Hugging Face's logo

nm-testing
/
Qwen2-VL-72B-Instruct-FP8-dynamic

Safetensors
qwen2_vl
compressed-tensors
Model card Files Community
mgoin commited on
Commit
269a11e
·
verified ·
1 Parent(s): 0b209bf

Upload folder using huggingface_hub

Browse files
Files changed (29) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +16 -0
  3. chat_template.json +3 -0
  4. config.json +220 -0
  5. generation_config.json +13 -0
  6. merges.txt +0 -0
  7. model-00001-of-00016.safetensors +3 -0
  8. model-00002-of-00016.safetensors +3 -0
  9. model-00003-of-00016.safetensors +3 -0
  10. model-00004-of-00016.safetensors +3 -0
  11. model-00005-of-00016.safetensors +3 -0
  12. model-00006-of-00016.safetensors +3 -0
  13. model-00007-of-00016.safetensors +3 -0
  14. model-00008-of-00016.safetensors +3 -0
  15. model-00009-of-00016.safetensors +3 -0
  16. model-00010-of-00016.safetensors +3 -0
  17. model-00011-of-00016.safetensors +3 -0
  18. model-00012-of-00016.safetensors +3 -0
  19. model-00013-of-00016.safetensors +3 -0
  20. model-00014-of-00016.safetensors +3 -0
  21. model-00015-of-00016.safetensors +3 -0
  22. model-00016-of-00016.safetensors +3 -0
  23. model.safetensors.index.json +0 -0
  24. preprocessor_config.json +29 -0
  25. recipe.yaml +6 -0
  26. special_tokens_map.json +31 -0
  27. tokenizer.json +3 -0
  28. tokenizer_config.json +144 -0
  29. 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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": 151649,
3
+ "<|box_start|>": 151648,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644,
7
+ "<|image_pad|>": 151655,
8
+ "<|object_ref_end|>": 151647,
9
+ "<|object_ref_start|>": 151646,
10
+ "<|quad_end|>": 151651,
11
+ "<|quad_start|>": 151650,
12
+ "<|video_pad|>": 151656,
13
+ "<|vision_end|>": 151653,
14
+ "<|vision_pad|>": 151654,
15
+ "<|vision_start|>": 151652
16
+ }
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 %}<|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 %}"
3
+ }
config.json ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/mgoin/.cache/huggingface/hub/models--Qwen--Qwen2-VL-72B-Instruct/snapshots/f400120e59a6196b024298b7d09fb517f742db7d",
3
+ "architectures": [
4
+ "Qwen2VLForConditionalGeneration"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8192,
11
+ "image_token_id": 151655,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 29568,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 80,
16
+ "model_type": "qwen2_vl",
17
+ "num_attention_heads": 64,
18
+ "num_hidden_layers": 80,
19
+ "num_key_value_heads": 8,
20
+ "quantization_config": {
21
+ "config_groups": {
22
+ "group_0": {
23
+ "input_activations": {
24
+ "actorder": null,
25
+ "block_structure": null,
26
+ "dynamic": true,
27
+ "group_size": null,
28
+ "num_bits": 8,
29
+ "observer": null,
30
+ "observer_kwargs": {},
31
+ "strategy": "token",
32
+ "symmetric": true,
33
+ "type": "float"
34
+ },
35
+ "output_activations": null,
36
+ "targets": [
37
+ "Linear"
38
+ ],
39
+ "weights": {
40
+ "actorder": null,
41
+ "block_structure": null,
42
+ "dynamic": false,
43
+ "group_size": null,
44
+ "num_bits": 8,
45
+ "observer": "minmax",
46
+ "observer_kwargs": {},
47
+ "strategy": "channel",
48
+ "symmetric": true,
49
+ "type": "float"
50
+ }
51
+ }
52
+ },
53
+ "format": "float-quantized",
54
+ "global_compression_ratio": 1.3357104612400095,
55
+ "ignore": [
56
+ "visual.blocks.0.attn.qkv",
57
+ "visual.blocks.0.attn.proj",
58
+ "visual.blocks.0.mlp.fc1",
59
+ "visual.blocks.0.mlp.fc2",
60
+ "visual.blocks.1.attn.qkv",
61
+ "visual.blocks.1.attn.proj",
62
+ "visual.blocks.1.mlp.fc1",
63
+ "visual.blocks.1.mlp.fc2",
64
+ "visual.blocks.2.attn.qkv",
65
+ "visual.blocks.2.attn.proj",
66
+ "visual.blocks.2.mlp.fc1",
67
+ "visual.blocks.2.mlp.fc2",
68
+ "visual.blocks.3.attn.qkv",
69
+ "visual.blocks.3.attn.proj",
70
+ "visual.blocks.3.mlp.fc1",
71
+ "visual.blocks.3.mlp.fc2",
72
+ "visual.blocks.4.attn.qkv",
73
+ "visual.blocks.4.attn.proj",
74
+ "visual.blocks.4.mlp.fc1",
75
+ "visual.blocks.4.mlp.fc2",
76
+ "visual.blocks.5.attn.qkv",
77
+ "visual.blocks.5.attn.proj",
78
+ "visual.blocks.5.mlp.fc1",
79
+ "visual.blocks.5.mlp.fc2",
80
+ "visual.blocks.6.attn.qkv",
81
+ "visual.blocks.6.attn.proj",
82
+ "visual.blocks.6.mlp.fc1",
83
+ "visual.blocks.6.mlp.fc2",
84
+ "visual.blocks.7.attn.qkv",
85
+ "visual.blocks.7.attn.proj",
86
+ "visual.blocks.7.mlp.fc1",
87
+ "visual.blocks.7.mlp.fc2",
88
+ "visual.blocks.8.attn.qkv",
89
+ "visual.blocks.8.attn.proj",
90
+ "visual.blocks.8.mlp.fc1",
91
+ "visual.blocks.8.mlp.fc2",
92
+ "visual.blocks.9.attn.qkv",
93
+ "visual.blocks.9.attn.proj",
94
+ "visual.blocks.9.mlp.fc1",
95
+ "visual.blocks.9.mlp.fc2",
96
+ "visual.blocks.10.attn.qkv",
97
+ "visual.blocks.10.attn.proj",
98
+ "visual.blocks.10.mlp.fc1",
99
+ "visual.blocks.10.mlp.fc2",
100
+ "visual.blocks.11.attn.qkv",
101
+ "visual.blocks.11.attn.proj",
102
+ "visual.blocks.11.mlp.fc1",
103
+ "visual.blocks.11.mlp.fc2",
104
+ "visual.blocks.12.attn.qkv",
105
+ "visual.blocks.12.attn.proj",
106
+ "visual.blocks.12.mlp.fc1",
107
+ "visual.blocks.12.mlp.fc2",
108
+ "visual.blocks.13.attn.qkv",
109
+ "visual.blocks.13.attn.proj",
110
+ "visual.blocks.13.mlp.fc1",
111
+ "visual.blocks.13.mlp.fc2",
112
+ "visual.blocks.14.attn.qkv",
113
+ "visual.blocks.14.attn.proj",
114
+ "visual.blocks.14.mlp.fc1",
115
+ "visual.blocks.14.mlp.fc2",
116
+ "visual.blocks.15.attn.qkv",
117
+ "visual.blocks.15.attn.proj",
118
+ "visual.blocks.15.mlp.fc1",
119
+ "visual.blocks.15.mlp.fc2",
120
+ "visual.blocks.16.attn.qkv",
121
+ "visual.blocks.16.attn.proj",
122
+ "visual.blocks.16.mlp.fc1",
123
+ "visual.blocks.16.mlp.fc2",
124
+ "visual.blocks.17.attn.qkv",
125
+ "visual.blocks.17.attn.proj",
126
+ "visual.blocks.17.mlp.fc1",
127
+ "visual.blocks.17.mlp.fc2",
128
+ "visual.blocks.18.attn.qkv",
129
+ "visual.blocks.18.attn.proj",
130
+ "visual.blocks.18.mlp.fc1",
131
+ "visual.blocks.18.mlp.fc2",
132
+ "visual.blocks.19.attn.qkv",
133
+ "visual.blocks.19.attn.proj",
134
+ "visual.blocks.19.mlp.fc1",
135
+ "visual.blocks.19.mlp.fc2",
136
+ "visual.blocks.20.attn.qkv",
137
+ "visual.blocks.20.attn.proj",
138
+ "visual.blocks.20.mlp.fc1",
139
+ "visual.blocks.20.mlp.fc2",
140
+ "visual.blocks.21.attn.qkv",
141
+ "visual.blocks.21.attn.proj",
142
+ "visual.blocks.21.mlp.fc1",
143
+ "visual.blocks.21.mlp.fc2",
144
+ "visual.blocks.22.attn.qkv",
145
+ "visual.blocks.22.attn.proj",
146
+ "visual.blocks.22.mlp.fc1",
147
+ "visual.blocks.22.mlp.fc2",
148
+ "visual.blocks.23.attn.qkv",
149
+ "visual.blocks.23.attn.proj",
150
+ "visual.blocks.23.mlp.fc1",
151
+ "visual.blocks.23.mlp.fc2",
152
+ "visual.blocks.24.attn.qkv",
153
+ "visual.blocks.24.attn.proj",
154
+ "visual.blocks.24.mlp.fc1",
155
+ "visual.blocks.24.mlp.fc2",
156
+ "visual.blocks.25.attn.qkv",
157
+ "visual.blocks.25.attn.proj",
158
+ "visual.blocks.25.mlp.fc1",
159
+ "visual.blocks.25.mlp.fc2",
160
+ "visual.blocks.26.attn.qkv",
161
+ "visual.blocks.26.attn.proj",
162
+ "visual.blocks.26.mlp.fc1",
163
+ "visual.blocks.26.mlp.fc2",
164
+ "visual.blocks.27.attn.qkv",
165
+ "visual.blocks.27.attn.proj",
166
+ "visual.blocks.27.mlp.fc1",
167
+ "visual.blocks.27.mlp.fc2",
168
+ "visual.blocks.28.attn.qkv",
169
+ "visual.blocks.28.attn.proj",
170
+ "visual.blocks.28.mlp.fc1",
171
+ "visual.blocks.28.mlp.fc2",
172
+ "visual.blocks.29.attn.qkv",
173
+ "visual.blocks.29.attn.proj",
174
+ "visual.blocks.29.mlp.fc1",
175
+ "visual.blocks.29.mlp.fc2",
176
+ "visual.blocks.30.attn.qkv",
177
+ "visual.blocks.30.attn.proj",
178
+ "visual.blocks.30.mlp.fc1",
179
+ "visual.blocks.30.mlp.fc2",
180
+ "visual.blocks.31.attn.qkv",
181
+ "visual.blocks.31.attn.proj",
182
+ "visual.blocks.31.mlp.fc1",
183
+ "visual.blocks.31.mlp.fc2",
184
+ "visual.merger.mlp.0",
185
+ "visual.merger.mlp.2",
186
+ "lm_head"
187
+ ],
188
+ "kv_cache_scheme": null,
189
+ "quant_method": "compressed-tensors",
190
+ "quantization_status": "compressed"
191
+ },
192
+ "rms_norm_eps": 1e-06,
193
+ "rope_scaling": {
194
+ "mrope_section": [
195
+ 16,
196
+ 24,
197
+ 24
198
+ ],
199
+ "rope_type": "default",
200
+ "type": "default"
201
+ },
202
+ "rope_theta": 1000000.0,
203
+ "sliding_window": 32768,
204
+ "tie_word_embeddings": false,
205
+ "torch_dtype": "bfloat16",
206
+ "transformers_version": "4.45.2",
207
+ "use_cache": true,
208
+ "use_sliding_window": false,
209
+ "video_token_id": 151656,
210
+ "vision_config": {
211
+ "hidden_size": 8192,
212
+ "in_chans": 3,
213
+ "model_type": "qwen2_vl",
214
+ "spatial_patch_size": 14
215
+ },
216
+ "vision_end_token_id": 151653,
217
+ "vision_start_token_id": 151652,
218
+ "vision_token_id": 151654,
219
+ "vocab_size": 152064
220
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "top_k": 1,
11
+ "top_p": 0.001,
12
+ "transformers_version": "4.45.2"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:385916bf0333c58f6c4533a686e12dced5956dc90d8041faa5cde98e60a0ea43
3
+ size 4919109848
model-00002-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f77db524ff470e7cffe7782db971535f97dcdba7decddb4cc22e4f3dae6ab7b
3
+ size 4873985928
model-00003-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d4ba499ae5a52112b7e8b889257cc55d90241382a0024fdd20e3d16d9c937c1
3
+ size 4782749304
model-00004-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65f1729972cc7f93a5bc40f8d57d36b7263f77710862e624a1c7626728338560
3
+ size 4873986032
model-00005-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1939c5f0d901610858ac0e0fd2b65ab973467b3dac07f2a764d5975b41dfec7
3
+ size 4782749368
model-00006-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c34c3d98977ea4f8198e76bab26f02030a245a84c9aefef77bf4fcc40dd4af96
3
+ size 4873986032
model-00007-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:502bd1c1a414cf204c491b13051f12c9b33502fcc9e20ccbbc601548c4f43aa7
3
+ size 4782749368
model-00008-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8b0ff304c4619e6509cfd44d59c792fbeffd96361a21bda4541013b35c7058a
3
+ size 4873986032
model-00009-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b3053a7f62b9c63b5a23c84486ae2bf919f3133988ac36c84d2b4ccc361cb8c
3
+ size 4782749368
model-00010-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b4333e4152e4975bdc77723c7e64f925a8019f8497d1cc6a07670d7eb2ae55e
3
+ size 4873986032
model-00011-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97d1c6008d5ffa2db781f096c670a22b816a957d78a0c6a7ef6ade0a6feb689f
3
+ size 4782749368
model-00012-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39dd9ac5dded4e416c3fef69bbe6a79cc9cf583a621e2def46cb124c0e2800e8
3
+ size 4873986032
model-00013-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aa768b0113b5beea15d2a7688a3d7500294208f0e3785aeaeaa9a210e06d644
3
+ size 4782749368
model-00014-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22b176272f7fafc08d8bf52de3e77b2c2316af5b7d321d054798e13302d52334
3
+ size 4873986032
model-00015-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d899e0f2f09b9e85463926ea89ebd9c5bce1743478a63c6a84ea85629e39dcdc
3
+ size 4782749368
model-00016-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5d80a23caa0ba27320fbdea9a0bec600689d8f8dd9c2f059b710f36565cc810
3
+ size 4096149840
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "max_pixels": 12845056,
26
+ "min_pixels": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
recipe.yaml ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ DEFAULT_stage:
2
+ DEFAULT_modifiers:
3
+ QuantizationModifier:
4
+ ignore: ['re:.*lm_head', 're:visual.*']
5
+ targets: Linear
6
+ scheme: FP8_DYNAMIC
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
3
+ size 11420371
tokenizer_config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
117
+ "additional_special_tokens": [
118
+ "<|im_start|>",
119
+ "<|im_end|>",
120
+ "<|object_ref_start|>",
121
+ "<|object_ref_end|>",
122
+ "<|box_start|>",
123
+ "<|box_end|>",
124
+ "<|quad_start|>",
125
+ "<|quad_end|>",
126
+ "<|vision_start|>",
127
+ "<|vision_end|>",
128
+ "<|vision_pad|>",
129
+ "<|image_pad|>",
130
+ "<|video_pad|>"
131
+ ],
132
+ "bos_token": null,
133
+ "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 %}",
134
+ "clean_up_tokenization_spaces": false,
135
+ "eos_token": "<|im_end|>",
136
+ "errors": "replace",
137
+ "model_max_length": 32768,
138
+ "pad_token": "<|endoftext|>",
139
+ "padding_side": "left",
140
+ "processor_class": "Qwen2VLProcessor",
141
+ "split_special_tokens": false,
142
+ "tokenizer_class": "Qwen2Tokenizer",
143
+ "unk_token": null
144
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff