Hugging Face's logo

HIT-TMG
/
Uni-MoE-2.0-Base

Any-to-Any
Safetensors
English
Chinese
grin_qwen2_vl
MoE
Unified Generation
Multi-modal
Model card Files
xet
Community
1
Ghaser commited on
Commit
082ce14
·
verified ·
1 Parent(s): b4e663c

Add files using upload-large-folder tool

Browse files
Files changed (27) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +66 -0
  3. audio_module.bin +3 -0
  4. chat_template.json +3 -0
  5. config.json +199 -0
  6. generation_config.json +6 -0
  7. image_generator.bin +3 -0
  8. mlp_gates.bin +3 -0
  9. model-00001-of-00011.safetensors +3 -0
  10. model-00002-of-00011.safetensors +3 -0
  11. model-00003-of-00011.safetensors +3 -0
  12. model-00004-of-00011.safetensors +3 -0
  13. model-00005-of-00011.safetensors +3 -0
  14. model-00006-of-00011.safetensors +3 -0
  15. model-00007-of-00011.safetensors +3 -0
  16. model-00008-of-00011.safetensors +3 -0
  17. model-00009-of-00011.safetensors +3 -0
  18. model-00010-of-00011.safetensors +3 -0
  19. model-00011-of-00011.safetensors +3 -0
  20. model.safetensors.index.json +0 -0
  21. preprocessor_config.json +25 -0
  22. special_tokens_map.json +38 -0
  23. tokenizer.json +3 -0
  24. tokenizer_config.json +551 -0
  25. training_args.bin +3 -0
  26. vision_aligner.bin +3 -0
  27. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|audio_end|>": 151666,
5
+ "<|audio_pad|>": 151667,
6
+ "<|audio_start|>": 151665,
7
+ "<|box_end|>": 151649,
8
+ "<|box_start|>": 151648,
9
+ "<|endoftext|>": 151643,
10
+ "<|file_sep|>": 151664,
11
+ "<|fim_middle|>": 151660,
12
+ "<|fim_pad|>": 151662,
13
+ "<|fim_prefix|>": 151659,
14
+ "<|fim_suffix|>": 151661,
15
+ "<|im_end|>": 151645,
16
+ "<|im_start|>": 151644,
17
+ "<|image_pad|>": 151655,
18
+ "<|object_ref_end|>": 151647,
19
+ "<|object_ref_start|>": 151646,
20
+ "<|quad_end|>": 151651,
21
+ "<|quad_start|>": 151650,
22
+ "<|repo_name|>": 151663,
23
+ "<|speech_end|>": 151669,
24
+ "<|speech_prompt|>": 151670,
25
+ "<|speech_split|>": 151671,
26
+ "<|speech_start|>": 151668,
27
+ "<|video_pad|>": 151656,
28
+ "<|vision_end|>": 151653,
29
+ "<|vision_pad|>": 151654,
30
+ "<|vision_start|>": 151652,
31
+ "[IMG0]": 151672,
32
+ "[IMG10]": 151682,
33
+ "[IMG11]": 151683,
34
+ "[IMG12]": 151684,
35
+ "[IMG13]": 151685,
36
+ "[IMG14]": 151686,
37
+ "[IMG15]": 151687,
38
+ "[IMG16]": 151688,
39
+ "[IMG17]": 151689,
40
+ "[IMG18]": 151690,
41
+ "[IMG19]": 151691,
42
+ "[IMG1]": 151673,
43
+ "[IMG20]": 151692,
44
+ "[IMG21]": 151693,
45
+ "[IMG22]": 151694,
46
+ "[IMG23]": 151695,
47
+ "[IMG24]": 151696,
48
+ "[IMG25]": 151697,
49
+ "[IMG26]": 151698,
50
+ "[IMG27]": 151699,
51
+ "[IMG28]": 151700,
52
+ "[IMG29]": 151701,
53
+ "[IMG2]": 151674,
54
+ "[IMG30]": 151702,
55
+ "[IMG31]": 151703,
56
+ "[IMG3]": 151675,
57
+ "[IMG4]": 151676,
58
+ "[IMG5]": 151677,
59
+ "[IMG6]": 151678,
60
+ "[IMG7]": 151679,
61
+ "[IMG8]": 151680,
62
+ "[IMG9]": 151681,
63
+ "[TASK0]": 151704,
64
+ "[TASK1]": 151705,
65
+ "[TASK2]": 151706
66
+ }
audio_module.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b27a4b8bad6eb9ff2dd7a035e58f668de719d5823febd40c50a695b39076bf62
3
+ size 3097110166
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GrinQwen2VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "audio_end_token_id": 151666,
7
+ "audio_start_token_id": 151665,
8
+ "audio_token_id": 151667,
9
+ "avg_hidden_states_last": false,
10
+ "bos_token_id": 151643,
11
+ "capacity_factor": 3.0,
12
+ "drop_policy": "probs",
13
+ "drop_token_num_print": true,
14
+ "dynamic_intermediate_size": 18944,
15
+ "enable_expert_tensor_parallelism": false,
16
+ "eos_token_id": 151645,
17
+ "ep_size": 1,
18
+ "fixed_ep_size": 1,
19
+ "fp32_gate": true,
20
+ "hidden_act": "silu",
21
+ "hidden_size": 3584,
22
+ "ignore_differentiable_router": false,
23
+ "image_grid_pinpoints": [
24
+ [
25
+ 384,
26
+ 384
27
+ ],
28
+ [
29
+ 384,
30
+ 768
31
+ ],
32
+ [
33
+ 384,
34
+ 1152
35
+ ],
36
+ [
37
+ 384,
38
+ 1536
39
+ ],
40
+ [
41
+ 768,
42
+ 384
43
+ ],
44
+ [
45
+ 768,
46
+ 768
47
+ ],
48
+ [
49
+ 768,
50
+ 1152
51
+ ],
52
+ [
53
+ 768,
54
+ 1536
55
+ ],
56
+ [
57
+ 1152,
58
+ 384
59
+ ],
60
+ [
61
+ 1152,
62
+ 768
63
+ ],
64
+ [
65
+ 1152,
66
+ 1152
67
+ ],
68
+ [
69
+ 1152,
70
+ 1536
71
+ ],
72
+ [
73
+ 1536,
74
+ 384
75
+ ],
76
+ [
77
+ 1536,
78
+ 768
79
+ ],
80
+ [
81
+ 1536,
82
+ 1152
83
+ ],
84
+ [
85
+ 1536,
86
+ 1536
87
+ ]
88
+ ],
89
+ "image_token_id": 151655,
90
+ "initializer_range": 0.02,
91
+ "input_jitter_noise": 0.01,
92
+ "intermediate_size": 18944,
93
+ "l_aux_weight": 0.025,
94
+ "l_aux_weight_decay_steps": 100000,
95
+ "layer_types": [
96
+ "sliding_attention",
97
+ "sliding_attention",
98
+ "sliding_attention",
99
+ "sliding_attention",
100
+ "sliding_attention",
101
+ "sliding_attention",
102
+ "sliding_attention",
103
+ "sliding_attention",
104
+ "sliding_attention",
105
+ "sliding_attention",
106
+ "sliding_attention",
107
+ "sliding_attention",
108
+ "sliding_attention",
109
+ "sliding_attention",
110
+ "sliding_attention",
111
+ "sliding_attention",
112
+ "sliding_attention",
113
+ "sliding_attention",
114
+ "sliding_attention",
115
+ "sliding_attention",
116
+ "sliding_attention",
117
+ "sliding_attention",
118
+ "sliding_attention",
119
+ "sliding_attention",
120
+ "sliding_attention",
121
+ "sliding_attention",
122
+ "sliding_attention",
123
+ "sliding_attention"
124
+ ],
125
+ "max_position_embeddings": 128000,
126
+ "max_window_layers": 28,
127
+ "min_capacity": 6,
128
+ "min_l_aux_weight": 0.025,
129
+ "mlp_dynamic_expert_num": 4,
130
+ "mlp_dynamic_null_expert_num": 1,
131
+ "mlp_dynamic_top_k": 2,
132
+ "mlp_dynamic_top_p": 0.7,
133
+ "mlp_fixed_expert_num": 2,
134
+ "mm_hidden_size": 1152,
135
+ "model_type": "grin_qwen2_vl",
136
+ "num_attention_heads": 28,
137
+ "num_hidden_layers": 28,
138
+ "num_key_value_heads": 4,
139
+ "rms_norm_eps": 1e-06,
140
+ "rope_scaling": {
141
+ "mrope_section": [
142
+ 16,
143
+ 24,
144
+ 24
145
+ ],
146
+ "rope_type": "default",
147
+ "type": "default"
148
+ },
149
+ "rope_theta": 1000000.0,
150
+ "router_jitter_noise": 0.01,
151
+ "shared_intermediate_size": 2368,
152
+ "sliding_window": 32768,
153
+ "speech_end_token_id": 151669,
154
+ "speech_prompt_token_id": 151670,
155
+ "speech_split_token_id": 151671,
156
+ "speech_start_token_id": 151668,
157
+ "tie_word_embeddings": false,
158
+ "token_drop": false,
159
+ "torch_dtype": "bfloat16",
160
+ "transformers_version": "4.45.1",
161
+ "tune_image_generator": false,
162
+ "tune_speech_generator": false,
163
+ "tune_speech_generator_only": false,
164
+ "use_cache": true,
165
+ "use_sliding_window": false,
166
+ "video_token_id": 151656,
167
+ "vision_config": {
168
+ "fullatt_block_indexes": [
169
+ 7,
170
+ 15,
171
+ 23,
172
+ 31
173
+ ],
174
+ "hidden_act": "silu",
175
+ "hidden_size": 1280,
176
+ "in_chans": 3,
177
+ "intermediate_size": 3420,
178
+ "model_type": "qwen2_vl",
179
+ "out_hidden_size": 3584,
180
+ "spatial_patch_size": 14,
181
+ "tokens_per_second": 2,
182
+ "window_size": 112
183
+ },
184
+ "vision_end_token_id": 151653,
185
+ "vision_hidden_size": 1152,
186
+ "vision_spatial_pool_stride": 12,
187
+ "vision_start_token_id": 151652,
188
+ "vision_token_id": 151654,
189
+ "vision_tower": "google/siglip-so400m-patch14-384",
190
+ "vision_tower_pretrained": null,
191
+ "vision_vision_select_layer": -2,
192
+ "vision_vision_tower": "google/siglip-so400m-patch14-384",
193
+ "visual_aligner_type": "linear",
194
+ "vocab_size": 152064,
195
+ "whisper_hidden_size": 1280,
196
+ "whisper_projector_type": "linear",
197
+ "whisper_query_tokens_size": 200,
198
+ "whisper_tower": "openai/whisper_large_v3"
199
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.45.1"
6
+ }
image_generator.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00979033725603fbe0392c5b9bdbca5c3e9d450ea707d5c99118c7138828498b
3
+ size 896
mlp_gates.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf98269e62df7fe8723ca4c79d72b93181391663fdbeca40ad764498ceae1115
3
+ size 1413890
model-00001-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef222315dcf60e0a62e6abf481a4b85eb26f8d2362a5da295f31b674f09d3381
3
+ size 5303177400
model-00002-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cd99208c5e95d11bd28a796e4523d9e4dc99ddaddc49d5b482230b318f92f06
3
+ size 5295839928
model-00003-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cb2c448d39cfa319e7fa07ea71a4dfa297b55a260cb415fd5483324e271b6e1
3
+ size 5295839928
model-00004-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86379f5471ba239d05f0dea4c334d2a01a5784b4e786ed1e320d6f0308ebdb53
3
+ size 5295839920
model-00005-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b9c9a85a307d5c37603d4ae1b778c737e621458932739ca9a396d58afbb4d7d
3
+ size 5295839936
model-00006-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe981dc7965ad3165b4d8f5154cc997914ffa3fded2eeb0de95056e971943351
3
+ size 5295839928
model-00007-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a40ff13aedd5ee64e3fbf49ed61ae924836ef54396e3987a12ad393aa0918d3a
3
+ size 5295839928
model-00008-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99e42e4e66070371e92ba20d075133d2bff36f05e4bc15f77891c33e6fd4f597
3
+ size 5295839920
model-00009-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef6356e130aff6dc55d8471bce958b09dcb8b9cb5cbf6f0bfe333d2b3505d1dd
3
+ size 5295839928
model-00010-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02fc9fea279e8eec4faa43799d21580d15df2d037bdfc43e01c19dc660670fbc
3
+ size 5357867352
model-00011-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a9f2fb627818ee9a61b15ccb6c7bcf796fdbc5720cb65540a84f7581262e407
3
+ size 3202188376
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 384,
4
+ "width": 384
5
+ },
6
+ "data_format": "channels_first",
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "SigLipImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "processor_class": "Qwen2VLProcessor",
19
+ "resample": 3,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": [
22
+ 384,
23
+ 384
24
+ ]
25
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>",
16
+ "<|audio_start|>",
17
+ "<|audio_end|>",
18
+ "<|audio_pad|>",
19
+ "<|speech_start|>",
20
+ "<|speech_end|>",
21
+ "<|speech_prompt|>",
22
+ "<|speech_split|>"
23
+ ],
24
+ "eos_token": {
25
+ "content": "<|im_end|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "pad_token": {
32
+ "content": "<|endoftext|>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ }
38
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:527d446ac3ab7ef41e79df7448810f627715a6a74d62ced4c983390a63757923
3
+ size 11429669
tokenizer_config.json ADDED
@@ -0,0 +1,551 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "151657": {
117
+ "content": "<tool_call>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "151658": {
125
+ "content": "</tool_call>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "151659": {
133
+ "content": "<|fim_prefix|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "151660": {
141
+ "content": "<|fim_middle|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "151661": {
149
+ "content": "<|fim_suffix|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "151662": {
157
+ "content": "<|fim_pad|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "151663": {
165
+ "content": "<|repo_name|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "151664": {
173
+ "content": "<|file_sep|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "151665": {
181
+ "content": "<|audio_start|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "151666": {
189
+ "content": "<|audio_end|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "151667": {
197
+ "content": "<|audio_pad|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "151668": {
205
+ "content": "<|speech_start|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "151669": {
213
+ "content": "<|speech_end|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "151670": {
221
+ "content": "<|speech_prompt|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "151671": {
229
+ "content": "<|speech_split|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "151672": {
237
+ "content": "[IMG0]",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "151673": {
245
+ "content": "[IMG1]",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "151674": {
253
+ "content": "[IMG2]",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "151675": {
261
+ "content": "[IMG3]",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "151676": {
269
+ "content": "[IMG4]",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "151677": {
277
+ "content": "[IMG5]",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "151678": {
285
+ "content": "[IMG6]",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "151679": {
293
+ "content": "[IMG7]",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "151680": {
301
+ "content": "[IMG8]",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "151681": {
309
+ "content": "[IMG9]",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ },
316
+ "151682": {
317
+ "content": "[IMG10]",
318
+ "lstrip": false,
319
+ "normalized": true,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": false
323
+ },
324
+ "151683": {
325
+ "content": "[IMG11]",
326
+ "lstrip": false,
327
+ "normalized": true,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": false
331
+ },
332
+ "151684": {
333
+ "content": "[IMG12]",
334
+ "lstrip": false,
335
+ "normalized": true,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": false
339
+ },
340
+ "151685": {
341
+ "content": "[IMG13]",
342
+ "lstrip": false,
343
+ "normalized": true,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": false
347
+ },
348
+ "151686": {
349
+ "content": "[IMG14]",
350
+ "lstrip": false,
351
+ "normalized": true,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": false
355
+ },
356
+ "151687": {
357
+ "content": "[IMG15]",
358
+ "lstrip": false,
359
+ "normalized": true,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": false
363
+ },
364
+ "151688": {
365
+ "content": "[IMG16]",
366
+ "lstrip": false,
367
+ "normalized": true,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": false
371
+ },
372
+ "151689": {
373
+ "content": "[IMG17]",
374
+ "lstrip": false,
375
+ "normalized": true,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": false
379
+ },
380
+ "151690": {
381
+ "content": "[IMG18]",
382
+ "lstrip": false,
383
+ "normalized": true,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": false
387
+ },
388
+ "151691": {
389
+ "content": "[IMG19]",
390
+ "lstrip": false,
391
+ "normalized": true,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": false
395
+ },
396
+ "151692": {
397
+ "content": "[IMG20]",
398
+ "lstrip": false,
399
+ "normalized": true,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": false
403
+ },
404
+ "151693": {
405
+ "content": "[IMG21]",
406
+ "lstrip": false,
407
+ "normalized": true,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": false
411
+ },
412
+ "151694": {
413
+ "content": "[IMG22]",
414
+ "lstrip": false,
415
+ "normalized": true,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": false
419
+ },
420
+ "151695": {
421
+ "content": "[IMG23]",
422
+ "lstrip": false,
423
+ "normalized": true,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": false
427
+ },
428
+ "151696": {
429
+ "content": "[IMG24]",
430
+ "lstrip": false,
431
+ "normalized": true,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": false
435
+ },
436
+ "151697": {
437
+ "content": "[IMG25]",
438
+ "lstrip": false,
439
+ "normalized": true,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": false
443
+ },
444
+ "151698": {
445
+ "content": "[IMG26]",
446
+ "lstrip": false,
447
+ "normalized": true,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": false
451
+ },
452
+ "151699": {
453
+ "content": "[IMG27]",
454
+ "lstrip": false,
455
+ "normalized": true,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": false
459
+ },
460
+ "151700": {
461
+ "content": "[IMG28]",
462
+ "lstrip": false,
463
+ "normalized": true,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": false
467
+ },
468
+ "151701": {
469
+ "content": "[IMG29]",
470
+ "lstrip": false,
471
+ "normalized": true,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": false
475
+ },
476
+ "151702": {
477
+ "content": "[IMG30]",
478
+ "lstrip": false,
479
+ "normalized": true,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": false
483
+ },
484
+ "151703": {
485
+ "content": "[IMG31]",
486
+ "lstrip": false,
487
+ "normalized": true,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": false
491
+ },
492
+ "151704": {
493
+ "content": "[TASK0]",
494
+ "lstrip": false,
495
+ "normalized": true,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": false
499
+ },
500
+ "151705": {
501
+ "content": "[TASK1]",
502
+ "lstrip": false,
503
+ "normalized": true,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": false
507
+ },
508
+ "151706": {
509
+ "content": "[TASK2]",
510
+ "lstrip": false,
511
+ "normalized": true,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": false
515
+ }
516
+ },
517
+ "additional_special_tokens": [
518
+ "<|im_start|>",
519
+ "<|im_end|>",
520
+ "<|object_ref_start|>",
521
+ "<|object_ref_end|>",
522
+ "<|box_start|>",
523
+ "<|box_end|>",
524
+ "<|quad_start|>",
525
+ "<|quad_end|>",
526
+ "<|vision_start|>",
527
+ "<|vision_end|>",
528
+ "<|vision_pad|>",
529
+ "<|image_pad|>",
530
+ "<|video_pad|>",
531
+ "<|audio_start|>",
532
+ "<|audio_end|>",
533
+ "<|audio_pad|>",
534
+ "<|speech_start|>",
535
+ "<|speech_end|>",
536
+ "<|speech_prompt|>",
537
+ "<|speech_split|>"
538
+ ],
539
+ "bos_token": null,
540
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
541
+ "clean_up_tokenization_spaces": false,
542
+ "eos_token": "<|im_end|>",
543
+ "errors": "replace",
544
+ "model_max_length": 15000,
545
+ "pad_token": "<|endoftext|>",
546
+ "padding_side": "left",
547
+ "processor_class": "Qwen2VLProcessor",
548
+ "split_special_tokens": false,
549
+ "tokenizer_class": "Qwen2Tokenizer",
550
+ "unk_token": null
551
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59bbbac1f4fe514bb8b0df594372275a9f7fb412ec849808b04c895840986a47
3
+ size 8056
vision_aligner.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:705d706e5ab5e15f633498c7e972213ef12155bfc619c6faa1de340e6be37231
3
+ size 33964104
vocab.json ADDED
The diff for this file is too large to render. See raw diff