.74.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.74.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.74.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.75.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.75.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.75.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.76.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.76.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.76.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.77.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.77.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.77.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.78.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.78.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.78.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.79.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.79.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.79.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.80.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.80.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.80.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.81.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.81.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.81.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.82.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.82.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.82.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.83.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.83.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.83.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.84.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.84.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.84.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.85.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.85.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.85.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.86.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.86.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.86.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.87.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.87.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.87.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.88.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.88.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.88.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.89.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.89.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.89.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.90.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.90.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.90.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.91.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.91.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.91.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.92.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.92.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.92.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.93.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.93.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.93.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.94.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.94.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.94.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.95.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.95.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.95.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.96.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.96.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.96.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.97.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.97.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.97.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.98.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.98.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.98.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.99.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.99.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.99.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.gate.e_score_correction_bias": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.gate.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.14.mlp.experts.0.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.0.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.1.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.1.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.10.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.10.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.100.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.100.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.100.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.101.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.101.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.101.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.102.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.102.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.102.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.103.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.103.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.103.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.104.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.104.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.104.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.105.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.105.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.105.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.106.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.106.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.106.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.107.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.107.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.107.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.108.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.108.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.108.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.109.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.109.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.109.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.11.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.11.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.110.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.110.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.110.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.111.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.111.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.111.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.112.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.112.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.112.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.113.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.113.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.113.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.114.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.114.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.114.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.115.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.115.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.115.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.116.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.116.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.116.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.117.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.117.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.117.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.118.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.118.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.118.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.119.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.119.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.119.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.12.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.12.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.120.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.120.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.120.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.121.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.121.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.121.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.122.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.122.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.122.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.123.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.123.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.123.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.124.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.124.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.124.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.125.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.125.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.125.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.126.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.126.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.126.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.127.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.127.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.127.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.13.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.13.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.14.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.14.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.15.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.15.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.16.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.16.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.17.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.17.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.18.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.18.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.19.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.19.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.2.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.2.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.20.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.20.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.21.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.21.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.22.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.22.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.23.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.23.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.24.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.24.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.25.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.25.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.26.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.26.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.27.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.27.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.28.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.28.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.29.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.29.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.3.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.3.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.30.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.30.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.31.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.31.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.32.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.32.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.33.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.33.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.34.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.34.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.35.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.35.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.36.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.36.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.37.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.37.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.38.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.38.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.39.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.39.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.4.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.4.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.40.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.40.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.41.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.41.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.42.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.42.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.43.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.43.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.44.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.44.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.45.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.45.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.46.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.46.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.47.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.47.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.48.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.48.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.49.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.49.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.5.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.5.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.50.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.50.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.51.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.51.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.52.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.52.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.53.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.53.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.54.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.54.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.55.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.55.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.56.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.56.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.57.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.57.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.58.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.58.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.59.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.59.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.6.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.6.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.60.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.60.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.61.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.61.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.62.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.62.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.63.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.63.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.64.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.64.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.64.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.65.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.65.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.65.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.66.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.66.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.66.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.67.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.67.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.67.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.68.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.68.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.68.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.69.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.69.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.69.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.7.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.7.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.70.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.70.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.70.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.71.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.71.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.71.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.72.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.72.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.72.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.73.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.73.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.73.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.74.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.74.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.74.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.75.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.75.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.75.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.76.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.76.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.76.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.77.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.77.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.77.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.78.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.78.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.78.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.79.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.79.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.79.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.8.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.8.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.80.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.80.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.80.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.81.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.81.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.81.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.82.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.82.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.82.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.83.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.83.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.83.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.84.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.84.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.84.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.85.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.85.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.85.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.86.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.86.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.86.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.87.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.87.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.87.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.88.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.88.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.88.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.89.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.89.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.89.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.9.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.9.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.90.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.90.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.90.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.91.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.91.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.91.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.92.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.92.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.92.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.93.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.93.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.93.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.94.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.94.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.94.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.95.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.95.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.95.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.96.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.96.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.96.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.97.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.97.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.97.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.98.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.98.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.98.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.99.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.99.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.99.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.gate.e_score_correction_bias": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.gate.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.15.mlp.experts.0.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.0.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.1.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.1.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.10.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.10.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.100.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.100.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.100.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.101.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.101.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.101.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.102.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.102.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.102.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.103.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.103.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.103.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.104.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.104.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.104.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.105.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.105.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.105.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.106.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.106.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.106.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.107.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.107.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.107.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.108.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.108.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.108.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.109.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.109.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.109.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.11.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.11.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.110.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.110.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.110.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.111.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.111.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.111.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.112.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.112.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.112.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.113.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.113.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.113.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.114.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.114.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.114.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.115.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.115.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.115.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.116.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.116.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.116.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.117.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.117.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.117.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.118.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.118.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.118.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.119.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.119.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.119.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.12.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.12.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.120.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.120.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.120.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.121.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.121.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.121.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.122.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.122.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.122.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.123.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.123.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.123.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.124.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.124.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.124.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.125.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.125.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.125.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.126.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.126.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.126.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.127.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.127.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.127.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.13.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.13.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.14.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.14.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.15.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.15.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.16.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.16.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.17.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.17.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.18.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.18.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.19.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.19.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.2.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.2.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.20.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.20.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.21.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.21.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.22.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.22.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.23.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.23.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.24.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.24.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.25.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.25.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.26.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.26.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.27.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.27.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.28.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.28.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.29.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.29.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.3.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.3.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.30.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.30.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.31.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.31.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.32.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.32.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.33.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.33.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.34.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.34.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.35.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.35.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.36.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.36.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.37.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.37.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.38.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.38.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.39.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.39.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.4.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.4.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.40.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.40.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.41.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.41.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.42.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.42.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.43.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.43.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.44.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.44.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.45.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.45.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.46.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.46.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.47.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.47.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.48.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.48.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.49.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.49.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.5.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.5.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.50.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.50.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.51.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.51.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.52.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.52.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.53.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.53.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.54.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.54.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.55.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.55.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.56.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.56.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.57.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.57.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.58.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.58.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.59.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.59.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.6.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.6.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.60.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.60.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.61.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.61.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.62.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.62.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.63.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.63.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.64.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.64.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.64.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.65.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.65.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.65.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.66.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.66.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.66.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.67.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.67.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.67.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.68.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.68.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.68.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.69.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.69.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.69.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.7.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.7.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.70.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.70.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.70.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.71.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.71.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.71.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.72.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.72.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.72.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.73.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.73.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.73.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.74.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.74.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.74.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.75.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.75.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.75.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.76.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.76.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.76.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.77.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.77.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.77.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.78.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.78.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.78.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.79.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.79.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.79.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.8.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.8.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.80.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.80.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.80.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.81.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.81.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.81.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.82.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.82.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.82.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.83.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.83.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.83.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.84.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.84.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.84.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.85.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.85.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.85.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.86.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.86.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.86.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.87.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.87.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.87.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.88.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.88.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.88.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.89.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.89.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.89.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.9.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.9.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.90.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.90.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.90.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.91.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.91.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.91.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.92.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.92.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.92.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.93.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.93.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.93.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.94.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.94.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.94.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.95.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.95.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.95.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.96.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.96.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.96.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.97.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.97.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.97.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.98.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.98.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.98.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.99.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.99.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.99.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.gate.e_score_correction_bias": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.gate.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.16.mlp.experts.0.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.0.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.1.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.1.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.10.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.10.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.100.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.100.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.100.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.101.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.101.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.101.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.102.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.102.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.102.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.103.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.103.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.103.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.104.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.104.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.104.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.105.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.105.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.105.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.106.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.106.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.106.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.107.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.107.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.107.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.108.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.108.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.108.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.109.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.109.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.109.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.11.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.11.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.110.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.110.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.110.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.111.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.111.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.111.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.112.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.112.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.112.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.113.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.113.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.113.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.114.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.114.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.114.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.115.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.115.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.115.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.116.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.116.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.116.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.117.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.117.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.117.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.118.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.118.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.118.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.119.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.119.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.119.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.12.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.12.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.120.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.120.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.120.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.121.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.121.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.121.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.122.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.122.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.122.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.123.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.123.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.123.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.124.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.124.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.124.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.125.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.125.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.125.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.126.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.126.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.126.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.127.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.127.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.127.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.13.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.13.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.14.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.14.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.15.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.15.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.16.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.16.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.17.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.17.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.18.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.18.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.19.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.19.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.2.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.2.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.20.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.20.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.21.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.21.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.22.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.22.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.23.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.23.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.24.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.24.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.25.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.25.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.26.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.26.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.27.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.27.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.28.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.28.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.29.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.29.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.3.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.3.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.30.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.30.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.31.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.31.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.32.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.32.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.33.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.33.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.34.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.34.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.35.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.35.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.36.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.36.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.37.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.37.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.38.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.38.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.39.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.39.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.4.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.4.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.40.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.40.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.41.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.41.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.42.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.42.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.43.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.43.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.44.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.44.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.45.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.45.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.46.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.46.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.47.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.47.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.48.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.48.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.49.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.49.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.5.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.5.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.50.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.50.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.51.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.51.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.52.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.52.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.53.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.53.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.54.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.54.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.55.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.55.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.56.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.56.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.57.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.57.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.58.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.58.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.59.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.59.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.6.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.6.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.60.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.60.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.61.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.61.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.62.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.62.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.63.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.63.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.64.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.64.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.64.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.65.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.65.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.65.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.66.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.66.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.66.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.67.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.67.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.67.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.68.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.68.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.68.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.69.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.69.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.69.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.7.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.7.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.70.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.70.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.70.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.71.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.71.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.71.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.72.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.72.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.72.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.73.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.73.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.73.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.74.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.74.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.74.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.75.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.75.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.75.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.76.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.76.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.76.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.77.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.77.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.77.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.78.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.78.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.78.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.79.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.79.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.79.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.8.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.8.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.80.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.80.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.80.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.81.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.81.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.81.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.82.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.82.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.82.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.83.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.83.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.83.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.84.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.84.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.84.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.85.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.85.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.85.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.86.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.86.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.86.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.87.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.87.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.87.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.88.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.88.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.88.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.89.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.89.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.89.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.9.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.9.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.90.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.90.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.90.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.91.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.91.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.91.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.92.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.92.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.92.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.93.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.93.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.93.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.94.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.94.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.94.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.95.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.95.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.95.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.96.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.96.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.96.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.97.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.97.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.97.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.98.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.98.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.98.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.99.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.99.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.99.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.gate.e_score_correction_bias": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.gate.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.17.mlp.experts.0.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.0.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.1.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.1.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.10.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.10.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.100.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.100.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.100.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.101.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.101.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.101.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.102.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.102.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.102.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.103.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.103.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.103.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.104.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.104.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.104.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.105.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.105.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.105.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.106.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.106.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.106.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.107.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.107.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.107.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.108.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.108.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.108.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.109.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.109.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.109.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.11.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.11.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.110.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.110.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.110.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.111.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.111.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.111.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.112.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.112.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.112.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.113.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.113.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.113.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.114.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.114.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.114.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.115.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.115.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.115.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.116.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.116.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.116.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.117.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.117.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.117.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.118.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.118.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.118.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.119.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.119.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.119.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.12.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.12.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.120.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.120.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.120.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.121.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.121.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.121.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.122.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.122.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.122.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.123.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.123.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.123.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.124.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.124.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.124.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.125.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.125.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.125.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.126.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.126.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.126.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.127.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.127.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.127.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.13.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.13.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.14.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.14.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.15.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.15.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.16.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.16.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.17.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.17.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.18.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.18.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.19.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.19.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.2.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.2.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.20.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.20.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.21.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.21.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.22.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.22.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.23.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.23.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.24.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.24.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.25.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.25.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.26.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.26.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.27.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.27.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.28.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.28.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.29.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.29.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.3.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.3.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.30.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.30.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.31.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.31.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.32.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.32.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.33.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.33.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.34.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.34.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.35.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.35.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.36.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.36.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.37.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.37.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.38.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.38.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.39.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.39.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.4.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.4.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.40.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.40.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.41.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.41.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.42.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.42.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.43.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.43.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.44.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.44.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.45.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.45.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.46.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.46.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.47.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.47.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.48.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.48.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.49.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.49.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.5.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.5.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.50.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.50.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.51.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.51.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.52.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.52.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.53.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.53.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.54.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.54.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.55.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.55.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.56.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.56.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.57.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.57.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.58.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.58.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.59.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.59.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.6.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.6.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.60.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.60.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.61.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.61.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.62.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.62.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.63.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.63.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.64.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.64.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.64.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.65.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.65.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.65.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.66.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.66.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.66.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.67.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.67.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.67.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.68.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.68.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.68.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.69.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.69.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.69.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.7.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.7.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.70.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.70.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.70.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.71.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.71.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.71.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.72.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.72.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.72.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.73.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.73.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.73.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.74.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.74.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.74.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.75.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.75.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.75.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.76.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.76.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.76.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.77.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.77.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.77.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.78.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.78.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.78.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.79.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.79.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.79.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.8.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.8.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.80.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.80.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.80.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.81.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.81.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.81.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.82.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.82.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.82.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.83.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.83.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.83.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.84.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.84.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.84.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.85.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.85.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.85.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.86.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.86.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.86.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.87.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.87.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.87.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.88.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.88.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.88.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.89.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.89.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.89.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.9.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.9.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.90.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.90.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.90.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.91.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.91.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.91.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.92.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.92.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.92.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.93.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.93.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.93.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.94.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.94.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.94.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.95.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.95.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.95.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.96.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.96.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.96.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.97.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.97.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.97.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.98.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.98.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.98.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.99.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.99.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.99.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.gate.e_score_correction_bias": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.gate.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.18.mlp.experts.0.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.0.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.1.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.1.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.10.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.10.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.100.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.100.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.100.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.101.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.101.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.101.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.102.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.102.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.102.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.103.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.103.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.103.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.104.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.104.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.104.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.105.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.105.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.105.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.106.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.106.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.106.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.107.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.107.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.107.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.108.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.108.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.108.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.109.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.109.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.109.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.11.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.11.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.110.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.110.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.110.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.111.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.111.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.111.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.112.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.112.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.112.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.113.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.113.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.113.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.114.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.114.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.114.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.115.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.115.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.115.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.116.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.116.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.116.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.117.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.117.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.117.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.118.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.118.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.118.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.119.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.119.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.119.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.12.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.12.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.120.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.120.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.120.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.121.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.121.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.121.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.122.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.122.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.122.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.123.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.123.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.123.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.124.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.124.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.124.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.125.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.125.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.125.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.126.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.126.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.126.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.127.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.127.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.127.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.13.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.13.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.14.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.14.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.15.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.15.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.16.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.16.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.17.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.17.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.18.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.18.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.19.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.19.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.2.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.2.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.20.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.20.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.21.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.21.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.22.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.22.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.23.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.23.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.24.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.24.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.25.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.25.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.26.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.26.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.27.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.27.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.28.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.28.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.29.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.29.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.3.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.3.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.30.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.30.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.31.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.31.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.32.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.32.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.33.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.33.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.34.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.34.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.35.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.35.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.36.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.36.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.37.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.37.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.38.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.38.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.39.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.39.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.4.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.4.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.40.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.40.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.41.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.41.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.42.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.42.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.43.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.43.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.44.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.44.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.45.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.45.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.46.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.46.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.47.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.47.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.48.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.48.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.49.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.49.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.5.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.5.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.50.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.50.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.51.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.51.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.52.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.52.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.53.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.53.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.54.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.54.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.55.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.55.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.56.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.56.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.57.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.57.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.58.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.58.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.59.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.59.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.6.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.6.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.60.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.60.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.61.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.61.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.62.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.62.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.63.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.63.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.64.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.64.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.64.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.65.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.65.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.65.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.66.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.66.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.66.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.67.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.67.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.67.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.68.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.68.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.68.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.69.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.69.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.69.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.7.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.7.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.70.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.70.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.70.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.71.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.71.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.71.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.72.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.72.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.72.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.73.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.73.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.73.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.74.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.74.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.74.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.75.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.75.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.75.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.76.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.76.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.76.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.77.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.77.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.77.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.78.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.78.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.78.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.79.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.79.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.79.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.8.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.8.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.80.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.80.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.80.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.81.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.81.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.81.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.82.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.82.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.82.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.83.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.83.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.83.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.84.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.84.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.84.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.85.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.85.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.85.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.86.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.86.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.86.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.87.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.87.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.87.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.88.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.88.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.88.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.89.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.89.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.89.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.9.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.9.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.90.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.90.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.90.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.91.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.91.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.91.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.92.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.92.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.92.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.93.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.93.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.93.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.94.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.94.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.94.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.95.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.95.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.95.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.96.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.96.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.96.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.97.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.97.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.97.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.98.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.98.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.98.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.99.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.99.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.99.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.gate.e_score_correction_bias": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.gate.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.19.mlp.experts.0.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.0.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.1.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.1.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.10.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.10.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.100.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.100.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.100.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.101.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.101.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.101.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.102.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.102.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.102.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.103.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.103.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.103.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.104.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.104.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.104.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.105.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.105.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.105.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.106.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.106.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.106.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.107.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.107.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.107.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.108.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.108.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.108.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.109.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.109.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.109.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.11.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.11.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.110.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.110.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.110.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.111.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.111.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.111.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.112.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.112.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.112.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.113.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.113.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.113.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.114.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.114.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.114.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.115.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.115.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.115.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.116.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.116.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.116.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.117.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.117.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.117.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.118.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.118.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.118.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.119.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.119.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.119.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.12.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.12.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.120.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.120.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.120.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.121.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.121.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.121.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.122.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.122.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.122.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.123.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.123.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.123.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.124.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.124.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.124.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.125.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.125.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.125.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.126.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.126.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.126.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.127.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.127.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.127.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.13.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.13.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.14.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.14.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.15.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.15.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.16.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.16.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.17.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.17.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.18.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.18.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.19.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.19.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.2.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.2.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.20.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.20.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.21.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.21.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.22.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.22.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.23.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.23.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.24.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.24.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.25.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.25.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.26.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.26.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.27.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.27.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.28.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.28.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.29.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.29.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.3.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.3.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.30.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.30.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.31.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.31.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.32.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.32.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.33.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.33.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.34.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.34.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.35.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.35.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.36.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.36.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.37.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.37.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.38.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.38.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.39.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.39.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.4.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.4.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.40.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.40.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.41.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.41.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.42.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.42.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.43.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.43.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.44.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.44.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.45.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.45.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.46.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.46.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.47.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.47.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.48.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.48.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.49.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.49.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.5.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.5.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.50.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.50.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.51.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.51.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.52.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.52.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.53.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.53.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.54.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.54.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.55.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.55.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.56.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.56.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.57.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.57.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.58.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.58.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.59.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.59.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.6.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.6.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.60.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.60.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.61.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.61.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.62.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.62.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.63.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.63.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.64.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.64.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.64.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.65.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.65.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.65.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.66.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.66.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.66.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.67.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.67.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.67.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.68.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.68.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.68.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.69.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.69.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.69.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.7.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.7.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.70.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.70.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.70.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.71.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.71.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.71.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.72.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.72.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.72.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.73.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.73.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.73.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.74.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.74.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.74.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.75.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.75.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.75.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.76.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.76.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.76.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.77.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.77.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.77.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.78.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.78.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.78.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.79.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.79.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.79.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.8.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.8.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.80.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.80.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.80.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.81.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.81.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.81.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.82.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.82.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.82.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.83.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.83.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.83.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.84.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.84.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.84.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.85.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.85.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.85.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.86.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.86.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.86.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.87.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.87.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.87.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.88.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.88.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.88.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.89.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.89.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.89.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.9.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.9.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.90.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.90.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.90.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.91.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.91.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.91.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.92.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.92.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.92.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.93.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.93.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.93.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.94.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.94.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.94.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.95.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.95.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.95.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.96.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.96.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.96.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.97.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.97.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.97.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.98.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.98.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.98.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.99.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.99.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.99.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.gate.e_score_correction_bias": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.gate.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.2.mlp.experts.0.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.0.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.1.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.1.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.10.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.10.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.100.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.100.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.100.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.101.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.101.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.101.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.102.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.102.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.102.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.103.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.103.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.103.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.104.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.104.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.104.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.105.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.105.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.105.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.106.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.106.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.106.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.107.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.107.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.107.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.108.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.108.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.108.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.109.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.109.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.109.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.11.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.11.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.110.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.110.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.110.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.111.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.111.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.111.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.112.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.112.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.112.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.113.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.113.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.113.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.114.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.114.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.114.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.115.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.115.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.115.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.116.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.116.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.116.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.117.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.117.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.117.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.118.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.118.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.118.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.119.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.119.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.119.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.12.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.12.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.120.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.120.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.120.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.121.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.121.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.121.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.122.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.122.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.122.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.123.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.123.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.123.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.124.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.124.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.124.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.125.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.125.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.125.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.126.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.126.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.126.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.127.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.127.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.127.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.13.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.13.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.14.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.14.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.15.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.15.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.16.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.16.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.17.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.17.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.18.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.18.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.19.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.19.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.2.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.2.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.20.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.20.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.21.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.21.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.22.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.22.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.23.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.23.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.24.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.24.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.25.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.25.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.26.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.26.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.27.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.27.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.28.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.28.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.29.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.29.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.3.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.3.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.30.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.30.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.31.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.31.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.32.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.32.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.33.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.33.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.34.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.34.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.35.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.35.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.36.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.36.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.37.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.37.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.38.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.38.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.39.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.39.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.4.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.4.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.40.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.40.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.41.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.41.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.42.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.42.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.43.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.43.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.44.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.44.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.45.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.45.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.46.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.46.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.47.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.47.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.48.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.48.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.49.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.49.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.5.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.5.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.50.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.50.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.51.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.51.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.52.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.52.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.53.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.53.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.54.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.54.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.55.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.55.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.56.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.56.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.57.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.57.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.58.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.58.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.59.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.59.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.6.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.6.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.60.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.60.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.61.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.61.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.62.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.62.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.63.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.63.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.64.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.64.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.64.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.65.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.65.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.65.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.66.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.66.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.66.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.67.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.67.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.67.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.68.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.68.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.68.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.69.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.69.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.69.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.7.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.7.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.70.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.70.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.70.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.71.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.71.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.71.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.72.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.72.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.72.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.73.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.73.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.73.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.74.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.74.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.74.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.75.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.75.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.75.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.76.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.76.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.76.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.77.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.77.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.77.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.78.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.78.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.78.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.79.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.79.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.79.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.8.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.8.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.80.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.80.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.80.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.81.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.81.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.81.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.82.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.82.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.82.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.83.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.83.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.83.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.84.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.84.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.84.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.85.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.85.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.85.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.86.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.86.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.86.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.87.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.87.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.87.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.88.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.88.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.88.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.89.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.89.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.89.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.9.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.9.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.90.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.90.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.90.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.91.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.91.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.91.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.92.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.92.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.92.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.93.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.93.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.93.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.94.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.94.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.94.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.95.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.95.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.95.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.96.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.96.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.96.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.97.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.97.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.97.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.98.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.98.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.98.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.99.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.99.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.99.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.gate.e_score_correction_bias": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.gate.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.20.mlp.experts.0.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.0.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.1.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.1.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.10.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.10.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.100.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.100.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.100.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.101.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.101.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.101.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.102.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.102.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.102.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.103.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.103.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.103.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.104.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.104.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.104.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.105.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.105.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.105.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.106.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.106.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.106.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.107.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.107.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.107.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.108.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.108.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.108.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.109.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.109.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.109.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.11.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.11.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.110.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.110.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.110.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.111.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.111.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.111.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.112.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.112.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.112.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.113.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.113.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.113.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.114.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.114.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.114.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.115.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.115.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.115.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.116.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.116.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.116.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.117.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.117.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.117.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.118.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.118.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.118.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.119.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.119.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.119.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.12.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.12.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.120.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.120.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.120.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.121.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.121.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.121.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.122.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.122.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.122.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.123.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.123.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.123.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.124.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.124.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.124.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.125.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.125.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.125.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.126.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.126.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.126.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.127.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.127.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.127.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.13.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.13.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.14.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.14.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.15.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.15.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.16.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.16.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.17.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.17.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.18.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.18.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.19.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.19.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.2.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.2.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.20.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.20.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.21.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.21.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.22.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.22.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.23.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.23.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.24.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.24.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.25.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.25.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.26.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.26.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.27.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.27.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.28.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.28.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.29.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.29.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.3.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.3.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.30.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.30.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.31.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.31.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.32.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.32.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.33.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.33.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.34.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.34.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.35.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.35.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.36.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.36.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.37.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.37.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.38.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.38.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.39.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.39.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.4.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.4.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.40.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.40.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.41.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.41.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.42.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.42.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.43.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.43.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.44.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.44.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.45.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.45.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.46.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.46.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.47.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.47.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.48.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.48.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.49.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.49.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.5.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.5.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.50.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.50.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.51.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.51.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.52.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.52.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.53.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.53.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.54.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.54.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.55.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.55.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.56.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.56.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.57.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.57.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.58.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.58.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.59.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.59.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.6.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.6.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.60.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.60.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.61.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.61.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.62.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.62.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.63.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.63.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.64.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.64.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.64.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.65.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.65.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.65.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.66.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.66.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.66.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.67.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.67.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.67.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.68.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.68.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.68.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.69.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.69.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.69.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.7.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.7.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.70.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.70.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.70.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.71.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.71.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.71.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.72.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.72.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.72.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.73.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.73.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.73.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.74.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.74.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.74.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.75.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.75.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.75.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.76.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.76.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.76.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.77.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.77.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.77.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.78.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.78.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.78.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.79.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.79.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.79.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.8.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.8.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.80.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.80.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.80.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.81.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.81.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.81.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.82.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.82.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.82.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.83.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.83.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.83.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.84.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.84.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.84.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.85.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.85.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.85.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.86.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.86.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.86.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.87.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.87.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.87.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.88.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.88.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.88.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.89.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.89.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.89.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.9.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.9.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.90.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.90.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.90.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.91.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.91.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.91.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.92.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.92.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.92.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.93.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.93.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.93.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.94.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.94.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.94.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.95.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.95.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.95.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.96.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.96.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.96.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.97.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.97.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.97.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.98.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.98.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.98.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.99.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.99.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.99.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.gate.e_score_correction_bias": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.gate.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.21.mlp.experts.0.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.0.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.1.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.1.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.10.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.10.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.100.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.100.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.100.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.101.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.101.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.101.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.102.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.102.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.102.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.103.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.103.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.103.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.104.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.104.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.104.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.105.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.105.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.105.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.106.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.106.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.106.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.107.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.107.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.107.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.108.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.108.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.108.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.109.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.109.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.109.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.11.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.11.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.110.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.110.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.110.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.111.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.111.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.111.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.112.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.112.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.112.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.113.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.113.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.113.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.114.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.114.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.114.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.115.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.115.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.115.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.116.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.116.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.116.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.117.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.117.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.117.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.118.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.118.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.118.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.119.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.119.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.119.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.12.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.12.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.120.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.120.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.120.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.121.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.121.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.121.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.122.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.122.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.122.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.123.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.123.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.123.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.124.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.124.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.124.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.125.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.125.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.125.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.126.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.126.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.126.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.127.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.127.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.127.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.13.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.13.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.14.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.14.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.15.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.15.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.16.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.16.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.17.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.17.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.18.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.18.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.19.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.19.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.2.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.2.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.20.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.20.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.21.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.21.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.22.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.22.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.23.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.23.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.24.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.24.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.25.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.25.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.26.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.26.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.27.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.27.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.28.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.28.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.29.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.29.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.3.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.3.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.30.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.30.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.31.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.31.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.32.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.32.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.33.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.33.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.34.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.34.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.35.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.35.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.36.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.36.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.37.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.37.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.38.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.38.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.39.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.39.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.4.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.4.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.40.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.40.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.41.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.41.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.42.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.42.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.43.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.43.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.44.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.44.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.45.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.45.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.46.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.46.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.47.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.47.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.48.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.48.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.49.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.49.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.5.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.5.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.50.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.50.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.51.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.51.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.52.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.52.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.53.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.53.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.54.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.54.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.55.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.55.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.56.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.56.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.57.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.57.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.58.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.58.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.59.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.59.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.6.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.6.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.60.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.60.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.61.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.61.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.62.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.62.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.63.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.63.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.64.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.64.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.64.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.65.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.65.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.65.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.66.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.66.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.66.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.67.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.67.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.67.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.68.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.68.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.68.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.69.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.69.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.69.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.7.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.7.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.70.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.70.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.70.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.71.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.71.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.71.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.72.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.72.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.72.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.73.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.73.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.73.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.74.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.74.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.74.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.75.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.75.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.75.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.76.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.76.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.76.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.77.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.77.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.77.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.78.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.78.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.78.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.79.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.79.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.79.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.8.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.8.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.80.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.80.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.80.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.81.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.81.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.81.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.82.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.82.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.82.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.83.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.83.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.83.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.84.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.84.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.84.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.85.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.85.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.85.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.86.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.86.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.86.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.87.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.87.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.87.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.88.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.88.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.88.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.89.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.89.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.89.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.9.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.9.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.90.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.90.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.90.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.91.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.91.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.91.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.92.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.92.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.92.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.93.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.93.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.93.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.94.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.94.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.94.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.95.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.95.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.95.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.96.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.96.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.96.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.97.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.97.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.97.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.98.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.98.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.98.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.99.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.99.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.99.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.gate.e_score_correction_bias": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.gate.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.22.mlp.experts.0.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.0.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.1.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.1.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.10.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.10.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.100.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.100.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.100.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.101.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.101.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.101.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.102.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.102.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.102.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.103.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.103.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.103.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.104.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.104.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.104.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.105.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.105.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.105.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.106.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.106.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.106.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.107.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.107.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.107.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.108.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.108.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.108.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.109.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.109.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.109.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.11.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.11.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.110.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.110.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.110.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.111.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.111.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.111.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.112.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.112.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.112.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.113.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.113.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.113.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.114.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.114.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.114.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.115.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.115.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.115.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.116.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.116.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.116.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.117.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.117.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.117.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.118.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.118.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.118.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.119.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.119.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.119.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.12.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.12.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.120.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.120.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.120.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.121.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.121.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.121.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.122.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.122.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.122.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.123.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.123.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.123.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.124.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.124.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.124.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.125.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.125.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.125.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.126.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.126.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.126.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.127.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.127.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.127.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.13.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.13.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.14.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.14.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.15.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.15.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.16.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.16.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.17.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.17.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.18.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.18.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.19.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.19.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.2.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.2.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.20.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.20.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.21.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.21.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.22.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.22.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.23.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.23.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.24.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.24.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.25.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.25.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.26.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.26.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.27.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.27.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.28.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.28.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.29.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.29.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.3.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.3.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.30.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.30.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.31.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.31.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.32.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.32.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.33.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.33.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.34.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.34.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.35.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.35.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.36.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.36.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.37.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.37.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.38.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.38.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.39.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.39.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.4.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.4.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.40.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.40.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.41.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.41.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.42.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.42.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.43.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.43.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.44.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.44.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.45.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.45.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.46.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.46.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.47.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.47.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.48.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.48.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.49.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.49.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.5.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.5.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.50.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.50.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.51.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.51.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.52.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.52.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.53.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.53.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.54.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.54.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.55.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.55.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.56.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.56.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.57.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.57.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.58.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.58.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.59.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.59.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.6.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.6.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.60.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.60.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.61.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.61.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.62.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.62.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.63.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.63.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.64.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.64.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.64.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.65.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.65.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.65.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.66.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.66.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.66.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.67.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.67.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.67.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.68.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.68.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.68.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.69.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.69.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.69.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.7.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.7.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.70.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.70.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.70.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.71.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.71.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.71.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.72.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.72.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.72.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.73.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.73.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.73.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.74.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.74.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.74.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.75.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.75.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.75.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.76.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.76.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.76.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.77.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.77.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.77.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.78.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.78.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.78.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.79.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.79.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.79.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.8.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.8.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.80.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.80.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.80.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.81.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.81.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.81.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.82.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.82.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.82.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.83.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.83.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.83.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.84.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.84.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.84.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.85.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.85.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.85.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.86.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.86.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.86.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.87.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.87.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.87.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.88.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.88.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.88.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.89.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.89.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.89.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.9.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.9.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.90.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.90.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.90.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.91.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.91.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.91.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.92.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.92.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.92.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.93.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.93.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.93.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.94.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.94.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.94.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.95.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.95.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.95.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.96.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.96.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.96.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.97.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.97.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.97.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.98.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.98.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.98.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.99.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.99.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.99.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.gate.e_score_correction_bias": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.gate.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.23.mlp.experts.0.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.0.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.1.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.1.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.10.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.10.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.100.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.100.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.100.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.101.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.101.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.101.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.102.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.102.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.102.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.103.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.103.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.103.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.104.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.104.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.104.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.105.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.105.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.105.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.106.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.106.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.106.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.107.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.107.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.107.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.108.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.108.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.108.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.109.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.109.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.109.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.11.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.11.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.110.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.110.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.110.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.111.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.111.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.111.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.112.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.112.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.112.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.113.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.113.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.113.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.114.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.114.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.114.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.115.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.115.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.115.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.116.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.116.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.116.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.117.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.117.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.117.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.118.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.118.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.118.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.119.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.119.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.119.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.12.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.12.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.120.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.120.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.120.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.121.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.121.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.121.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.122.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.122.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.122.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.123.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.123.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.123.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.124.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.124.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.124.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.125.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.125.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.125.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.126.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.126.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.126.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.127.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.127.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.127.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.13.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.13.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.14.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.14.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.15.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.15.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.16.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.16.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.17.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.17.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.18.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.18.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.19.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.19.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.2.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.2.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.20.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.20.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.21.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.21.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.22.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.22.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.23.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.23.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.24.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.24.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.25.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.25.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.26.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.26.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.27.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.27.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.28.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.28.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.29.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.29.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.3.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.3.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.30.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.30.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.31.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.31.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.32.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.32.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.33.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.33.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.34.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.34.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.35.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.35.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.36.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.36.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.37.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.37.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.38.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.38.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.39.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.39.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.4.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.4.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.40.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.40.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.41.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.41.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.42.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.42.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.43.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.43.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.44.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.44.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.45.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.45.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.46.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.46.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.47.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.47.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.48.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.48.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.49.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.49.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.5.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.5.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.50.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.50.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.51.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.51.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.52.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.52.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.53.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.53.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.54.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.54.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.55.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.55.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.56.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.56.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.57.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.57.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.58.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.58.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.59.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.59.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.6.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.6.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.60.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.60.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.61.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.61.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.62.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.62.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.63.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.63.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.64.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.64.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.64.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.65.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.65.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.65.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.66.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.66.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.66.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.67.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.67.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.67.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.68.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.68.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.68.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.69.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.69.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.69.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.7.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.7.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.70.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.70.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.70.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.71.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.71.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.71.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.72.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.72.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.72.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.73.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.73.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.73.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.74.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.74.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.74.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.75.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.75.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.75.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.76.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.76.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.76.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.77.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.77.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.77.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.78.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.78.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.78.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.79.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.79.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.79.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.8.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.8.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.80.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.80.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.80.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.81.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.81.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.81.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.82.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.82.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.82.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.83.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.83.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.83.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.84.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.84.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.84.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.85.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.85.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.85.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.86.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.86.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.86.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.87.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.87.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.87.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.88.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.88.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.88.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.89.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.89.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.89.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.9.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.9.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.90.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.90.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.90.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.91.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.91.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.91.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.92.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.92.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.92.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.93.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.93.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.93.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.94.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.94.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.94.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.95.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.95.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.95.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.96.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.96.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.96.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.97.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.97.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.97.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.98.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.98.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.98.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.99.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.99.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.99.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.gate.e_score_correction_bias": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.gate.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.24.mlp.experts.0.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.0.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.1.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.1.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.10.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.10.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.100.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.100.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.100.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.101.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.101.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.101.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.102.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.102.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.102.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.103.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.103.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.103.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.104.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.104.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.104.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.105.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.105.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.105.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.106.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.106.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.106.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.107.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.107.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.107.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.108.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.108.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.108.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.109.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.109.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.109.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.11.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.11.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.110.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.110.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.110.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.111.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.111.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.111.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.112.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.112.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.112.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.113.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.113.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.113.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.114.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.114.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.114.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.115.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.115.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.115.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.116.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.116.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.116.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.117.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.117.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.117.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.118.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.118.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.118.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.119.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.119.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.119.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.12.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.12.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.120.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.120.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.120.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.121.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.121.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.121.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.122.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.122.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.122.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.123.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.123.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.123.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.124.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.124.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.124.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.125.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.125.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.125.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.126.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.126.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.126.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.127.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.127.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.127.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.13.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.13.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.14.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.14.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.15.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.15.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.16.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.16.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.17.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.17.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.18.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.18.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.19.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.19.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.2.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.2.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.20.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.20.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.21.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.21.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.22.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.22.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.23.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.23.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.24.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.24.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.25.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.25.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.26.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.26.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.27.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.27.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.28.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.28.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.29.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.29.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.3.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.3.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.30.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.30.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.31.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.31.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.32.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.32.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.33.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.33.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.34.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.34.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.35.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.35.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.36.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.36.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.37.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.37.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.38.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.38.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.39.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.39.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.4.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.4.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.40.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.40.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.41.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.41.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.42.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.42.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.43.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.43.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.44.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.44.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.45.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.45.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.46.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.46.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.47.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.47.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.48.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.48.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.49.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.49.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.5.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.5.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.50.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.50.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.51.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.51.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.52.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.52.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.53.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.53.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.54.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.54.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.55.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.55.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.56.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.56.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.57.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.57.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.58.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.58.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.59.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.59.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.6.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.6.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.60.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.60.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.61.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.61.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.62.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.62.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.63.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.63.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.64.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.64.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.64.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.65.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.65.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.65.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.66.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.66.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.66.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.67.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.67.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.67.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.68.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.68.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.68.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.69.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.69.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.69.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.7.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.7.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.70.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.70.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.70.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.71.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.71.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.71.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.72.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.72.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.72.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.73.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.73.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.73.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.74.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.74.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.74.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.75.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.75.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.75.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.76.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.76.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.76.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.77.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.77.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.77.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.78.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.78.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.78.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.79.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.79.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.79.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.8.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.8.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.80.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.80.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.80.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.81.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.81.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.81.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.82.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.82.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.82.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.83.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.83.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.83.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.84.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.84.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.84.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.85.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.85.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.85.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.86.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.86.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.86.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.87.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.87.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.87.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.88.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.88.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.88.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.89.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.89.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.89.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.9.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.9.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.90.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.90.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.90.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.91.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.91.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.91.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.92.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.92.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.92.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.93.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.93.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.93.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.94.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.94.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.94.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.95.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.95.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.95.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.96.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.96.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.96.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.97.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.97.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.97.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.98.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.98.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.98.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.99.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.99.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.99.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.gate.e_score_correction_bias": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.gate.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.25.mlp.experts.0.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.0.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.1.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.1.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.10.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.10.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.100.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.100.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.100.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.101.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.101.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.101.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.102.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.102.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.102.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.103.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.103.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.103.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.104.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.104.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.104.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.105.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.105.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.105.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.106.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.106.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.106.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.107.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.107.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.107.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.108.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.108.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.108.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.109.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.109.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.109.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.11.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.11.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.110.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.110.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.110.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.111.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.111.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.111.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.112.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.112.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.112.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.113.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.113.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.113.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.114.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.114.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.114.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.115.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.115.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.115.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.116.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.116.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.116.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.117.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.117.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.117.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.118.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.118.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.118.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.119.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.119.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.119.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.12.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.12.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.120.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.120.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.120.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.121.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.121.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.121.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.122.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.122.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.122.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.123.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.123.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.123.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.124.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.124.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.124.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.125.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.125.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.125.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.126.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.126.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.126.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.127.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.127.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.127.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.13.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.13.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.14.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.14.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.15.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.15.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.16.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.16.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.17.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.17.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.18.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.18.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.19.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.19.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.2.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.2.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.20.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.20.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.21.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.21.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.22.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.22.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.23.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.23.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.24.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.24.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.25.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.25.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.26.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.26.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.27.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.27.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.28.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.28.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.29.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.29.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.3.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.3.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.30.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.30.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.31.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.31.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.32.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.32.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.33.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.33.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.34.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.34.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.35.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.35.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.36.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.36.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.37.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.37.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.38.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.38.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.39.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.39.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.4.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.4.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.40.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.40.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.41.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.41.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.42.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.42.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.43.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.43.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.44.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.44.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.45.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.45.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.46.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.46.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.47.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.47.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.48.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.48.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.49.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.49.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.5.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.5.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.50.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.50.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.51.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.51.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.52.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.52.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.53.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.53.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.54.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.54.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.55.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.55.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.56.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.56.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.57.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.57.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.58.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.58.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.59.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.59.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.6.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.6.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.60.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.60.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.61.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.61.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.62.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.62.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.63.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.63.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.64.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.64.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.64.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.65.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.65.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.65.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.66.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.66.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.66.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.67.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.67.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.67.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.68.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.68.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.68.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.69.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.69.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.69.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.7.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.7.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.70.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.70.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.70.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.71.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.71.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.71.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.72.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.72.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.72.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.73.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.73.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.73.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.74.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.74.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.74.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.75.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.75.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.75.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.76.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.76.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.76.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.77.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.77.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.77.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.78.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.78.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.78.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.79.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.79.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.79.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.8.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.8.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.80.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.80.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.80.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.81.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.81.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.81.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.82.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.82.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.82.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.83.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.83.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.83.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.84.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.84.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.84.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.85.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.85.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.85.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.86.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.86.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.86.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.87.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.87.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.87.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.88.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.88.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.88.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.89.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.89.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.89.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.9.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.9.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.90.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.90.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.90.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.91.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.91.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.91.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.92.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.92.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.92.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.93.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.93.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.93.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.94.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.94.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.94.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.95.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.95.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.95.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.96.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.96.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.96.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.97.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.97.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.97.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.98.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.98.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.98.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.99.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.99.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.99.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.gate.e_score_correction_bias": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.gate.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.26.mlp.experts.0.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.0.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.1.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.1.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.10.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.10.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.100.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.100.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.100.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.101.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.101.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.101.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.102.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.102.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.102.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.103.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.103.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.103.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.104.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.104.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.104.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.105.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.105.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.105.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.106.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.106.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.106.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.107.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.107.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.107.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.108.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.108.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.108.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.109.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.109.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.109.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.11.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.11.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.110.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.110.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.110.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.111.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.111.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.111.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.112.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.112.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.112.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.113.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.113.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.113.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.114.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.114.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.114.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.115.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.115.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.115.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.116.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.116.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.116.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.117.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.117.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.117.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.118.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.118.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.118.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.119.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.119.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.119.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.12.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.12.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.120.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.120.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.120.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.121.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.121.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.121.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.122.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.122.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.122.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.123.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.123.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.123.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.124.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.124.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.124.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.125.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.125.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.125.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.126.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.126.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.126.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.127.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.127.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.127.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.13.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.13.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.14.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.14.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.15.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.15.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.16.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.16.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.17.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.17.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.18.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.18.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.19.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.19.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.2.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.2.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.20.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.20.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.21.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.21.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.22.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.22.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.23.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.23.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.24.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.24.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.25.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.25.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.26.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.26.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.27.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.27.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.28.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.28.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.29.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.29.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.3.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.3.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.30.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.30.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.31.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.31.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.32.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.32.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.33.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.33.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.34.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.34.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.35.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.35.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.36.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.36.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.37.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.37.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.38.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.38.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.39.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.39.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.4.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.4.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.40.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.40.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.41.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.41.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.42.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.42.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.43.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.43.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.44.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.44.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.45.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.45.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.46.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.46.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.47.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.47.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.48.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.48.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.49.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.49.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.5.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.5.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.50.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.50.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.51.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.51.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.52.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.52.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.53.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.53.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.54.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.54.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.55.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.55.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.56.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.56.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.57.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.57.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.58.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.58.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.59.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.59.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.6.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.6.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.60.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.60.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.61.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.61.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.62.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.62.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.63.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.63.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.64.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.64.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.64.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.65.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.65.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.65.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.66.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.66.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.66.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.67.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.67.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.67.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.68.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.68.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.68.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.69.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.69.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.69.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.7.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.7.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.70.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.70.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.70.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.71.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.71.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.71.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.72.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.72.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.72.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.73.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.73.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.73.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.74.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.74.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.74.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.75.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.75.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.75.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.76.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.76.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.76.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.77.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.77.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.77.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.78.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.78.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.78.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.79.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.79.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.79.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.8.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.8.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.80.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.80.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.80.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.81.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.81.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.81.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.82.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.82.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.82.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.83.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.83.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.83.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.84.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.84.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.84.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.85.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.85.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.85.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.86.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.86.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.86.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.87.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.87.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.87.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.88.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.88.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.88.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.89.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.89.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.89.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.9.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.9.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.90.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.90.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.90.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.91.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.91.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.91.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.92.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.92.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.92.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.93.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.93.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.93.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.94.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.94.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.94.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.95.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.95.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.95.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.96.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.96.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.96.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.97.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.97.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.97.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.98.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.98.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.98.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.99.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.99.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.99.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.gate.e_score_correction_bias": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.gate.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.27.mlp.experts.0.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.0.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.1.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.1.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.10.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.10.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.100.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.100.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.100.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.101.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.101.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.101.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.102.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.102.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.102.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.103.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.103.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.103.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.104.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.104.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.104.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.105.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.105.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.105.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.106.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.106.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.106.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.107.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.107.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.107.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.108.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.108.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.108.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.109.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.109.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.109.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.11.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.11.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.110.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.110.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.110.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.111.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.111.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.111.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.112.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.112.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.112.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.113.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.113.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.113.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.114.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.114.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.114.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.115.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.115.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.115.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.116.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.116.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.116.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.117.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.117.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.117.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.118.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.118.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.118.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.119.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.119.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.119.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.12.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.12.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.120.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.120.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.120.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.121.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.121.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.121.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.122.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.122.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.122.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.123.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.123.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.123.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.124.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.124.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.124.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.125.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.125.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.125.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.126.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.126.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.126.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.127.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.127.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.127.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.13.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.13.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.14.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.14.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.15.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.15.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.16.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.16.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.17.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.17.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.18.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.18.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.19.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.19.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.2.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.2.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.20.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.20.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.21.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.21.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.22.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.22.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.23.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.23.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.24.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.24.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.25.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.25.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.26.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.26.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.27.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.27.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.28.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.28.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.29.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.29.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.3.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.3.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.30.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.30.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.31.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.31.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.32.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.32.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.33.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.33.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.34.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.34.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.35.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.35.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.36.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.36.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.37.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.37.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.38.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.38.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.39.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.39.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.4.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.4.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.40.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.40.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.41.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.41.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.42.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.42.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.43.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.43.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.44.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.44.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.45.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.45.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.46.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.46.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.47.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.47.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.48.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.48.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.49.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.49.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.5.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.5.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.50.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.50.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.51.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.51.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.52.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.52.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.53.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.53.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.54.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.54.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.55.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.55.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.56.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.56.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.57.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.57.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.58.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.58.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.59.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.59.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.6.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.6.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.60.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.60.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.61.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.61.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.62.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.62.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.63.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.63.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.64.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.64.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.64.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.65.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.65.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.65.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.66.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.66.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.66.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.67.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.67.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.67.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.68.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.68.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.68.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.69.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.69.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.69.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.7.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.7.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.70.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.70.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.70.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.71.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.71.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.71.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.72.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.72.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.72.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.73.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.73.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.73.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.74.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.74.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.74.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.75.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.75.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.75.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.76.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.76.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.76.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.77.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.77.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.77.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.78.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.78.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.78.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.79.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.79.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.79.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.8.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.8.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.80.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.80.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.80.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.81.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.81.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.81.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.82.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.82.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.82.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.83.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.83.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.83.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.84.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.84.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.84.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.85.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.85.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.85.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.86.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.86.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.86.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.87.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.87.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.87.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.88.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.88.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.88.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.89.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.89.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.89.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.9.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.9.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.90.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.90.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.90.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.91.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.91.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.91.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.92.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.92.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.92.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.93.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.93.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.93.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.94.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.94.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.94.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.95.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.95.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.95.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.96.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.96.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.96.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.97.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.97.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.97.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.98.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.98.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.98.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.99.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.99.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.99.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.gate.e_score_correction_bias": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.gate.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.28.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.28.mlp.experts.0.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.0.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.1.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.1.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.10.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.10.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.10.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.100.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.100.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.100.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.101.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.101.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.101.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.102.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.102.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.102.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.103.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.103.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.103.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.104.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.104.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.104.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.105.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.105.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.105.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.106.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.106.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.106.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.107.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.107.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.107.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.108.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.108.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.108.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.109.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.109.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.109.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.11.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.11.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.11.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.110.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.110.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.110.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.111.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.111.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.111.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.112.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.112.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.112.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.113.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.113.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.113.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.114.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.114.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.114.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.115.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.115.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.115.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.116.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.116.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.116.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.117.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.117.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.117.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.118.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.118.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.118.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.119.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.119.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.119.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.12.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.12.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.12.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.120.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.120.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.120.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.121.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.121.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.121.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.122.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.122.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.122.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.123.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.123.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.123.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.124.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.124.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.124.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.125.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.125.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.125.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.126.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.126.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.126.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.127.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.127.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.127.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.13.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.13.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.13.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.14.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.14.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.14.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.15.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.15.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.15.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.16.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.16.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.16.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.17.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.17.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.17.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.18.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.18.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.18.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.19.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.19.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.19.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.2.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.2.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.20.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.20.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.20.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.21.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.21.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.21.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.22.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.22.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.22.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.23.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.23.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.23.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.24.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.24.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.24.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.25.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.25.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.25.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.26.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.26.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.26.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.27.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.27.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.27.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.28.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.28.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.28.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.29.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.29.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.29.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.3.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.3.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.30.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.30.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.30.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.31.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.31.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.31.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.32.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.32.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.32.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.33.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.33.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.33.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.34.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.34.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.34.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.35.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.35.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.35.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.36.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.36.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.36.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.37.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.37.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.37.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.38.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.38.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.38.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.39.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.39.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.39.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.4.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.4.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.4.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.40.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.40.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.40.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.41.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.41.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.41.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.42.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.42.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.42.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.43.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.43.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.43.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.44.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.44.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.44.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.45.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.45.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.45.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.46.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.46.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.46.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.47.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.47.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.47.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.48.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.48.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.48.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.49.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.49.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.49.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.5.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.5.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.5.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.50.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.50.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.50.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.51.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.51.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.51.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.52.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.52.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.52.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.53.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.53.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.53.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.54.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.54.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.54.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.55.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.55.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.55.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.56.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.56.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.56.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.57.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.57.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.57.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.58.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.58.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.58.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.59.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.59.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.59.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.6.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.6.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.6.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.60.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.60.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.60.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.61.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.61.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.61.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.62.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.62.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.62.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.63.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.63.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.63.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.64.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.64.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.64.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.65.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.65.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.65.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.66.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.66.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.66.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.67.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.67.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.67.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.68.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.68.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.68.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.69.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.69.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.69.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.7.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.7.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.7.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.70.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.70.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.70.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.71.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.71.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.71.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.72.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.72.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.72.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.73.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.73.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.73.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.74.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.74.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.74.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.75.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.75.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.75.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.76.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.76.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.76.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.77.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.77.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.77.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.78.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.78.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.78.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.79.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.79.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.79.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.8.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.8.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.8.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.80.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.80.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.80.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.81.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.81.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.81.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.82.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.82.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.82.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.83.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.83.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.83.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.84.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.84.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.84.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.85.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.85.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.85.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.86.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.86.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.86.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.87.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.87.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.87.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.88.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.88.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.88.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.89.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.89.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.89.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.9.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.9.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.9.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.90.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.90.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.90.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.91.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.91.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.91.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.92.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.92.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.92.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.93.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.93.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.93.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.94.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.94.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.94.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.95.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.95.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.95.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.96.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.96.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.96.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.97.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.97.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.97.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.98.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.98.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.98.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.99.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.99.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.99.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.gate.e_score_correction_bias": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.gate.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.29.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.29.mlp.experts.0.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.0.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.1.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.1.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.10.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.10.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.10.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.100.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.100.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.100.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.101.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.101.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.101.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.102.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.102.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.102.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.103.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.103.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.103.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.104.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.104.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.104.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.105.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.105.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.105.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.106.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.106.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.106.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.107.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.107.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.107.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.108.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.108.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.108.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.109.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.109.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.109.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.11.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.11.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.11.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.110.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.110.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.110.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.111.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.111.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.111.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.112.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.112.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.112.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.113.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.113.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.113.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.114.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.114.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.114.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.115.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.115.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.115.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.116.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.116.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.116.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.117.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.117.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.117.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.118.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.118.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.118.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.119.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.119.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.119.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.12.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.12.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.12.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.120.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.120.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.120.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.121.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.121.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.121.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.122.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.122.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.122.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.123.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.123.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.123.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.124.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.124.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.124.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.125.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.125.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.125.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.126.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.126.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.126.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.127.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.127.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.127.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.13.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.13.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.13.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.14.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.14.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.14.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.15.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.15.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.15.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.16.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.16.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.16.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.17.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.17.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.17.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.18.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.18.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.18.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.19.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.19.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.19.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.2.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.2.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.20.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.20.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.20.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.21.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.21.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.21.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.22.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.22.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.22.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.23.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.23.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.23.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.24.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.24.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.24.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.25.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.25.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.25.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.26.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.26.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.26.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.27.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.27.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.27.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.28.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.28.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.28.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.29.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.29.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.29.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.3.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.3.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.30.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.30.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.30.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.31.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.31.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.31.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.32.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.32.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.32.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.33.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.33.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.33.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.34.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.34.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.34.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.35.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.35.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.35.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.36.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.36.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.36.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.37.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.37.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.37.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.38.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.38.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.38.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.39.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.39.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.39.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.4.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.4.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.4.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.40.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.40.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.40.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.41.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.41.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.41.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.42.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.42.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.42.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.43.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.43.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.43.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.44.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.44.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.44.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.45.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.45.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.45.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.46.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.46.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.46.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.47.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.47.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.47.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.48.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.48.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.48.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.49.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.49.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.49.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.5.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.5.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.5.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.50.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.50.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.50.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.51.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.51.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.51.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.52.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.52.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.52.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.53.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.53.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.53.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.54.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.54.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.54.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.55.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.55.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.55.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.56.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.56.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.56.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.57.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.57.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.57.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.58.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.58.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.58.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.59.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.59.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.59.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.6.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.6.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.6.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.60.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.60.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.60.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.61.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.61.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.61.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.62.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.62.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.62.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.63.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.63.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.63.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.64.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.64.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.64.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.65.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.65.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.65.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.66.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.66.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.66.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.67.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.67.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.67.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.68.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.68.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.68.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.69.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.69.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.69.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.7.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.7.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.7.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.70.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.70.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.70.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.71.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.71.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.71.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.72.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.72.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.72.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.73.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.73.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.73.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.74.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.74.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.74.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.75.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.75.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.75.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.76.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.76.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.76.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.77.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.77.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.77.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.78.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.78.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.78.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.79.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.79.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.79.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.8.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.8.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.8.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.80.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.80.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.80.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.81.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.81.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.81.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.82.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.82.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.82.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.83.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.83.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.83.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.84.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.84.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.84.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.85.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.85.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.85.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.86.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.86.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.86.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.87.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.87.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.87.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.88.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.88.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.88.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.89.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.89.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.89.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.9.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.9.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.9.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.90.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.90.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.90.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.91.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.91.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.91.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.92.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.92.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.92.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.93.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.93.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.93.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.94.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.94.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.94.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.95.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.95.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.95.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.96.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.96.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.96.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.97.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.97.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.97.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.98.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.98.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.98.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.99.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.99.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.99.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.gate.e_score_correction_bias": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.gate.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.3.mlp.experts.0.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.0.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.1.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.1.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.10.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.10.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.100.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.100.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.100.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.101.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.101.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.101.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.102.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.102.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.102.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.103.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.103.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.103.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.104.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.104.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.104.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.105.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.105.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.105.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.106.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.106.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.106.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.107.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.107.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.107.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.108.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.108.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.108.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.109.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.109.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.109.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.11.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.11.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.110.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.110.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.110.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.111.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.111.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.111.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.112.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.112.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.112.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.113.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.113.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.113.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.114.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.114.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.114.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.115.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.115.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.115.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.116.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.116.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.116.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.117.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.117.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.117.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.118.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.118.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.118.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.119.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.119.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.119.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.12.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.12.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.120.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.120.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.120.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.121.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.121.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.121.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.122.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.122.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.122.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.123.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.123.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.123.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.124.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.124.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.124.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.125.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.125.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.125.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.126.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.126.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.126.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.127.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.127.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.127.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.13.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.13.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.14.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.14.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.15.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.15.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.16.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.16.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.17.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.17.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.18.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.18.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.19.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.19.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.2.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.2.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.20.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.20.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.21.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.21.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.22.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.22.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.23.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.23.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.24.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.24.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.25.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.25.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.26.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.26.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.27.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.27.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.28.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.28.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.29.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.29.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.3.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.3.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.30.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.30.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.31.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.31.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.32.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.32.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.33.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.33.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.34.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.34.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.35.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.35.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.36.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.36.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.37.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.37.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.38.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.38.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.39.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.39.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.4.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.4.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.40.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.40.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.41.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.41.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.42.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.42.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.43.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.43.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.44.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.44.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.45.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.45.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.46.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.46.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.47.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.47.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.48.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.48.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.49.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.49.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.5.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.5.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.50.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.50.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.51.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.51.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.52.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.52.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.53.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.53.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.54.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.54.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.55.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.55.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.56.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.56.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.57.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.57.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.58.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.58.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.59.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.59.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.6.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.6.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.60.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.60.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.61.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.61.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.62.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.62.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.63.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.63.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.64.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.64.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.64.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.65.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.65.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.65.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.66.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.66.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.66.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.67.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.67.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.67.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.68.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.68.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.68.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.69.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.69.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.69.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.7.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.7.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.70.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.70.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.70.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.71.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.71.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.71.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.72.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.72.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.72.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.73.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.73.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.73.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.74.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.74.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.74.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.75.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.75.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.75.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.76.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.76.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.76.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.77.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.77.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.77.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.78.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.78.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.78.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.79.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.79.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.79.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.8.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.8.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.80.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.80.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.80.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.81.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.81.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.81.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.82.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.82.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.82.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.83.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.83.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.83.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.84.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.84.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.84.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.85.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.85.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.85.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.86.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.86.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.86.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.87.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.87.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.87.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.88.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.88.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.88.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.89.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.89.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.89.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.9.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.9.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.90.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.90.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.90.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.91.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.91.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.91.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.92.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.92.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.92.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.93.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.93.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.93.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.94.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.94.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.94.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.95.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.95.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.95.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.96.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.96.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.96.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.97.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.97.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.97.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.98.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.98.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.98.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.99.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.99.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.99.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.gate.e_score_correction_bias": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.gate.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.30.mlp.experts.0.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.0.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.1.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.1.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.10.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.10.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.10.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.100.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.100.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.100.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.101.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.101.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.101.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.102.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.102.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.102.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.103.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.103.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.103.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.104.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.104.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.104.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.105.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.105.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.105.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.106.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.106.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.106.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.107.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.107.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.107.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.108.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.108.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.108.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.109.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.109.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.109.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.11.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.11.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.11.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.110.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.110.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.110.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.111.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.111.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.111.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.112.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.112.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.112.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.113.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.113.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.113.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.114.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.114.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.114.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.115.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.115.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.115.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.116.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.116.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.116.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.117.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.117.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.117.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.118.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.118.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.118.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.119.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.119.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.119.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.12.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.12.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.12.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.120.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.120.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.120.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.121.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.121.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.121.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.122.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.122.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.122.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.123.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.123.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.123.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.124.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.124.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.124.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.125.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.125.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.125.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.126.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.126.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.126.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.127.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.127.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.127.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.13.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.13.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.13.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.14.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.14.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.14.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.15.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.15.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.15.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.16.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.16.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.16.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.17.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.17.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.17.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.18.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.18.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.18.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.19.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.19.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.19.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.2.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.2.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.20.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.20.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.20.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.21.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.21.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.21.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.22.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.22.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.22.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.23.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.23.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.23.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.24.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.24.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.24.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.25.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.25.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.25.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.26.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.26.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.26.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.27.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.27.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.27.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.28.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.28.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.28.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.29.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.29.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.29.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.3.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.3.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.30.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.30.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.30.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.31.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.31.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.31.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.32.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.32.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.32.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.33.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.33.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.33.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.34.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.34.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.34.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.35.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.35.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.35.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.36.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.36.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.36.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.37.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.37.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.37.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.38.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.38.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.38.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.39.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.39.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.39.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.4.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.4.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.4.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.40.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.40.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.40.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.41.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.41.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.41.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.42.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.42.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.42.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.43.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.43.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.43.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.44.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.44.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.44.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.45.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.45.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.45.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.46.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.46.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.46.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.47.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.47.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.47.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.48.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.48.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.48.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.49.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.49.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.49.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.5.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.5.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.5.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.50.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.50.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.50.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.51.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.51.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.51.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.52.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.52.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.52.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.53.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.53.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.53.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.54.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.54.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.54.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.55.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.55.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.55.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.56.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.56.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.56.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.57.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.57.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.57.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.58.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.58.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.58.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.59.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.59.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.59.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.6.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.6.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.6.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.60.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.60.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.60.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.61.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.61.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.61.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.62.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.62.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.62.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.63.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.63.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.63.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.64.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.64.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.64.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.65.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.65.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.65.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.66.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.66.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.66.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.67.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.67.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.67.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.68.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.68.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.68.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.69.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.69.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.69.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.7.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.7.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.7.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.70.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.70.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.70.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.71.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.71.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.71.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.72.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.72.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.72.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.73.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.73.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.73.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.74.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.74.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.74.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.75.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.75.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.75.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.76.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.76.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.76.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.77.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.77.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.77.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.78.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.78.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.78.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.79.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.79.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.79.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.8.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.8.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.8.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.80.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.80.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.80.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.81.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.81.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.81.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.82.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.82.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.82.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.83.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.83.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.83.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.84.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.84.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.84.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.85.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.85.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.85.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.86.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.86.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.86.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.87.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.87.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.87.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.88.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.88.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.88.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.89.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.89.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.89.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.9.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.9.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.9.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.90.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.90.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.90.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.91.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.91.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.91.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.92.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.92.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.92.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.93.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.93.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.93.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.94.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.94.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.94.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.95.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.95.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.95.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.96.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.96.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.96.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.97.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.97.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.97.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.98.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.98.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.98.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.99.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.99.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.99.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.gate.e_score_correction_bias": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.gate.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.31.mlp.experts.0.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.0.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.1.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.1.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.10.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.10.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.10.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.100.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.100.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.100.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.101.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.101.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.101.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.102.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.102.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.102.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.103.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.103.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.103.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.104.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.104.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.104.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.105.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.105.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.105.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.106.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.106.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.106.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.107.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.107.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.107.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.108.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.108.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.108.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.109.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.109.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.109.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.11.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.11.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.11.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.110.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.110.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.110.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.111.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.111.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.111.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.112.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.112.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.112.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.113.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.113.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.113.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.114.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.114.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.114.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.115.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.115.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.115.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.116.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.116.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.116.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.117.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.117.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.117.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.118.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.118.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.118.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.119.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.119.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.119.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.12.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.12.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.12.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.120.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.120.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.120.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.121.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.121.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.121.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.122.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.122.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.122.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.123.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.123.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.123.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.124.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.124.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.124.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.125.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.125.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.125.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.126.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.126.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.126.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.127.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.127.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.127.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.13.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.13.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.13.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.14.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.14.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.14.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.15.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.15.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.15.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.16.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.16.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.16.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.17.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.17.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.17.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.18.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.18.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.18.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.19.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.19.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.19.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.2.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.2.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.20.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.20.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.20.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.21.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.21.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.21.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.22.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.22.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.22.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.23.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.23.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.23.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.24.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.24.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.24.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.25.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.25.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.25.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.26.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.26.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.26.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.27.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.27.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.27.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.28.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.28.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.28.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.29.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.29.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.29.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.3.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.3.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.30.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.30.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.30.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.31.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.31.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.31.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.32.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.32.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.32.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.33.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.33.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.33.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.34.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.34.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.34.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.35.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.35.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.35.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.36.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.36.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.36.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.37.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.37.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.37.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.38.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.38.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.38.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.39.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.39.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.39.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.4.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.4.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.4.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.40.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.40.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.40.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.41.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.41.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.41.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.42.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.42.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.42.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.43.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.43.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.43.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.44.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.44.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.44.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.45.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.45.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.45.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.46.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.46.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.46.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.47.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.47.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.47.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.48.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.48.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.48.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.49.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.49.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.49.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.5.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.5.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.5.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.50.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.50.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.50.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.51.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.51.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.51.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.52.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.52.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.52.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.53.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.53.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.53.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.54.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.54.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.54.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.55.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.55.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.55.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.56.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.56.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.56.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.57.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.57.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.57.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.58.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.58.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.58.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.59.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.59.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.59.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.6.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.6.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.6.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.60.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.60.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.60.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.61.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.61.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.61.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.62.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.62.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.62.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.63.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.63.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.63.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.64.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.64.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.64.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.65.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.65.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.65.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.66.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.66.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.66.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.67.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.67.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.67.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.68.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.68.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.68.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.69.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.69.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.69.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.7.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.7.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.7.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.70.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.70.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.70.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.71.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.71.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.71.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.72.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.72.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.72.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.73.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.73.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.73.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.74.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.74.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.74.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.75.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.75.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.75.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.76.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.76.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.76.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.77.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.77.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.77.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.78.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.78.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.78.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.79.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.79.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.79.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.8.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.8.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.8.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.80.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.80.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.80.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.81.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.81.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.81.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.82.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.82.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.82.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.83.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.83.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.83.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.84.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.84.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.84.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.85.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.85.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.85.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.86.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.86.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.86.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.87.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.87.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.87.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.88.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.88.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.88.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.89.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.89.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.89.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.9.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.9.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.9.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.90.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.90.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.90.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.91.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.91.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.91.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.92.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.92.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.92.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.93.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.93.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.93.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.94.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.94.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.94.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.95.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.95.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.95.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.96.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.96.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.96.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.97.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.97.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.97.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.98.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.98.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.98.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.99.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.99.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.99.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.gate.e_score_correction_bias": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.gate.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.32.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.32.mlp.experts.0.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.0.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.0.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.1.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.1.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.1.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.10.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.10.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.10.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.100.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.100.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.100.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.101.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.101.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.101.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.102.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.102.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.102.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.103.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.103.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.103.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.104.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.104.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.104.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.105.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.105.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.105.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.106.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.106.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.106.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.107.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.107.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.107.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.108.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.108.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.108.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.109.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.109.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.109.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.11.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.11.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.11.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.110.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.110.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.110.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.111.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.111.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.111.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.112.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.112.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.112.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.113.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.113.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.113.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.114.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.114.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.114.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.115.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.115.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.115.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.116.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.116.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.116.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.117.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.117.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.117.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.118.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.118.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.118.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.119.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.119.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.119.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.12.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.12.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.12.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.120.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.120.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.120.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.121.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.121.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.121.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.122.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.122.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.122.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.123.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.123.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.123.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.124.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.124.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.124.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.125.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.125.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.125.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.126.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.126.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.126.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.127.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.127.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.127.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.13.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.13.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.13.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.14.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.14.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.14.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.15.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.15.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.15.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.16.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.16.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.16.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.17.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.17.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.17.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.18.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.18.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.18.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.19.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.19.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.19.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.2.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.2.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.2.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.20.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.20.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.20.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.21.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.21.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.21.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.22.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.22.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.22.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.23.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.23.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.23.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.24.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.24.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.24.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.25.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.25.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.25.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.26.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.26.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.26.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.27.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.27.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.27.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.28.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.28.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.28.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.29.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.29.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.29.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.3.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.3.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.3.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.30.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.30.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.30.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.31.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.31.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.31.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.32.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.32.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.32.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.33.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.33.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.33.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.34.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.34.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.34.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.35.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.35.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.35.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.36.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.36.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.36.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.37.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.37.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.37.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.38.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.38.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.38.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.39.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.39.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.39.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.4.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.4.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.4.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.40.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.40.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.40.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.41.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.41.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.41.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.42.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.42.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.42.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.43.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.43.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.43.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.44.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.44.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.44.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.45.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.45.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.45.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.46.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.46.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.46.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.47.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.47.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.47.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.48.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.48.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.48.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.49.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.49.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.49.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.5.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.5.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.5.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.50.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.50.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.50.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.51.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.51.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.51.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.52.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.52.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.52.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.53.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.53.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.53.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.54.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.54.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.54.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.55.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.55.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.55.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.56.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.56.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.56.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.57.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.57.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.57.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.58.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.58.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.58.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.59.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.59.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.59.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.6.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.6.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.6.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.60.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.60.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.60.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.61.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.61.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.61.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.62.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.62.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.62.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.63.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.63.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.63.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.64.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.64.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.64.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.65.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.65.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.65.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.66.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.66.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.66.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.67.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.67.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.67.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.68.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.68.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.68.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.69.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.69.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.69.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.7.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.7.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.7.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.70.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.70.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.70.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.71.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.71.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.71.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.72.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.72.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.72.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.73.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.73.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.73.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.74.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.74.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.74.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.75.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.75.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.75.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.76.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.76.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.76.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.77.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.77.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.77.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.78.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.78.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.78.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.79.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.79.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.79.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.8.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.8.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.8.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.80.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.80.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.80.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.81.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.81.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.81.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.82.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.82.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.82.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.83.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.83.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.83.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.84.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.84.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.84.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.85.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.85.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.85.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.86.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.86.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.86.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.87.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.87.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.87.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.88.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.88.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.88.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.89.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.89.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.89.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.9.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.9.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.9.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.90.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.90.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.90.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.91.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.91.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.91.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.92.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.92.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.92.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.93.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.93.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.93.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.94.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.94.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.94.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.95.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.95.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.95.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.96.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.96.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.96.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.97.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.97.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.97.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.98.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.98.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.98.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.99.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.99.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.99.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.gate.e_score_correction_bias": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.gate.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.33.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.33.mlp.experts.0.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.0.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.0.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.1.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.1.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.1.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.10.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.10.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.10.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.100.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.100.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.100.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.101.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.101.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.101.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.102.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.102.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.102.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.103.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.103.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.103.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.104.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.104.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.104.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.105.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.105.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.105.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.106.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.106.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.106.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.107.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.107.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.107.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.108.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.108.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.108.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.109.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.109.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.109.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.11.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.11.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.11.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.110.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.110.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.110.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.111.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.111.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.111.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.112.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.112.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.112.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.113.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.113.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.113.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.114.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.114.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.114.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.115.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.115.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.115.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.116.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.116.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.116.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.117.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.117.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.117.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.118.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.118.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.118.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.119.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.119.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.119.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.12.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.12.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.12.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.120.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.120.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.120.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.121.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.121.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.121.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.122.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.122.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.122.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.123.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.123.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.123.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.124.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.124.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.124.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.125.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.125.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.125.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.126.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.126.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.126.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.127.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.127.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.127.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.13.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.13.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.13.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.14.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.14.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.14.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.15.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.15.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.15.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.16.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.16.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.16.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.17.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.17.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.17.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.18.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.18.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.18.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.19.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.19.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.19.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.2.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.2.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.2.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.20.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.20.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.20.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.21.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.21.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.21.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.22.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.22.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.22.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.23.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.23.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.23.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.24.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.24.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.24.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.25.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.25.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.25.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.26.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.26.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.26.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.27.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.27.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.27.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.28.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.28.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.28.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.29.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.29.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.29.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.3.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.3.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.3.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.30.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.30.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.30.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.31.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.31.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.31.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.32.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.32.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.32.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.33.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.33.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.33.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.34.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.34.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.34.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.35.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.35.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.35.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.36.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.36.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.36.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.37.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.37.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.37.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.38.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.38.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.38.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.39.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.39.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.39.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.4.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.4.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.4.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.40.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.40.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.40.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.41.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.41.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.41.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.42.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.42.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.42.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.43.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.43.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.43.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.44.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.44.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.44.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.45.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.45.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.45.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.46.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.46.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.46.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.47.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.47.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.47.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.48.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.48.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.48.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.49.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.49.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.49.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.5.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.5.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.5.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.50.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.50.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.50.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.51.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.51.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.51.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.52.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.52.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.52.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.53.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.53.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.53.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.54.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.54.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.54.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.55.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.55.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.55.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.56.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.56.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.56.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.57.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.57.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.57.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.58.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.58.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.58.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.59.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.59.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.59.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.6.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.6.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.6.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.60.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.60.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.60.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.61.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.61.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.61.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.62.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.62.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.62.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.63.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.63.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.63.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.64.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.64.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.64.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.65.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.65.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.65.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.66.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.66.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.66.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.67.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.67.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.67.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.68.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.68.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.68.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.69.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.69.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.69.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.7.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.7.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.7.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.70.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.70.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.70.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.71.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.71.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.71.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.72.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.72.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.72.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.73.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.73.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.73.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.74.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.74.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.74.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.75.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.75.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.75.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.76.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.76.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.76.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.77.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.77.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.77.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.78.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.78.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.78.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.79.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.79.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.79.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.8.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.8.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.8.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.80.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.80.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.80.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.81.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.81.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.81.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.82.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.82.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.82.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.83.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.83.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.83.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.84.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.84.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.84.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.85.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.85.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.85.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.86.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.86.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.86.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.87.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.87.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.87.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.88.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.88.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.88.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.89.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.89.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.89.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.9.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.9.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.9.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.90.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.90.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.90.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.91.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.91.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.91.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.92.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.92.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.92.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.93.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.93.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.93.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.94.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.94.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.94.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.95.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.95.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.95.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.96.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.96.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.96.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.97.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.97.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.97.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.98.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.98.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.98.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.99.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.99.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.99.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.gate.e_score_correction_bias": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.gate.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.34.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.34.mlp.experts.0.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.0.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.0.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.1.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.1.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.1.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.10.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.10.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.10.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.100.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.100.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.100.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.101.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.101.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.101.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.102.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.102.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.102.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.103.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.103.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.103.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.104.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.104.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.104.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.105.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.105.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.105.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.106.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.106.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.106.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.107.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.107.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.107.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.108.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.108.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.108.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.109.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.109.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.109.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.11.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.11.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.11.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.110.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.110.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.110.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.111.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.111.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.111.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.112.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.112.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.112.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.113.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.113.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.113.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.114.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.114.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.114.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.115.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.115.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.115.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.116.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.116.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.116.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.117.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.117.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.117.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.118.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.118.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.118.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.119.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.119.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.119.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.12.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.12.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.12.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.120.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.120.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.120.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.121.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.121.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.121.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.122.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.122.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.122.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.123.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.123.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.123.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.124.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.124.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.124.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.125.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.125.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.125.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.126.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.126.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.126.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.127.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.127.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.127.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.13.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.13.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.13.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.14.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.14.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.14.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.15.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.15.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.15.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.16.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.16.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.16.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.17.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.17.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.17.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.18.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.18.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.18.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.19.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.19.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.19.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.2.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.2.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.2.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.20.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.20.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.20.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.21.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.21.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.21.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.22.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.22.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.22.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.23.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.23.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.23.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.24.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.24.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.24.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.25.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.25.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.25.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.26.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.26.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.26.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.27.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.27.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.27.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.28.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.28.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.28.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.29.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.29.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.29.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.3.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.3.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.3.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.30.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.30.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.30.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.31.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.31.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.31.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.32.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.32.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.32.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.33.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.33.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.33.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.34.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.34.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.34.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.35.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.35.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.35.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.36.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.36.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.36.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.37.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.37.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.37.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.38.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.38.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.38.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.39.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.39.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.39.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.4.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.4.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.4.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.40.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.40.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.40.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.41.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.41.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.41.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.42.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.42.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.42.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.43.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.43.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.43.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.44.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.44.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.44.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.45.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.45.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.45.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.46.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.46.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.46.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.47.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.47.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.47.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.48.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.48.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.48.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.49.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.49.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.49.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.5.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.5.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.5.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.50.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.50.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.50.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.51.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.51.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.51.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.52.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.52.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.52.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.53.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.53.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.53.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.54.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.54.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.54.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.55.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.55.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.55.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.56.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.56.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.56.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.57.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.57.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.57.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.58.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.58.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.58.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.59.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.59.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.59.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.6.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.6.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.6.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.60.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.60.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.60.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.61.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.61.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.61.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.62.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.62.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.62.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.63.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.63.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.63.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.64.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.64.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.64.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.65.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.65.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.65.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.66.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.66.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.66.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.67.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.67.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.67.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.68.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.68.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.68.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.69.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.69.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.69.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.7.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.7.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.7.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.70.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.70.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.70.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.71.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.71.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.71.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.72.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.72.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.72.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.73.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.73.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.73.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.74.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.74.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.74.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.75.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.75.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.75.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.76.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.76.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.76.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.77.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.77.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.77.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.78.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.78.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.78.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.79.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.79.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.79.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.8.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.8.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.8.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.80.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.80.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.80.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.81.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.81.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.81.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.82.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.82.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.82.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.83.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.83.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.83.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.84.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.84.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.84.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.85.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.85.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.85.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.86.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.86.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.86.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.87.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.87.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.87.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.88.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.88.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.88.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.89.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.89.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.89.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.9.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.9.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.9.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.90.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.90.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.90.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.91.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.91.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.91.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.92.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.92.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.92.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.93.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.93.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.93.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.94.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.94.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.94.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.95.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.95.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.95.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.96.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.96.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.96.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.97.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.97.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.97.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.98.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.98.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.98.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.99.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.99.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.99.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.gate.e_score_correction_bias": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.gate.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.35.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.35.mlp.experts.0.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.0.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.0.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.1.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.1.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.1.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.10.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.10.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.10.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.100.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.100.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.100.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.101.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.101.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.101.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.102.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.102.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.102.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.103.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.103.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.103.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.104.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.104.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.104.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.105.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.105.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.105.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.106.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.106.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.106.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.107.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.107.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.107.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.108.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.108.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.108.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.109.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.109.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.109.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.11.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.11.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.11.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.110.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.110.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.110.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.111.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.111.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.111.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.112.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.112.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.112.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.113.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.113.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.113.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.114.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.114.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.114.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.115.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.115.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.115.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.116.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.116.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.116.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.117.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.117.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.117.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.118.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.118.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.118.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.119.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.119.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.119.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.12.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.12.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.12.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.120.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.120.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.120.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.121.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.121.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.121.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.122.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.122.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.122.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.123.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.123.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.123.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.124.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.124.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.124.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.125.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.125.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.125.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.126.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.126.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.126.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.127.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.127.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.127.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.13.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.13.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.13.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.14.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.14.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.14.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.15.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.15.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.15.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.16.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.16.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.16.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.17.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.17.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.17.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.18.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.18.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.18.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.19.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.19.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.19.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.2.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.2.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.2.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.20.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.20.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.20.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.21.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.21.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.21.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.22.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.22.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.22.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.23.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.23.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.23.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.24.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.24.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.24.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.25.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.25.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.25.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.26.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.26.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.26.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.27.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.27.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.27.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.28.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.28.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.28.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.29.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.29.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.29.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.3.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.3.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.3.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.30.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.30.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.30.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.31.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.31.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.31.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.32.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.32.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.32.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.33.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.33.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.33.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.34.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.34.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.34.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.35.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.35.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.35.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.36.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.36.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.36.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.37.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.37.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.37.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.38.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.38.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.38.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.39.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.39.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.39.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.4.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.4.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.4.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.40.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.40.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.40.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.41.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.41.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.41.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.42.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.42.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.42.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.43.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.43.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.43.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.44.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.44.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.44.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.45.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.45.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.45.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.46.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.46.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.46.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.47.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.47.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.47.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.48.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.48.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.48.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.49.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.49.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.49.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.5.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.5.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.5.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.50.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.50.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.50.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.51.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.51.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.51.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.52.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.52.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.52.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.53.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.53.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.53.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.54.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.54.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.54.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.55.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.55.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.55.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.56.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.56.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.56.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.57.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.57.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.57.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.58.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.58.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.58.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.59.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.59.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.59.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.6.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.6.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.6.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.60.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.60.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.60.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.61.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.61.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.61.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.62.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.62.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.62.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.63.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.63.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.63.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.64.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.64.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.64.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.65.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.65.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.65.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.66.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.66.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.66.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.67.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.67.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.67.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.68.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.68.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.68.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.69.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.69.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.69.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.7.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.7.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.7.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.70.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.70.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.70.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.71.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.71.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.71.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.72.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.72.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.72.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.73.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.73.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.73.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.74.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.74.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.74.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.75.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.75.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.75.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.76.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.76.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.76.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.77.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.77.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.77.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.78.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.78.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.78.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.79.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.79.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.79.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.8.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.8.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.8.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.80.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.80.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.80.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.81.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.81.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.81.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.82.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.82.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.82.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.83.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.83.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.83.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.84.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.84.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.84.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.85.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.85.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.85.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.86.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.86.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.86.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.87.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.87.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.87.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.88.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.88.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.88.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.89.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.89.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.89.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.9.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.9.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.9.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.90.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.90.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.90.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.91.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.91.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.91.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.92.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.92.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.92.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.93.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.93.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.93.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.94.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.94.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.94.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.95.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.95.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.95.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.96.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.96.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.96.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.97.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.97.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.97.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.98.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.98.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.98.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.99.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.99.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.99.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.gate.e_score_correction_bias": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.gate.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.36.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.36.mlp.experts.0.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.0.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.0.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.1.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.1.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.1.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.10.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.10.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.10.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.100.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.100.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.100.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.101.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.101.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.101.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.102.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.102.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.102.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.103.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.103.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.103.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.104.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.104.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.104.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.105.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.105.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.105.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.106.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.106.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.106.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.107.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.107.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.107.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.108.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.108.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.108.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.109.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.109.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.109.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.11.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.11.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.11.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.110.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.110.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.110.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.111.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.111.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.111.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.112.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.112.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.112.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.113.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.113.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.113.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.114.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.114.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.114.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.115.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.115.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.115.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.116.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.116.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.116.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.117.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.117.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.117.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.118.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.118.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.118.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.119.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.119.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.119.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.12.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.12.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.12.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.120.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.120.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.120.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.121.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.121.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.121.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.122.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.122.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.122.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.123.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.123.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.123.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.124.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.124.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.124.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.125.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.125.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.125.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.126.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.126.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.126.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.127.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.127.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.127.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.13.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.13.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.13.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.14.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.14.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.14.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.15.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.15.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.15.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.16.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.16.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.16.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.17.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.17.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.17.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.18.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.18.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.18.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.19.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.19.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.19.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.2.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.2.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.2.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.20.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.20.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.20.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.21.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.21.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.21.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.22.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.22.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.22.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.23.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.23.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.23.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.24.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.24.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.24.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.25.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.25.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.25.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.26.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.26.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.26.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.27.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.27.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.27.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.28.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.28.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.28.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.29.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.29.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.29.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.3.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.3.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.3.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.30.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.30.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.30.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.31.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.31.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.31.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.32.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.32.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.32.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.33.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.33.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.33.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.34.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.34.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.34.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.35.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.35.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.35.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.36.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.36.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.36.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.37.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.37.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.37.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.38.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.38.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.38.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.39.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.39.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.39.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.4.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.4.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.4.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.40.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.40.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.40.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.41.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.41.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.41.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.42.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.42.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.42.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.43.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.43.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.43.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.44.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.44.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.44.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.45.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.45.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.45.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.46.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.46.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.46.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.47.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.47.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.47.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.48.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.48.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.48.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.49.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.49.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.49.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.5.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.5.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.5.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.50.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.50.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.50.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.51.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.51.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.51.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.52.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.52.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.52.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.53.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.53.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.53.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.54.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.54.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.54.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.55.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.55.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.55.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.56.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.56.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.56.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.57.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.57.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.57.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.58.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.58.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.58.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.59.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.59.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.59.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.6.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.6.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.6.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.60.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.60.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.60.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.61.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.61.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.61.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.62.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.62.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.62.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.63.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.63.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.63.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.64.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.64.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.64.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.65.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.65.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.65.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.66.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.66.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.66.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.67.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.67.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.67.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.68.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.68.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.68.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.69.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.69.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.69.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.7.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.7.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.7.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.70.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.70.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.70.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.71.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.71.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.71.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.72.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.72.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.72.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.73.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.73.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.73.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.74.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.74.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.74.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.75.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.75.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.75.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.76.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.76.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.76.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.77.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.77.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.77.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.78.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.78.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.78.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.79.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.79.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.79.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.8.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.8.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.8.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.80.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.80.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.80.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.81.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.81.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.81.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.82.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.82.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.82.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.83.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.83.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.83.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.84.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.84.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.84.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.85.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.85.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.85.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.86.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.86.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.86.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.87.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.87.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.87.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.88.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.88.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.88.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.89.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.89.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.89.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.9.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.9.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.9.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.90.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.90.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.90.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.91.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.91.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.91.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.92.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.92.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.92.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.93.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.93.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.93.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.94.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.94.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.94.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.95.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.95.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.95.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.96.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.96.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.96.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.97.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.97.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.97.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.98.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.98.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.98.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.99.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.99.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.99.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.gate.e_score_correction_bias": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.gate.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.37.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.37.mlp.experts.0.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.0.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.0.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.1.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.1.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.1.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.10.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.10.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.10.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.100.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.100.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.100.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.101.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.101.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.101.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.102.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.102.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.102.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.103.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.103.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.103.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.104.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.104.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.104.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.105.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.105.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.105.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.106.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.106.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.106.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.107.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.107.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.107.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.108.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.108.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.108.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.109.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.109.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.109.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.11.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.11.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.11.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.110.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.110.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.110.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.111.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.111.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.111.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.112.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.112.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.112.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.113.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.113.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.113.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.114.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.114.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.114.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.115.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.115.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.115.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.116.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.116.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.116.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.117.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.117.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.117.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.118.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.118.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.118.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.119.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.119.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.119.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.12.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.12.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.12.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.120.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.120.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.120.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.121.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.121.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.121.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.122.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.122.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.122.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.123.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.123.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.123.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.124.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.124.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.124.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.125.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.125.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.125.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.126.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.126.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.126.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.127.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.127.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.127.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.13.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.13.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.13.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.14.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.14.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.14.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.15.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.15.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.15.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.16.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.16.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.16.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.17.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.17.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.17.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.18.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.18.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.18.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.19.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.19.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.19.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.2.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.2.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.2.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.20.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.20.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.20.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.21.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.21.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.21.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.22.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.22.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.22.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.23.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.23.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.23.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.24.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.24.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.24.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.25.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.25.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.25.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.26.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.26.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.26.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.27.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.27.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.27.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.28.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.28.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.28.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.29.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.29.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.29.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.3.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.3.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.3.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.30.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.30.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.30.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.31.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.31.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.31.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.32.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.32.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.32.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.33.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.33.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.33.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.34.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.34.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.34.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.35.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.35.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.35.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.36.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.36.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.36.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.37.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.37.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.37.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.38.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.38.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.38.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.39.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.39.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.39.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.4.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.4.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.4.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.40.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.40.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.40.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.41.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.41.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.41.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.42.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.42.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.42.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.43.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.43.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.43.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.44.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.44.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.44.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.45.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.45.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.45.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.46.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.46.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.46.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.47.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.47.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.47.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.48.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.48.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.48.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.49.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.49.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.49.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.5.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.5.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.5.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.50.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.50.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.50.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.51.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.51.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.51.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.52.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.52.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.52.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.53.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.53.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.53.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.54.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.54.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.54.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.55.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.55.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.55.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.56.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.56.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.56.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.57.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.57.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.57.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.58.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.58.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.58.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.59.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.59.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.59.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.6.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.6.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.6.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.60.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.60.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.60.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.61.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.61.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.61.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.62.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.62.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.62.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.63.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.63.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.63.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.64.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.64.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.64.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.65.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.65.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.65.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.66.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.66.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.66.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.67.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.67.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.67.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.68.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.68.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.68.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.69.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.69.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.69.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.7.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.7.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.7.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.70.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.70.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.70.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.71.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.71.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.71.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.72.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.72.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.72.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.73.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.73.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.73.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.74.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.74.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.74.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.75.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.75.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.75.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.76.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.76.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.76.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.77.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.77.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.77.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.78.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.78.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.78.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.79.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.79.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.79.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.8.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.8.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.8.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.80.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.80.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.80.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.81.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.81.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.81.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.82.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.82.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.82.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.83.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.83.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.83.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.84.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.84.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.84.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.85.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.85.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.85.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.86.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.86.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.86.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.87.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.87.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.87.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.88.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.88.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.88.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.89.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.89.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.89.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.9.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.9.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.9.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.90.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.90.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.90.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.91.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.91.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.91.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.92.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.92.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.92.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.93.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.93.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.93.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.94.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.94.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.94.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.95.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.95.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.95.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.96.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.96.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.96.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.97.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.97.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.97.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.98.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.98.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.98.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.99.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.99.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.99.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.gate.e_score_correction_bias": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.gate.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.38.input_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.38.mlp.experts.0.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.0.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.0.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.1.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.1.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.1.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.10.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.10.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.10.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.100.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.100.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.100.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.101.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.101.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.101.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.102.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.102.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.102.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.103.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.103.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.103.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.104.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.104.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.104.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.105.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.105.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.105.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.106.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.106.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.106.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.107.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.107.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.107.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.108.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.108.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.108.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.109.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.109.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.109.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.11.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.11.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.11.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.110.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.110.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.110.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.111.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.111.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.111.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.112.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.112.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.112.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.113.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.113.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.113.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.114.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.114.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.114.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.115.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.115.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.115.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.116.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.116.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.116.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.117.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.117.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.117.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.118.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.118.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.118.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.119.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.119.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.119.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.12.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.12.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.12.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.120.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.120.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.120.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.121.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.121.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.121.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.122.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.122.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.122.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.123.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.123.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.123.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.124.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.124.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.124.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.125.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.125.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.125.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.126.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.126.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.126.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.127.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.127.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.127.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.13.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.13.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.13.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.14.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.14.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.14.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.15.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.15.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.15.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.16.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.16.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.16.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.17.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.17.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.17.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.18.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.18.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.18.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.19.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.19.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.19.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.2.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.2.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.2.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.20.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.20.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.20.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.21.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.21.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.21.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.22.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.22.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.22.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.23.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.23.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.23.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.24.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.24.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.24.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.25.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.25.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.25.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.26.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.26.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.26.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.27.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.27.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.27.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.28.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.28.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.28.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.29.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.29.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.29.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.3.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.3.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.3.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.30.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.30.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.30.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.31.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.31.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.31.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.32.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.32.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.32.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.33.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.33.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.33.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.34.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.34.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.34.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.35.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.35.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.35.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.36.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.36.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.36.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.37.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.37.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.37.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.38.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.38.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.38.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.39.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.39.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.39.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.4.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.4.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.4.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.40.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.40.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.40.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.41.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.41.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.41.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.42.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.42.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.42.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.43.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.43.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.43.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.44.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.44.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.44.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.45.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.45.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.45.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.46.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.46.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.46.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.47.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.47.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.47.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.48.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.48.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.48.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.49.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.49.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.49.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.5.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.5.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.5.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.50.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.50.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.50.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.51.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.51.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.51.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.52.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.52.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.52.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.53.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.53.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.53.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.54.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.54.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.54.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.55.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.55.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.55.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.56.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.56.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.56.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.57.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.57.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.57.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.58.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.58.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.58.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.59.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.59.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.59.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.6.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.6.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.6.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.60.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.60.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.60.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.61.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.61.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.61.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.62.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.62.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.62.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.63.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.63.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.63.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.64.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.64.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.64.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.65.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.65.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.65.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.66.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.66.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.66.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.67.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.67.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.67.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.68.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.68.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.68.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.69.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.69.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.69.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.7.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.7.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.7.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.70.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.70.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.70.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.71.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.71.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.71.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.72.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.72.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.72.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.73.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.73.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.73.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.74.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.74.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.74.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.75.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.75.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.75.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.76.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.76.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.76.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.77.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.77.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.77.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.78.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.78.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.78.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.79.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.79.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.79.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.8.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.8.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.8.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.80.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.80.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.80.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.81.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.81.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.81.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.82.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.82.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.82.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.83.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.83.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.83.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.84.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.84.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.84.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.85.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.85.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.85.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.86.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.86.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.86.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.87.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.87.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.87.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.88.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.88.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.88.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.89.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.89.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.89.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.9.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.9.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.9.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.90.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.90.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.90.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.91.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.91.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.91.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.92.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.92.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.92.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.93.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.93.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.93.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.94.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.94.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.94.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.95.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.95.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.95.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.96.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.96.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.96.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.97.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.97.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.97.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.98.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.98.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.98.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.99.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.99.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.99.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.gate.e_score_correction_bias": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.gate.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.39.input_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.39.mlp.experts.0.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.0.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.0.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.1.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.1.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.1.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.10.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.10.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.10.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.100.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.100.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.100.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.101.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.101.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.101.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.102.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.102.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.102.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.103.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.103.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.103.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.104.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.104.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.104.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.105.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.105.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.105.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.106.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.106.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.106.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.107.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.107.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.107.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.108.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.108.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.108.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.109.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.109.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.109.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.11.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.11.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.11.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.110.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.110.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.110.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.111.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.111.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.111.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.112.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.112.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.112.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.113.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.113.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.113.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.114.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.114.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.114.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.115.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.115.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.115.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.116.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.116.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.116.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.117.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.117.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.117.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.118.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.118.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.118.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.119.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.119.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.119.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.12.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.12.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.12.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.120.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.120.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.120.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.121.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.121.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.121.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.122.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.122.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.122.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.123.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.123.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.123.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.124.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.124.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.124.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.125.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.125.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.125.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.126.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.126.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.126.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.127.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.127.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.127.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.13.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.13.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.13.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.14.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.14.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.14.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.15.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.15.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.15.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.16.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.16.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.16.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.17.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.17.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.17.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.18.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.18.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.18.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.19.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.19.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.19.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.2.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.2.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.2.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.20.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.20.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.20.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.21.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.21.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.21.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.22.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.22.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.22.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.23.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.23.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.23.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.24.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.24.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.24.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.25.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.25.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.25.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.26.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.26.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.26.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.27.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.27.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.27.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.28.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.28.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.28.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.29.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.29.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.29.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.3.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.3.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.3.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.30.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.30.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.30.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.31.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.31.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.31.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.32.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.32.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.32.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.33.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.33.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.33.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.34.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.34.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.34.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.35.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.35.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.35.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.36.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.36.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.36.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.37.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.37.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.37.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.38.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.38.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.38.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.39.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.39.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.39.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.4.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.4.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.4.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.40.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.40.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.40.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.41.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.41.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.41.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.42.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.42.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.42.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.43.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.43.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.43.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.44.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.44.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.44.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.45.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.45.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.45.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.46.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.46.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.46.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.47.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.47.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.47.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.48.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.48.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.48.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.49.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.49.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.49.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.5.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.5.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.5.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.50.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.50.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.50.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.51.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.51.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.51.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.52.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.52.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.52.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.53.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.53.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.53.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.54.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.54.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.54.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.55.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.55.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.55.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.56.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.56.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.56.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.57.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.57.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.57.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.58.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.58.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.58.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.59.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.59.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.59.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.6.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.6.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.6.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.60.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.60.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.60.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.61.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.61.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.61.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.62.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.62.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.62.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.63.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.63.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.63.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.64.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.64.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.64.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.65.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.65.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.65.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.66.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.66.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.66.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.67.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.67.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.67.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.68.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.68.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.68.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.69.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.69.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.69.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.7.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.7.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.7.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.70.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.70.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.70.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.71.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.71.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.71.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.72.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.72.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.72.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.73.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.73.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.73.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.74.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.74.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.74.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.75.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.75.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.75.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.76.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.76.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.76.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.77.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.77.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.77.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.78.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.78.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.78.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.79.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.79.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.79.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.8.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.8.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.8.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.80.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.80.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.80.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.81.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.81.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.81.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.82.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.82.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.82.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.83.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.83.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.83.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.84.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.84.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.84.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.85.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.85.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.85.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.86.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.86.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.86.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.87.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.87.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.87.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.88.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.88.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.88.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.89.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.89.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.89.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.9.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.9.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.9.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.90.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.90.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.90.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.91.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.91.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.91.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.92.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.92.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.92.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.93.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.93.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.93.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.94.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.94.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.94.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.95.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.95.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.95.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.96.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.96.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.96.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.97.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.97.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.97.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.98.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.98.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.98.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.99.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.99.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.99.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.gate.e_score_correction_bias": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.gate.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.4.mlp.experts.0.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.0.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.1.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.1.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.10.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.10.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.100.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.100.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.100.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.101.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.101.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.101.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.102.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.102.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.102.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.103.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.103.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.103.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.104.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.104.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.104.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.105.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.105.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.105.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.106.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.106.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.106.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.107.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.107.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.107.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.108.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.108.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.108.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.109.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.109.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.109.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.11.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.11.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.110.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.110.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.110.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.111.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.111.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.111.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.112.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.112.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.112.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.113.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.113.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.113.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.114.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.114.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.114.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.115.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.115.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.115.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.116.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.116.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.116.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.117.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.117.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.117.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.118.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.118.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.118.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.119.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.119.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.119.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.12.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.12.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.120.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.120.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.120.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.121.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.121.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.121.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.122.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.122.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.122.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.123.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.123.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.123.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.124.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.124.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.124.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.125.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.125.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.125.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.126.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.126.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.126.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.127.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.127.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.127.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.13.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.13.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.14.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.14.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.15.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.15.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.16.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.16.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.17.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.17.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.18.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.18.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.19.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.19.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.2.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.2.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.20.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.20.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.21.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.21.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.22.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.22.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.23.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.23.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.24.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.24.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.25.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.25.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.26.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.26.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.27.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.27.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.28.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.28.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.29.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.29.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.3.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.3.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.30.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.30.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.31.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.31.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.32.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.32.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.33.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.33.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.34.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.34.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.35.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.35.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.36.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.36.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.37.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.37.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.38.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.38.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.39.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.39.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.4.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.4.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.40.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.40.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.41.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.41.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.42.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.42.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.43.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.43.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.44.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.44.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.45.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.45.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.46.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.46.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.47.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.47.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.48.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.48.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.49.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.49.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.5.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.5.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.50.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.50.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.51.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.51.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.52.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.52.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.53.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.53.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.54.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.54.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.55.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.55.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.56.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.56.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.57.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.57.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.58.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.58.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.59.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.59.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.6.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.6.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.60.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.60.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.61.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.61.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.62.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.62.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.63.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.63.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.64.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.64.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.64.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.65.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.65.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.65.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.66.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.66.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.66.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.67.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.67.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.67.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.68.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.68.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.68.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.69.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.69.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.69.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.7.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.7.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.70.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.70.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.70.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.71.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.71.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.71.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.72.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.72.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.72.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.73.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.73.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.73.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.74.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.74.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.74.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.75.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.75.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.75.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.76.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.76.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.76.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.77.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.77.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.77.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.78.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.78.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.78.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.79.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.79.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.79.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.8.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.8.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.80.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.80.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.80.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.81.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.81.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.81.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.82.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.82.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.82.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.83.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.83.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.83.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.84.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.84.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.84.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.85.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.85.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.85.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.86.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.86.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.86.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.87.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.87.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.87.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.88.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.88.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.88.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.89.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.89.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.89.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.9.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.9.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.90.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.90.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.90.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.91.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.91.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.91.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.92.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.92.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.92.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.93.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.93.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.93.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.94.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.94.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.94.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.95.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.95.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.95.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.96.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.96.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.96.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.97.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.97.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.97.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.98.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.98.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.98.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.99.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.99.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.99.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.gate.e_score_correction_bias": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.gate.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.40.input_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.40.mlp.experts.0.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.0.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.0.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.1.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.1.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.1.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.10.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.10.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.10.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.100.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.100.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.100.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.101.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.101.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.101.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.102.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.102.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.102.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.103.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.103.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.103.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.104.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.104.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.104.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.105.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.105.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.105.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.106.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.106.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.106.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.107.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.107.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.107.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.108.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.108.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.108.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.109.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.109.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.109.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.11.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.11.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.11.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.110.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.110.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.110.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.111.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.111.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.111.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.112.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.112.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.112.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.113.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.113.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.113.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.114.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.114.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.114.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.115.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.115.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.115.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.116.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.116.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.116.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.117.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.117.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.117.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.118.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.118.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.118.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.119.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.119.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.119.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.12.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.12.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.12.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.120.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.120.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.120.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.121.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.121.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.121.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.122.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.122.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.122.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.123.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.123.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.123.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.124.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.124.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.124.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.125.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.125.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.125.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.126.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.126.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.126.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.127.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.127.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.127.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.13.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.13.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.13.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.14.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.14.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.14.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.15.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.15.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.15.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.16.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.16.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.16.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.17.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.17.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.17.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.18.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.18.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.18.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.19.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.19.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.19.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.2.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.2.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.2.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.20.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.20.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.20.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.21.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.21.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.21.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.22.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.22.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.22.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.23.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.23.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.23.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.24.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.24.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.24.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.25.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.25.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.25.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.26.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.26.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.26.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.27.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.27.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.27.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.28.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.28.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.28.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.29.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.29.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.29.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.3.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.3.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.3.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.30.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.30.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.30.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.31.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.31.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.31.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.32.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.32.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.32.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.33.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.33.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.33.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.34.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.34.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.34.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.35.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.35.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.35.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.36.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.36.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.36.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.37.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.37.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.37.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.38.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.38.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.38.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.39.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.39.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.39.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.4.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.4.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.4.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.40.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.40.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.40.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.41.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.41.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.41.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.42.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.42.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.42.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.43.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.43.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.43.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.44.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.44.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.44.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.45.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.45.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.45.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.46.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.46.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.46.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.47.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.47.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.47.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.48.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.48.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.48.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.49.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.49.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.49.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.5.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.5.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.5.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.50.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.50.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.50.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.51.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.51.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.51.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.52.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.52.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.52.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.53.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.53.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.53.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.54.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.54.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.54.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.55.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.55.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.55.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.56.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.56.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.56.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.57.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.57.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.57.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.58.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.58.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.58.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.59.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.59.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.59.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.6.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.6.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.6.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.60.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.60.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.60.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.61.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.61.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.61.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.62.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.62.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.62.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.63.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.63.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.63.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.64.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.64.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.64.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.65.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.65.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.65.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.66.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.66.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.66.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.67.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.67.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.67.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.68.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.68.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.68.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.69.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.69.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.69.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.7.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.7.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.7.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.70.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.70.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.70.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.71.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.71.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.71.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.72.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.72.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.72.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.73.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.73.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.73.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.74.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.74.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.74.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.75.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.75.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.75.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.76.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.76.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.76.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.77.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.77.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.77.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.78.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.78.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.78.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.79.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.79.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.79.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.8.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.8.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.8.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.80.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.80.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.80.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.81.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.81.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.81.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.82.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.82.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.82.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.83.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.83.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.83.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.84.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.84.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.84.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.85.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.85.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.85.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.86.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.86.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.86.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.87.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.87.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.87.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.88.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.88.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.88.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.89.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.89.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.89.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.9.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.9.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.9.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.90.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.90.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.90.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.91.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.91.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.91.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.92.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.92.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.92.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.93.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.93.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.93.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.94.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.94.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.94.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.95.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.95.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.95.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.96.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.96.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.96.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.97.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.97.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.97.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.98.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.98.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.98.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.99.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.99.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.99.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.gate.e_score_correction_bias": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.gate.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.41.input_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.41.mlp.experts.0.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.0.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.0.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.1.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.1.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.1.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.10.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.10.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.10.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.100.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.100.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.100.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.101.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.101.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.101.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.102.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.102.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.102.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.103.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.103.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.103.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.104.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.104.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.104.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.105.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.105.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.105.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.106.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.106.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.106.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.107.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.107.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.107.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.108.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.108.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.108.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.109.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.109.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.109.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.11.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.11.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.11.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.110.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.110.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.110.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.111.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.111.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.111.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.112.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.112.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.112.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.113.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.113.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.113.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.114.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.114.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.114.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.115.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.115.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.115.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.116.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.116.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.116.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.117.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.117.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.117.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.118.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.118.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.118.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.119.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.119.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.119.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.12.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.12.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.12.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.120.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.120.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.120.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.121.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.121.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.121.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.122.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.122.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.122.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.123.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.123.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.123.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.124.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.124.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.124.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.125.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.125.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.125.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.126.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.126.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.126.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.127.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.127.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.127.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.13.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.13.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.13.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.14.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.14.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.14.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.15.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.15.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.15.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.16.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.16.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.16.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.17.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.17.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.17.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.18.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.18.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.18.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.19.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.19.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.19.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.2.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.2.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.2.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.20.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.20.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.20.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.21.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.21.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.21.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.22.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.22.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.22.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.23.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.23.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.23.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.24.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.24.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.24.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.25.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.25.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.25.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.26.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.26.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.26.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.27.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.27.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.27.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.28.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.28.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.28.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.29.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.29.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.29.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.3.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.3.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.3.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.30.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.30.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.30.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.31.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.31.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.31.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.32.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.32.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.32.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.33.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.33.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.33.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.34.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.34.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.34.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.35.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.35.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.35.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.36.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.36.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.36.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.37.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.37.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.37.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.38.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.38.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.38.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.39.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.39.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.39.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.4.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.4.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.4.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.40.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.40.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.40.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.41.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.41.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.41.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.42.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.42.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.42.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.43.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.43.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.43.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.44.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.44.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.44.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.45.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.45.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.45.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.46.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.46.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.46.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.47.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.47.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.47.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.48.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.48.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.48.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.49.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.49.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.49.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.5.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.5.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.5.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.50.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.50.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.50.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.51.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.51.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.51.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.52.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.52.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.52.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.53.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.53.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.53.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.54.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.54.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.54.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.55.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.55.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.55.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.56.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.56.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.56.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.57.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.57.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.57.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.58.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.58.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.58.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.59.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.59.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.59.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.6.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.6.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.6.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.60.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.60.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.60.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.61.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.61.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.61.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.62.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.62.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.62.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.63.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.63.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.63.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.64.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.64.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.64.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.65.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.65.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.65.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.66.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.66.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.66.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.67.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.67.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.67.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.68.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.68.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.68.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.69.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.69.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.69.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.7.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.7.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.7.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.70.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.70.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.70.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.71.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.71.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.71.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.72.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.72.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.72.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.73.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.73.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.73.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.74.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.74.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.74.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.75.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.75.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.75.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.76.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.76.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.76.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.77.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.77.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.77.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.78.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.78.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.78.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.79.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.79.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.79.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.8.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.8.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.8.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.80.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.80.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.80.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.81.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.81.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.81.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.82.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.82.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.82.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.83.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.83.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.83.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.84.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.84.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.84.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.85.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.85.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.85.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.86.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.86.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.86.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.87.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.87.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.87.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.88.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.88.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.88.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.89.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.89.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.89.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.9.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.9.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.9.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.90.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.90.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.90.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.91.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.91.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.91.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.92.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.92.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.92.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.93.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.93.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.93.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.94.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.94.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.94.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.95.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.95.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.95.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.96.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.96.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.96.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.97.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.97.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.97.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.98.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.98.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.98.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.99.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.99.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.99.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.gate.e_score_correction_bias": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.gate.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.42.input_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.42.mlp.experts.0.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.0.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.0.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.1.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.1.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.1.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.10.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.10.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.10.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.100.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.100.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.100.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.101.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.101.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.101.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.102.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.102.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.102.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.103.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.103.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.103.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.104.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.104.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.104.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.105.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.105.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.105.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.106.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.106.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.106.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.107.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.107.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.107.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.108.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.108.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.108.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.109.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.109.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.109.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.11.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.11.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.11.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.110.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.110.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.110.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.111.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.111.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.111.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.112.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.112.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.112.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.113.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.113.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.113.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.114.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.114.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.114.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.115.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.115.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.115.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.116.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.116.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.116.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.117.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.117.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.117.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.118.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.118.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.118.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.119.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.119.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.119.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.12.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.12.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.12.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.120.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.120.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.120.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.121.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.121.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.121.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.122.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.122.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.122.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.123.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.123.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.123.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.124.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.124.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.124.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.125.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.125.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.125.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.126.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.126.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.126.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.127.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.127.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.127.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.13.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.13.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.13.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.14.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.14.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.14.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.15.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.15.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.15.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.16.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.16.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.16.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.17.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.17.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.17.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.18.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.18.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.18.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.19.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.19.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.19.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.2.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.2.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.2.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.20.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.20.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.20.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.21.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.21.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.21.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.22.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.22.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.22.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.23.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.23.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.23.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.24.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.24.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.24.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.25.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.25.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.25.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.26.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.26.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.26.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.27.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.27.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.27.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.28.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.28.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.28.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.29.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.29.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.29.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.3.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.3.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.3.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.30.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.30.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.30.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.31.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.31.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.31.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.32.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.32.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.32.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.33.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.33.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.33.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.34.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.34.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.34.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.35.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.35.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.35.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.36.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.36.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.36.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.37.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.37.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.37.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.38.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.38.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.38.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.39.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.39.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.39.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.4.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.4.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.4.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.40.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.40.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.40.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.41.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.41.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.41.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.42.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.42.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.42.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.43.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.43.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.43.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.44.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.44.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.44.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.45.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.45.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.45.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.46.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.46.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.46.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.47.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.47.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.47.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.48.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.48.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.48.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.49.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.49.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.49.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.5.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.5.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.5.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.50.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.50.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.50.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.51.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.51.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.51.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.52.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.52.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.52.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.53.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.53.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.53.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.54.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.54.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.54.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.55.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.55.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.55.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.56.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.56.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.56.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.57.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.57.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.57.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.58.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.58.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.58.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.59.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.59.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.59.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.6.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.6.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.6.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.60.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.60.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.60.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.61.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.61.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.61.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.62.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.62.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.62.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.63.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.63.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.63.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.64.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.64.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.64.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.65.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.65.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.65.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.66.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.66.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.66.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.67.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.67.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.67.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.68.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.68.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.68.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.69.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.69.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.69.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.7.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.7.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.7.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.70.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.70.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.70.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.71.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.71.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.71.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.72.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.72.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.72.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.73.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.73.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.73.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.74.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.74.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.74.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.75.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.75.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.75.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.76.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.76.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.76.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.77.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.77.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.77.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.78.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.78.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.78.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.79.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.79.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.79.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.8.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.8.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.8.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.80.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.80.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.80.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.81.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.81.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.81.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.82.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.82.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.82.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.83.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.83.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.83.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.84.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.84.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.84.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.85.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.85.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.85.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.86.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.86.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.86.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.87.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.87.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.87.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.88.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.88.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.88.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.89.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.89.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.89.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.9.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.9.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.9.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.90.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.90.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.90.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.91.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.91.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.91.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.92.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.92.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.92.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.93.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.93.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.93.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.94.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.94.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.94.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.95.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.95.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.95.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.96.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.96.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.96.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.97.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.97.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.97.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.98.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.98.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.98.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.99.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.99.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.99.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.gate.e_score_correction_bias": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.gate.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.43.input_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.43.mlp.experts.0.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.0.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.0.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.1.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.1.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.1.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.10.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.10.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.10.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.100.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.100.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.100.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.101.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.101.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.101.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.102.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.102.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.102.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.103.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.103.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.103.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.104.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.104.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.104.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.105.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.105.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.105.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.106.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.106.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.106.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.107.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.107.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.107.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.108.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.108.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.108.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.109.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.109.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.109.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.11.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.11.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.11.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.110.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.110.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.110.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.111.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.111.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.111.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.112.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.112.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.112.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.113.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.113.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.113.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.114.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.114.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.114.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.115.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.115.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.115.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.116.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.116.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.116.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.117.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.117.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.117.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.118.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.118.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.118.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.119.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.119.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.119.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.12.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.12.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.12.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.120.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.120.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.120.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.121.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.121.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.121.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.122.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.122.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.122.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.123.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.123.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.123.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.124.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.124.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.124.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.125.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.125.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.125.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.126.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.126.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.126.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.127.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.127.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.127.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.13.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.13.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.13.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.14.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.14.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.14.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.15.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.15.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.15.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.16.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.16.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.16.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.17.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.17.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.17.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.18.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.18.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.18.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.19.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.19.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.19.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.2.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.2.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.2.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.20.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.20.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.20.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.21.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.21.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.21.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.22.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.22.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.22.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.23.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.23.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.23.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.24.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.24.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.24.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.25.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.25.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.25.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.26.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.26.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.26.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.27.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.27.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.27.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.28.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.28.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.28.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.29.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.29.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.29.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.3.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.3.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.3.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.30.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.30.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.30.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.31.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.31.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.31.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.32.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.32.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.32.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.33.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.33.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.33.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.34.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.34.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.34.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.35.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.35.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.35.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.36.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.36.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.36.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.37.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.37.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.37.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.38.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.38.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.38.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.39.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.39.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.39.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.4.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.4.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.4.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.40.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.40.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.40.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.41.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.41.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.41.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.42.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.42.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.42.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.43.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.43.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.43.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.44.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.44.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.44.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.45.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.45.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.45.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.46.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.46.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.46.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.47.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.47.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.47.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.48.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.48.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.48.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.49.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.49.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.49.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.5.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.5.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.5.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.50.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.50.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.50.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.51.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.51.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.51.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.52.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.52.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.52.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.53.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.53.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.53.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.54.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.54.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.54.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.55.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.55.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.55.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.56.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.56.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.56.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.57.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.57.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.57.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.58.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.58.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.58.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.59.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.59.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.59.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.6.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.6.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.6.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.60.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.60.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.60.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.61.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.61.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.61.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.62.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.62.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.62.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.63.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.63.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.63.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.64.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.64.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.64.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.65.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.65.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.65.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.66.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.66.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.66.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.67.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.67.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.67.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.68.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.68.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.68.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.69.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.69.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.69.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.7.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.7.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.7.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.70.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.70.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.70.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.71.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.71.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.71.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.72.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.72.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.72.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.73.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.73.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.73.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.74.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.74.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.74.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.75.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.75.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.75.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.76.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.76.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.76.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.77.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.77.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.77.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.78.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.78.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.78.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.79.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.79.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.79.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.8.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.8.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.8.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.80.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.80.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.80.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.81.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.81.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.81.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.82.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.82.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.82.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.83.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.83.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.83.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.84.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.84.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.84.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.85.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.85.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.85.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.86.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.86.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.86.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.87.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.87.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.87.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.88.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.88.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.88.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.89.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.89.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.89.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.9.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.9.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.9.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.90.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.90.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.90.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.91.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.91.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.91.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.92.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.92.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.92.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.93.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.93.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.93.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.94.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.94.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.94.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.95.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.95.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.95.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.96.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.96.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.96.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.97.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.97.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.97.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.98.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.98.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.98.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.99.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.99.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.99.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.gate.e_score_correction_bias": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.gate.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.44.input_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.44.mlp.experts.0.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.0.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.0.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.1.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.1.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.1.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.10.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.10.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.10.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.100.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.100.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.100.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.101.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.101.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.101.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.102.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.102.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.102.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.103.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.103.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.103.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.104.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.104.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.104.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.105.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.105.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.105.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.106.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.106.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.106.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.107.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.107.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.107.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.108.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.108.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.108.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.109.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.109.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.109.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.11.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.11.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.11.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.110.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.110.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.110.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.111.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.111.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.111.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.112.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.112.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.112.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.113.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.113.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.113.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.114.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.114.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.114.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.115.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.115.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.115.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.116.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.116.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.116.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.117.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.117.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.117.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.118.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.118.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.118.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.119.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.119.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.119.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.12.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.12.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.12.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.120.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.120.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.120.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.121.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.121.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.121.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.122.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.122.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.122.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.123.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.123.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.123.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.124.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.124.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.124.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.125.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.125.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.125.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.126.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.126.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.126.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.127.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.127.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.127.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.13.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.13.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.13.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.14.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.14.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.14.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.15.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.15.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.15.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.16.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.16.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.16.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.17.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.17.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.17.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.18.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.18.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.18.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.19.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.19.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.19.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.2.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.2.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.2.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.20.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.20.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.20.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.21.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.21.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.21.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.22.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.22.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.22.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.23.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.23.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.23.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.24.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.24.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.24.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.25.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.25.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.25.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.26.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.26.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.26.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.27.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.27.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.27.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.28.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.28.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.28.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.29.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.29.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.29.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.3.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.3.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.3.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.30.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.30.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.30.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.31.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.31.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.31.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.32.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.32.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.32.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.33.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.33.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.33.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.34.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.34.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.34.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.35.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.35.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.35.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.36.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.36.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.36.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.37.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.37.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.37.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.38.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.38.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.38.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.39.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.39.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.39.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.4.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.4.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.4.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.40.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.40.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.40.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.41.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.41.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.41.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.42.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.42.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.42.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.43.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.43.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.43.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.44.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.44.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.44.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.45.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.45.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.45.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.46.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.46.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.46.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.47.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.47.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.47.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.48.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.48.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.48.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.49.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.49.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.49.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.5.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.5.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.5.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.50.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.50.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.50.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.51.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.51.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.51.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.52.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.52.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.52.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.53.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.53.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.53.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.54.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.54.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.54.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.55.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.55.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.55.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.56.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.56.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.56.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.57.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.57.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.57.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.58.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.58.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.58.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.59.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.59.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.59.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.6.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.6.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.6.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.60.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.60.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.60.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.61.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.61.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.61.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.62.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.62.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.62.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.63.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.63.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.63.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.64.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.64.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.64.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.65.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.65.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.65.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.66.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.66.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.66.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.67.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.67.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.67.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.68.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.68.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.68.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.69.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.69.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.69.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.7.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.7.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.7.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.70.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.70.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.70.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.71.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.71.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.71.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.72.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.72.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.72.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.73.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.73.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.73.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.74.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.74.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.74.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.75.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.75.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.75.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.76.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.76.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.76.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.77.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.77.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.77.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.78.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.78.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.78.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.79.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.79.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.79.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.8.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.8.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.8.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.80.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.80.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.80.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.81.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.81.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.81.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.82.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.82.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.82.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.83.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.83.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.83.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.84.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.84.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.84.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.85.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.85.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.85.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.86.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.86.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.86.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.87.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.87.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.87.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.88.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.88.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.88.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.89.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.89.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.89.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.9.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.9.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.9.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.90.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.90.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.90.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.91.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.91.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.91.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.92.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.92.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.92.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.93.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.93.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.93.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.94.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.94.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.94.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.95.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.95.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.95.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.96.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.96.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.96.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.97.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.97.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.97.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.98.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.98.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.98.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.99.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.99.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.99.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.gate.e_score_correction_bias": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.gate.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.45.input_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.45.mlp.experts.0.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.0.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.0.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.1.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.1.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.1.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.10.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.10.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.10.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.100.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.100.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.100.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.101.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.101.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.101.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.102.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.102.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.102.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.103.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.103.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.103.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.104.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.104.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.104.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.105.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.105.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.105.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.106.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.106.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.106.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.107.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.107.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.107.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.108.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.108.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.108.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.109.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.109.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.109.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.11.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.11.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.11.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.110.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.110.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.110.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.111.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.111.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.111.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.112.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.112.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.112.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.113.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.113.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.113.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.114.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.114.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.114.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.115.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.115.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.115.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.116.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.116.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.116.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.117.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.117.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.117.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.118.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.118.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.118.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.119.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.119.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.119.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.12.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.12.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.12.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.120.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.120.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.120.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.121.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.121.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.121.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.122.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.122.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.122.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.123.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.123.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.123.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.124.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.124.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.124.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.125.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.125.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.125.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.126.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.126.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.126.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.127.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.127.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.127.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.13.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.13.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.13.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.14.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.14.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.14.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.15.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.15.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.15.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.16.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.16.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.16.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.17.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.17.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.17.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.18.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.18.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.18.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.19.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.19.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.19.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.2.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.2.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.2.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.20.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.20.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.20.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.21.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.21.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.21.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.22.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.22.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.22.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.23.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.23.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.23.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.24.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.24.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.24.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.25.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.25.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.25.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.26.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.26.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.26.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.27.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.27.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.27.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.28.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.28.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.28.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.29.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.29.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.29.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.3.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.3.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.3.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.30.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.30.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.30.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.31.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.31.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.31.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.32.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.32.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.32.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.33.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.33.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.33.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.34.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.34.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.34.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.35.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.35.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.35.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.36.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.36.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.36.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.37.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.37.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.37.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.38.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.38.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.38.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.39.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.39.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.39.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.4.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.4.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.4.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.40.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.40.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.40.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.41.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.41.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.41.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.42.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.42.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.42.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.43.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.43.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.43.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.44.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.44.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.44.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.45.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.45.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.45.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.46.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.46.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.46.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.47.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.47.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.47.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.48.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.48.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.48.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.49.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.49.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.49.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.5.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.5.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.5.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.50.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.50.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.50.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.51.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.51.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.51.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.52.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.52.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.52.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.53.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.53.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.53.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.54.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.54.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.54.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.55.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.55.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.55.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.56.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.56.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.56.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.57.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.57.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.57.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.58.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.58.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.58.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.59.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.59.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.59.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.6.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.6.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.6.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.60.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.60.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.60.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.61.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.61.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.61.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.62.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.62.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.62.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.63.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.63.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.63.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.64.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.64.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.64.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.65.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.65.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.65.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.66.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.66.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.66.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.67.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.67.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.67.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.68.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.68.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.68.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.69.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.69.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.69.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.7.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.7.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.7.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.70.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.70.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.70.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.71.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.71.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.71.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.72.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.72.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.72.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.73.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.73.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.73.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.74.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.74.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.74.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.75.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.75.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.75.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.76.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.76.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.76.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.77.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.77.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.77.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.78.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.78.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.78.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.79.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.79.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.79.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.8.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.8.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.8.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.80.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.80.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.80.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.81.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.81.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.81.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.82.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.82.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.82.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.83.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.83.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.83.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.84.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.84.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.84.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.85.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.85.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.85.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.86.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.86.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.86.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.87.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.87.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.87.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.88.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.88.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.88.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.89.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.89.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.89.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.9.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.9.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.9.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.90.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.90.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.90.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.91.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.91.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.91.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.92.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.92.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.92.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.93.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.93.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.93.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.94.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.94.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.94.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.95.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.95.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.95.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.96.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.96.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.96.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.97.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.97.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.97.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.98.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.98.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.98.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.99.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.99.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.99.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.gate.e_score_correction_bias": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.gate.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.5.mlp.experts.0.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.0.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.1.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.1.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.10.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.10.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.100.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.100.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.100.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.101.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.101.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.101.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.102.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.102.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.102.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.103.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.103.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.103.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.104.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.104.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.104.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.105.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.105.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.105.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.106.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.106.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.106.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.107.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.107.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.107.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.108.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.108.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.108.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.109.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.109.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.109.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.11.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.11.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.110.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.110.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.110.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.111.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.111.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.111.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.112.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.112.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.112.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.113.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.113.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.113.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.114.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.114.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.114.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.115.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.115.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.115.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.116.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.116.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.116.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.117.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.117.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.117.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.118.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.118.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.118.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.119.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.119.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.119.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.12.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.12.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.120.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.120.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.120.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.121.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.121.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.121.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.122.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.122.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.122.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.123.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.123.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.123.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.124.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.124.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.124.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.125.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.125.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.125.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.126.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.126.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.126.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.127.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.127.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.127.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.13.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.13.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.14.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.14.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.15.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.15.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.16.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.16.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.17.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.17.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.18.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.18.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.19.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.19.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.2.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.2.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.20.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.20.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.21.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.21.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.22.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.22.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.23.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.23.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.24.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.24.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.25.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.25.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.26.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.26.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.27.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.27.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.28.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.28.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.29.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.29.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.3.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.3.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.30.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.30.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.31.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.31.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.32.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.32.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.33.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.33.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.34.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.34.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.35.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.35.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.36.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.36.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.37.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.37.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.38.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.38.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.39.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.39.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.4.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.4.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.40.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.40.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.41.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.41.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.42.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.42.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.43.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.43.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.44.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.44.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.45.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.45.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.46.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.46.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.47.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.47.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.48.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.48.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.49.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.49.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.5.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.5.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.50.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.50.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.51.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.51.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.52.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.52.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.53.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.53.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.54.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.54.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.55.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.55.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.56.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.56.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.57.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.57.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.58.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.58.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.59.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.59.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.6.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.6.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.60.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.60.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.61.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.61.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.62.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.62.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.63.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.63.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.64.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.64.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.64.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.65.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.65.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.65.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.66.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.66.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.66.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.67.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.67.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.67.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.68.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.68.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.68.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.69.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.69.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.69.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.7.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.7.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.70.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.70.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.70.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.71.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.71.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.71.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.72.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.72.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.72.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.73.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.73.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.73.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.74.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.74.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.74.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.75.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.75.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.75.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.76.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.76.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.76.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.77.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.77.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.77.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.78.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.78.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.78.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.79.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.79.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.79.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.8.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.8.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.80.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.80.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.80.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.81.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.81.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.81.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.82.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.82.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.82.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.83.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.83.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.83.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.84.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.84.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.84.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.85.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.85.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.85.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.86.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.86.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.86.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.87.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.87.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.87.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.88.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.88.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.88.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.89.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.89.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.89.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.9.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.9.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.90.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.90.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.90.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.91.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.91.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.91.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.92.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.92.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.92.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.93.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.93.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.93.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.94.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.94.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.94.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.95.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.95.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.95.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.96.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.96.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.96.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.97.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.97.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.97.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.98.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.98.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.98.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.99.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.99.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.99.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.gate.e_score_correction_bias": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.gate.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.6.mlp.experts.0.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.0.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.1.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.1.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.10.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.10.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.100.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.100.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.100.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.101.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.101.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.101.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.102.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.102.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.102.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.103.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.103.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.103.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.104.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.104.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.104.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.105.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.105.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.105.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.106.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.106.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.106.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.107.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.107.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.107.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.108.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.108.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.108.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.109.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.109.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.109.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.11.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.11.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.110.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.110.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.110.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.111.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.111.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.111.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.112.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.112.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.112.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.113.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.113.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.113.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.114.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.114.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.114.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.115.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.115.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.115.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.116.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.116.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.116.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.117.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.117.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.117.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.118.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.118.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.118.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.119.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.119.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.119.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.12.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.12.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.120.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.120.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.120.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.121.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.121.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.121.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.122.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.122.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.122.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.123.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.123.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.123.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.124.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.124.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.124.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.125.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.125.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.125.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.126.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.126.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.126.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.127.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.127.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.127.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.13.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.13.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.14.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.14.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.15.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.15.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.16.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.16.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.17.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.17.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.18.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.18.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.19.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.19.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.2.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.2.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.20.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.20.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.21.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.21.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.22.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.22.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.23.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.23.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.24.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.24.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.25.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.25.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.26.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.26.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.27.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.27.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.28.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.28.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.29.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.29.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.3.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.3.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.30.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.30.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.31.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.31.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.32.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.32.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.33.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.33.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.34.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.34.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.35.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.35.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.36.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.36.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.37.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.37.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.38.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.38.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.39.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.39.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.4.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.4.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.40.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.40.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.41.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.41.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.42.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.42.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.43.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.43.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.44.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.44.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.45.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.45.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.46.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.46.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.47.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.47.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.48.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.48.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.49.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.49.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.5.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.5.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.50.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.50.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.51.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.51.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.52.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.52.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.53.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.53.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.54.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.54.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.55.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.55.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.56.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.56.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.57.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.57.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.58.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.58.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.59.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.59.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.6.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.6.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.60.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.60.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.61.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.61.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.62.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.62.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.63.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.63.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.64.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.64.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.64.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.65.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.65.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.65.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.66.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.66.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.66.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.67.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.67.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.67.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.68.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.68.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.68.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.69.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.69.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.69.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.7.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.7.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.70.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.70.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.70.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.71.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.71.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.71.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.72.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.72.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.72.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.73.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.73.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.73.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.74.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.74.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.74.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.75.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.75.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.75.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.76.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.76.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.76.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.77.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.77.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.77.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.78.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.78.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.78.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.79.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.79.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.79.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.8.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.8.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.80.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.80.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.80.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.81.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.81.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.81.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.82.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.82.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.82.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.83.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.83.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.83.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.84.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.84.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.84.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.85.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.85.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.85.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.86.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.86.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.86.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.87.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.87.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.87.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.88.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.88.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.88.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.89.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.89.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.89.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.9.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.9.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.90.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.90.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.90.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.91.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.91.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.91.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.92.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.92.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.92.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.93.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.93.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.93.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.94.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.94.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.94.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.95.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.95.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.95.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.96.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.96.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.96.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.97.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.97.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.97.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.98.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.98.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.98.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.99.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.99.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.99.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.gate.e_score_correction_bias": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.gate.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.7.mlp.experts.0.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.0.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.1.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.1.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.10.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.10.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.100.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.100.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.100.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.101.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.101.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.101.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.102.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.102.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.102.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.103.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.103.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.103.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.104.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.104.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.104.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.105.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.105.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.105.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.106.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.106.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.106.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.107.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.107.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.107.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.108.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.108.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.108.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.109.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.109.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.109.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.11.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.11.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.110.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.110.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.110.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.111.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.111.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.111.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.112.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.112.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.112.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.113.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.113.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.113.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.114.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.114.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.114.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.115.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.115.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.115.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.116.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.116.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.116.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.117.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.117.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.117.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.118.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.118.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.118.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.119.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.119.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.119.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.12.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.12.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.120.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.120.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.120.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.121.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.121.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.121.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.122.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.122.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.122.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.123.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.123.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.123.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.124.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.124.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.124.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.125.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.125.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.125.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.126.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.126.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.126.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.127.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.127.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.127.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.13.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.13.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.14.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.14.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.15.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.15.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.16.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.16.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.17.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.17.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.18.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.18.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.19.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.19.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.2.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.2.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.20.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.20.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.21.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.21.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.22.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.22.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.23.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.23.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.24.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.24.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.25.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.25.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.26.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.26.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.27.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.27.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.28.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.28.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.29.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.29.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.3.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.3.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.30.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.30.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.31.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.31.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.32.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.32.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.33.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.33.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.34.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.34.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.35.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.35.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.36.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.36.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.37.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.37.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.38.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.38.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.39.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.39.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.4.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.4.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.40.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.40.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.41.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.41.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.42.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.42.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.43.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.43.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.44.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.44.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.45.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.45.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.46.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.46.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.47.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.47.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.48.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.48.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.49.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.49.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.5.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.5.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.50.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.50.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.51.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.51.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.52.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.52.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.53.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.53.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.54.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.54.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.55.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.55.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.56.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.56.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.57.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.57.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.58.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.58.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.59.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.59.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.6.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.6.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.60.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.60.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.61.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.61.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.62.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.62.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.63.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.63.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.64.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.64.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.64.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.65.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.65.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.65.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.66.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.66.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.66.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.67.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.67.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.67.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.68.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.68.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.68.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.69.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.69.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.69.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.7.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.7.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.70.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.70.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.70.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.71.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.71.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.71.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.72.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.72.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.72.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.73.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.73.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.73.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.74.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.74.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.74.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.75.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.75.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.75.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.76.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.76.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.76.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.77.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.77.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.77.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.78.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.78.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.78.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.79.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.79.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.79.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.8.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.8.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.80.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.80.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.80.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.81.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.81.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.81.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.82.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.82.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.82.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.83.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.83.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.83.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.84.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.84.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.84.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.85.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.85.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.85.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.86.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.86.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.86.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.87.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.87.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.87.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.88.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.88.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.88.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.89.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.89.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.89.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.9.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.9.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.90.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.90.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.90.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.91.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.91.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.91.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.92.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.92.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.92.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.93.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.93.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.93.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.94.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.94.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.94.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.95.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.95.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.95.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.96.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.96.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.96.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.97.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.97.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.97.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.98.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.98.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.98.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.99.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.99.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.99.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.gate.e_score_correction_bias": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.gate.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.8.mlp.experts.0.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.0.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.1.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.1.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.10.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.10.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.100.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.100.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.100.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.101.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.101.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.101.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.102.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.102.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.102.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.103.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.103.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.103.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.104.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.104.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.104.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.105.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.105.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.105.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.106.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.106.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.106.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.107.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.107.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.107.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.108.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.108.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.108.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.109.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.109.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.109.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.11.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.11.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.110.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.110.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.110.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.111.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.111.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.111.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.112.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.112.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.112.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.113.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.113.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.113.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.114.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.114.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.114.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.115.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.115.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.115.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.116.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.116.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.116.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.117.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.117.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.117.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.118.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.118.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.118.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.119.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.119.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.119.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.12.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.12.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.120.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.120.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.120.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.121.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.121.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.121.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.122.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.122.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.122.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.123.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.123.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.123.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.124.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.124.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.124.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.125.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.125.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.125.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.126.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.126.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.126.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.127.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.127.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.127.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.13.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.13.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.14.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.14.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.15.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.15.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.16.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.16.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.17.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.17.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.18.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.18.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.19.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.19.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.2.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.2.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.20.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.20.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.21.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.21.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.22.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.22.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.23.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.23.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.24.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.24.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.25.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.25.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.26.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.26.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.27.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.27.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.28.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.28.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.29.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.29.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.3.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.3.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.30.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.30.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.31.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.31.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.32.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.32.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.33.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.33.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.34.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.34.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.35.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.35.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.36.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.36.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.37.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.37.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.38.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.38.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.39.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.39.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.4.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.4.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.40.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.40.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.41.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.41.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.42.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.42.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.43.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.43.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.44.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.44.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.45.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.45.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.46.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.46.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.47.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.47.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.48.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.48.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.49.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.49.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.5.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.5.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.50.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.50.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.51.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.51.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.52.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.52.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.53.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.53.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.54.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.54.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.55.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.55.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.56.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.56.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.57.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.57.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.58.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.58.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.59.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.59.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.6.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.6.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.60.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.60.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.61.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.61.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.62.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.62.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.63.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.63.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.64.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.64.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.64.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.65.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.65.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.65.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.66.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.66.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.66.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.67.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.67.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.67.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.68.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.68.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.68.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.69.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.69.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.69.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.7.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.7.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.70.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.70.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.70.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.71.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.71.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.71.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.72.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.72.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.72.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.73.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.73.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.73.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.74.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.74.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.74.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.75.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.75.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.75.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.76.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.76.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.76.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.77.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.77.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.77.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.78.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.78.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.78.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.79.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.79.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.79.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.8.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.8.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.80.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.80.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.80.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.81.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.81.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.81.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.82.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.82.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.82.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.83.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.83.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.83.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.84.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.84.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.84.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.85.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.85.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.85.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.86.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.86.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.86.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.87.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.87.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.87.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.88.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.88.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.88.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.89.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.89.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.89.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.9.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.9.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.90.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.90.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.90.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.91.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.91.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.91.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.92.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.92.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.92.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.93.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.93.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.93.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.94.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.94.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.94.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.95.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.95.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.95.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.96.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.96.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.96.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.97.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.97.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.97.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.98.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.98.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.98.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.99.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.99.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.99.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.gate.e_score_correction_bias": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.gate.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.9.mlp.experts.0.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.0.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.1.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.1.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.10.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.10.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.100.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.100.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.100.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.101.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.101.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.101.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.102.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.102.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.102.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.103.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.103.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.103.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.104.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.104.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.104.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.105.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.105.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.105.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.106.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.106.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.106.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.107.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.107.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.107.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.108.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.108.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.108.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.109.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.109.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.109.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.11.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.11.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.110.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.110.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.110.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.111.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.111.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.111.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.112.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.112.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.112.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.113.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.113.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.113.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.114.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.114.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.114.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.115.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.115.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.115.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.116.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.116.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.116.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.117.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.117.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.117.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.118.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.118.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.118.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.119.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.119.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.119.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.12.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.12.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.120.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.120.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.120.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.121.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.121.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.121.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.122.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.122.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.122.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.123.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.123.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.123.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.124.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.124.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.124.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.125.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.125.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.125.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.126.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.126.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.126.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.127.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.127.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.127.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.13.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.13.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.14.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.14.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.15.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.15.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.16.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.16.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.17.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.17.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.18.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.18.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.19.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.19.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.2.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.2.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.20.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.20.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.21.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.21.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.22.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.22.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.23.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.23.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.24.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.24.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.25.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.25.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.26.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.26.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.27.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.27.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.28.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.28.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.29.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.29.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.3.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.3.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.30.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.30.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.31.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.31.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.32.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.32.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.33.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.33.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.34.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.34.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.35.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.35.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.36.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.36.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.37.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.37.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.38.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.38.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.39.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.39.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.4.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.4.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.40.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.40.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.41.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.41.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.42.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.42.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.43.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.43.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.44.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.44.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.45.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.45.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.46.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.46.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.47.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.47.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.48.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.48.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.49.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.49.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.5.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.5.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.50.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.50.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.51.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.51.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.52.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.52.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.53.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.53.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.54.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.54.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.55.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.55.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.56.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.56.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.57.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.57.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.58.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.58.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.59.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.59.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.6.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.6.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.60.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.60.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.61.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.61.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.62.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.62.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.63.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.63.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.64.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.64.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.64.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.65.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.65.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.65.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.66.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.66.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.66.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.67.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.67.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.67.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.68.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.68.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.68.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.69.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.69.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.69.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.7.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.7.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.70.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.70.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.70.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.71.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.71.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.71.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.72.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.72.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.72.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.73.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.73.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.73.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.74.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.74.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.74.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.75.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.75.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.75.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.76.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.76.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.76.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.77.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.77.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.77.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.78.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.78.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.78.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.79.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.79.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.79.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.8.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.8.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.80.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.80.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.80.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.81.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.81.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.81.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.82.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.82.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.82.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.83.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.83.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.83.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.84.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.84.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.84.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.85.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.85.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.85.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.86.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.86.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.86.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.87.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.87.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.87.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.88.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.88.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.88.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.89.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.89.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.89.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.9.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.9.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.90.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.90.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.90.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.91.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.91.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.91.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.92.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.92.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.92.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.93.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.93.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.93.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.94.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.94.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.94.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.95.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.95.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.95.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.96.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.96.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.96.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.97.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.97.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.97.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.98.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.98.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.98.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.99.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.99.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.99.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.gate.e_score_correction_bias": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.gate.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.norm.weight": "model-00003-of-00048.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..47e7ec6fc39e9a26ea382317b9f9421fbd75f603 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,34 @@ +{ + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|im_end|>" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..8a090ee6b8bb2f47ede5c58e267ffd79dcdfcbe5 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:840a2be2f18847f07571118fb785c9bde4726991852229d98469e421bf5d1064 +size 19971076 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f0911eb841a95c460097641c49e61a7dbf55ac33 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,341 @@ +{ + "added_tokens_decoder": { + "151329": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151330": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151331": { + "content": "[gMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151332": { + "content": "[sMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151333": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151334": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151335": { + "content": "<|system|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151336": { + "content": "<|user|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151337": { + "content": "<|assistant|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151338": { + "content": "<|observation|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151339": { + "content": "<|begin_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151340": { + "content": "<|end_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151341": { + "content": "<|begin_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151342": { + "content": "<|end_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151343": { + "content": "<|begin_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151344": { + "content": "<|end_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151345": { + "content": "<|begin_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151346": { + "content": "<|end_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151347": { + "content": "<|code_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151348": { + "content": "<|code_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151349": { + "content": "<|code_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151350": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151351": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151352": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151353": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151354": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151355": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151356": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151357": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151358": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151359": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151360": { + "content": "/nothink", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151361": { + "content": "<|begin_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151362": { + "content": "<|end_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151363": { + "content": "<|image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151364": { + "content": "<|video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151365": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151366": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "clean_up_tokenization_spaces": false, + "do_lower_case": false, + "eos_token": "<|im_end|>", + "extra_special_tokens": {}, + "model_max_length": 128000, + "pad_token": "<|im_end|>", + "padding_side": "left", + "remove_space": false, + "tokenizer_class": "PreTrainedTokenizerFast" +}