Upload optimized ONNX model
Browse files- .gitattributes +11 -0
- chat_template.jinja +1 -0
- config.json +16 -11
- generation_config.json +1 -1
- onnx/model.onnx +2 -2
- onnx/model.onnx_data +2 -2
- onnx/model.onnx_data_1 +3 -0
- onnx/model.onnx_data_2 +3 -0
- onnx/model.onnx_data_3 +3 -0
- onnx/model.onnx_data_4 +3 -0
- onnx/model.onnx_data_5 +3 -0
- onnx/model.onnx_data_6 +3 -0
- onnx/model.onnx_data_7 +3 -0
- onnx/model_fp16.onnx +2 -2
- onnx/model_fp16.onnx_data +2 -2
- onnx/model_fp16.onnx_data_1 +3 -0
- onnx/model_fp16.onnx_data_2 +3 -0
- onnx/model_fp16.onnx_data_3 +3 -0
- onnx/model_q4.onnx +2 -2
- onnx/model_q4.onnx_data +2 -2
- onnx/model_q4.onnx_data_1 +3 -0
- onnx/model_q4f16.onnx +2 -2
- onnx/model_q4f16.onnx_data +2 -2
- onnx/model_q4f16.onnx_data_1 +2 -2
- tokenizer.json +2 -2
- tokenizer_config.json +3 -3
.gitattributes
CHANGED
|
@@ -39,3 +39,14 @@ onnx/model_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
|
|
| 39 |
onnx/model_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
|
| 40 |
onnx/model_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
|
| 41 |
onnx/model_q4f16.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
onnx/model_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
|
| 40 |
onnx/model_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
|
| 41 |
onnx/model_q4f16.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
onnx/model.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
onnx/model.onnx_data_2 filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
onnx/model.onnx_data_3 filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
onnx/model.onnx_data_4 filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
onnx/model.onnx_data_5 filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
onnx/model.onnx_data_6 filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
onnx/model.onnx_data_7 filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
onnx/model_fp16.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
onnx/model_fp16.onnx_data_2 filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
onnx/model_fp16.onnx_data_3 filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
onnx/model_q4.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
|
chat_template.jinja
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}
|
config.json
CHANGED
|
@@ -1,11 +1,16 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "microsoft/Phi-4-mini-instruct",
|
| 3 |
"architectures": [
|
| 4 |
"Phi3ForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_bias": false,
|
| 7 |
"attention_dropout": 0.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"bos_token_id": 199999,
|
|
|
|
| 9 |
"embd_pdrop": 0.0,
|
| 10 |
"eos_token_id": 199999,
|
| 11 |
"full_attn_mod": 1,
|
|
@@ -26,7 +31,7 @@
|
|
| 26 |
"partial_rotary_factor": 0.75,
|
| 27 |
"resid_pdrop": 0.0,
|
| 28 |
"rms_norm_eps": 1e-05,
|
| 29 |
-
"
|
| 30 |
"long_factor": [
|
| 31 |
1,
|
| 32 |
1.118320672,
|
|
@@ -77,6 +82,8 @@
|
|
| 77 |
44.16,
|
| 78 |
47.77
|
| 79 |
],
|
|
|
|
|
|
|
| 80 |
"short_factor": [
|
| 81 |
1.0,
|
| 82 |
1.0,
|
|
@@ -132,21 +139,19 @@
|
|
| 132 |
"rope_theta": 10000.0,
|
| 133 |
"sliding_window": 262144,
|
| 134 |
"tie_word_embeddings": true,
|
| 135 |
-
"
|
| 136 |
-
"transformers_version": "4.50.0.dev0",
|
| 137 |
"use_cache": true,
|
| 138 |
"vocab_size": 200064,
|
| 139 |
"transformers.js_config": {
|
| 140 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 141 |
"kv_cache_dtype": {
|
| 142 |
"q4f16": "float16",
|
| 143 |
"fp16": "float16"
|
| 144 |
-
},
|
| 145 |
-
"use_external_data_format": {
|
| 146 |
-
"model.onnx": 1,
|
| 147 |
-
"model_fp16.onnx": 1,
|
| 148 |
-
"model_q4.onnx": 1,
|
| 149 |
-
"model_q4f16.onnx": 2
|
| 150 |
}
|
| 151 |
}
|
| 152 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"Phi3ForCausalLM"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
| 9 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
|
| 10 |
+
"AutoTokenizer": "Xenova/gpt-4o"
|
| 11 |
+
},
|
| 12 |
"bos_token_id": 199999,
|
| 13 |
+
"dtype": "bfloat16",
|
| 14 |
"embd_pdrop": 0.0,
|
| 15 |
"eos_token_id": 199999,
|
| 16 |
"full_attn_mod": 1,
|
|
|
|
| 31 |
"partial_rotary_factor": 0.75,
|
| 32 |
"resid_pdrop": 0.0,
|
| 33 |
"rms_norm_eps": 1e-05,
|
| 34 |
+
"rope_parameters": {
|
| 35 |
"long_factor": [
|
| 36 |
1,
|
| 37 |
1.118320672,
|
|
|
|
| 82 |
44.16,
|
| 83 |
47.77
|
| 84 |
],
|
| 85 |
+
"rope_theta": 10000.0,
|
| 86 |
+
"rope_type": "longrope",
|
| 87 |
"short_factor": [
|
| 88 |
1.0,
|
| 89 |
1.0,
|
|
|
|
| 139 |
"rope_theta": 10000.0,
|
| 140 |
"sliding_window": 262144,
|
| 141 |
"tie_word_embeddings": true,
|
| 142 |
+
"transformers_version": "5.0.0.dev0",
|
|
|
|
| 143 |
"use_cache": true,
|
| 144 |
"vocab_size": 200064,
|
| 145 |
"transformers.js_config": {
|
| 146 |
+
"use_external_data_format": {
|
| 147 |
+
"model.onnx": 8,
|
| 148 |
+
"model_fp16.onnx": 4,
|
| 149 |
+
"model_q4.onnx": 2,
|
| 150 |
+
"model_q4f16.onnx": 2
|
| 151 |
+
},
|
| 152 |
"kv_cache_dtype": {
|
| 153 |
"q4f16": "float16",
|
| 154 |
"fp16": "float16"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 155 |
}
|
| 156 |
}
|
| 157 |
}
|
generation_config.json
CHANGED
|
@@ -6,5 +6,5 @@
|
|
| 6 |
199999
|
| 7 |
],
|
| 8 |
"pad_token_id": 199999,
|
| 9 |
-
"transformers_version": "
|
| 10 |
}
|
|
|
|
| 6 |
199999
|
| 7 |
],
|
| 8 |
"pad_token_id": 199999,
|
| 9 |
+
"transformers_version": "5.0.0.dev0"
|
| 10 |
}
|
onnx/model.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7b3bc8f2ccc546a3db64cb083b7566ae0379daa137a1dcc3cad97458d3861a9
|
| 3 |
+
size 765149
|
onnx/model.onnx_data
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5e003644ccf8a555bc8a47fb5f1db44be661c75495e6113af1e894afe2642c7
|
| 3 |
+
size 2458386432
|
onnx/model.onnx_data_1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8aae6a27a25e9f006d8d64b0b477fa71f395ea47e2410b7a6fb5a1557b3390a9
|
| 3 |
+
size 2076315648
|
onnx/model.onnx_data_2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8feb1b1b4f466b7e62e4bdfc3497568eb0df2a80ccbedcaf370ff2ef7a1d5704
|
| 3 |
+
size 2051149824
|
onnx/model.onnx_data_3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:203d8f6977f3566a56921a2b76bc6fece27f8d0548de94832bb57bd2da8bfa94
|
| 3 |
+
size 2013388800
|
onnx/model.onnx_data_4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fb8230de4ed19e78defb04432975fbb2ad4ef4f92cb54bbcacffc4e1e59f6bc
|
| 3 |
+
size 2013388800
|
onnx/model.onnx_data_5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:713e09c1343cc1e64a3f3fc157693ec3b08b353a0e89f0ae568bacaf7f0b3db1
|
| 3 |
+
size 2013388800
|
onnx/model.onnx_data_6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18330921aaf83d05e48130e67002b3ec7a122e17978721cbcabd62374603f800
|
| 3 |
+
size 2013388800
|
onnx/model.onnx_data_7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc52557ecf95f564fdf537a75de8d95852443261a6e4d747d69ca80401ec6541
|
| 3 |
+
size 756584448
|
onnx/model_fp16.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b490f6dbce4c1ac814cb99d2d795d97a083ce94c283f544e1d9e482e98fff6f
|
| 3 |
+
size 766643
|
onnx/model_fp16.onnx_data
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5c305fe1b67de9fd15f2b14668490562441ab3772aa4f6b55405da569a7cd8b
|
| 3 |
+
size 2084892672
|
onnx/model_fp16.onnx_data_1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c599f18f950bd6b9306464b0500beb769e4f443c48410d7557a8702a3a5de20e
|
| 3 |
+
size 2063720448
|
onnx/model_fp16.onnx_data_2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0fcf7693b163be40c8f761f0b1017bcbe91c779bfed92912369363fdfcf55e4a
|
| 3 |
+
size 2063720448
|
onnx/model_fp16.onnx_data_3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3450755dc9afb48dc5ce286cecb51ab3d01c006195c5394d6d2143554b69c617
|
| 3 |
+
size 1485662208
|
onnx/model_q4.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6da980b3746861c25fc5137f835fca7a78df69e5adc4c5d159be1404afaa527c
|
| 3 |
+
size 848557
|
onnx/model_q4.onnx_data
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5e003644ccf8a555bc8a47fb5f1db44be661c75495e6113af1e894afe2642c7
|
| 3 |
+
size 2458386432
|
onnx/model_q4.onnx_data_1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cec4bdbc68288e38486fa8e653e8b49e882b92f3dd17e7cfab29cc1127fd3607
|
| 3 |
+
size 2065969152
|
onnx/model_q4f16.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71e4e9e7b9d216b720e802acac7ef36d50dc253b860d7a5599e10482276351cd
|
| 3 |
+
size 849814
|
onnx/model_q4f16.onnx_data
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89e17f87c1109f4d9f71350deb4104c05f90803a0b1f07d5e7fdd34b69e3ec24
|
| 3 |
+
size 2093094912
|
onnx/model_q4f16.onnx_data_1
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44838ae340ab4e836d488977aea082a9be1978800466a96a266c593bc947010e
|
| 3 |
+
size 974389248
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5ee8c0b1f9862ab7052a99edd2f8f3e69258b2d2670c5880bb44d3fc0599c4c
|
| 3 |
+
size 13303003
|
tokenizer_config.json
CHANGED
|
@@ -101,12 +101,12 @@
|
|
| 101 |
}
|
| 102 |
},
|
| 103 |
"bos_token": "<|endoftext|>",
|
| 104 |
-
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
|
| 105 |
"clean_up_tokenization_spaces": false,
|
| 106 |
"eos_token": "<|endoftext|>",
|
| 107 |
"extra_special_tokens": {},
|
| 108 |
"model_max_length": 131072,
|
| 109 |
"pad_token": "<|endoftext|>",
|
| 110 |
"tokenizer_class": "GPT2Tokenizer",
|
| 111 |
-
"unk_token": "<|endoftext|>"
|
| 112 |
-
}
|
|
|
|
|
|
| 101 |
}
|
| 102 |
},
|
| 103 |
"bos_token": "<|endoftext|>",
|
|
|
|
| 104 |
"clean_up_tokenization_spaces": false,
|
| 105 |
"eos_token": "<|endoftext|>",
|
| 106 |
"extra_special_tokens": {},
|
| 107 |
"model_max_length": 131072,
|
| 108 |
"pad_token": "<|endoftext|>",
|
| 109 |
"tokenizer_class": "GPT2Tokenizer",
|
| 110 |
+
"unk_token": "<|endoftext|>",
|
| 111 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}"
|
| 112 |
+
}
|