Hugging Face's logo

ig1
/
Qwen2.5-VL-72B-Instruct-FP8-Dynamic

Image-Text-to-Text
Transformers
Safetensors
English
qwen2_5_vl
multimodal
conversational
Inference Endpoints
compressed-tensors
Model card Files Community
ig1sa commited on
Commit
7028740
·
verified ·
1 Parent(s): f5d2a96

Upload folder using huggingface_hub

Browse files
Files changed (29) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +24 -0
  3. chat_template.json +3 -0
  4. config.json +255 -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 +208 -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 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
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 +1,255 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen2.5-VL-72B",
3
+ "architectures": [
4
+ "Qwen2_5_VLForConditionalGeneration"
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": 128000,
15
+ "max_window_layers": 80,
16
+ "model_type": "qwen2_5_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": 1.323305644571225,
55
+ "ignore": [
56
+ "visual.blocks.0.attn.qkv",
57
+ "visual.blocks.0.attn.proj",
58
+ "visual.blocks.0.mlp.gate_proj",
59
+ "visual.blocks.0.mlp.up_proj",
60
+ "visual.blocks.0.mlp.down_proj",
61
+ "visual.blocks.1.attn.qkv",
62
+ "visual.blocks.1.attn.proj",
63
+ "visual.blocks.1.mlp.gate_proj",
64
+ "visual.blocks.1.mlp.up_proj",
65
+ "visual.blocks.1.mlp.down_proj",
66
+ "visual.blocks.2.attn.qkv",
67
+ "visual.blocks.2.attn.proj",
68
+ "visual.blocks.2.mlp.gate_proj",
69
+ "visual.blocks.2.mlp.up_proj",
70
+ "visual.blocks.2.mlp.down_proj",
71
+ "visual.blocks.3.attn.qkv",
72
+ "visual.blocks.3.attn.proj",
73
+ "visual.blocks.3.mlp.gate_proj",
74
+ "visual.blocks.3.mlp.up_proj",
75
+ "visual.blocks.3.mlp.down_proj",
76
+ "visual.blocks.4.attn.qkv",
77
+ "visual.blocks.4.attn.proj",
78
+ "visual.blocks.4.mlp.gate_proj",
79
+ "visual.blocks.4.mlp.up_proj",
80
+ "visual.blocks.4.mlp.down_proj",
81
+ "visual.blocks.5.attn.qkv",
82
+ "visual.blocks.5.attn.proj",
83
+ "visual.blocks.5.mlp.gate_proj",
84
+ "visual.blocks.5.mlp.up_proj",
85
+ "visual.blocks.5.mlp.down_proj",
86
+ "visual.blocks.6.attn.qkv",
87
+ "visual.blocks.6.attn.proj",
88
+ "visual.blocks.6.mlp.gate_proj",
89
+ "visual.blocks.6.mlp.up_proj",
90
+ "visual.blocks.6.mlp.down_proj",
91
+ "visual.blocks.7.attn.qkv",
92
+ "visual.blocks.7.attn.proj",
93
+ "visual.blocks.7.mlp.gate_proj",
94
+ "visual.blocks.7.mlp.up_proj",
95
+ "visual.blocks.7.mlp.down_proj",
96
+ "visual.blocks.8.attn.qkv",
97
+ "visual.blocks.8.attn.proj",
98
+ "visual.blocks.8.mlp.gate_proj",
99
+ "visual.blocks.8.mlp.up_proj",
100
+ "visual.blocks.8.mlp.down_proj",
101
+ "visual.blocks.9.attn.qkv",
102
+ "visual.blocks.9.attn.proj",
103
+ "visual.blocks.9.mlp.gate_proj",
104
+ "visual.blocks.9.mlp.up_proj",
105
+ "visual.blocks.9.mlp.down_proj",
106
+ "visual.blocks.10.attn.qkv",
107
+ "visual.blocks.10.attn.proj",
108
+ "visual.blocks.10.mlp.gate_proj",
109
+ "visual.blocks.10.mlp.up_proj",
110
+ "visual.blocks.10.mlp.down_proj",
111
+ "visual.blocks.11.attn.qkv",
112
+ "visual.blocks.11.attn.proj",
113
+ "visual.blocks.11.mlp.gate_proj",
114
+ "visual.blocks.11.mlp.up_proj",
115
+ "visual.blocks.11.mlp.down_proj",
116
+ "visual.blocks.12.attn.qkv",
117
+ "visual.blocks.12.attn.proj",
118
+ "visual.blocks.12.mlp.gate_proj",
119
+ "visual.blocks.12.mlp.up_proj",
120
+ "visual.blocks.12.mlp.down_proj",
121
+ "visual.blocks.13.attn.qkv",
122
+ "visual.blocks.13.attn.proj",
123
+ "visual.blocks.13.mlp.gate_proj",
124
+ "visual.blocks.13.mlp.up_proj",
125
+ "visual.blocks.13.mlp.down_proj",
126
+ "visual.blocks.14.attn.qkv",
127
+ "visual.blocks.14.attn.proj",
128
+ "visual.blocks.14.mlp.gate_proj",
129
+ "visual.blocks.14.mlp.up_proj",
130
+ "visual.blocks.14.mlp.down_proj",
131
+ "visual.blocks.15.attn.qkv",
132
+ "visual.blocks.15.attn.proj",
133
+ "visual.blocks.15.mlp.gate_proj",
134
+ "visual.blocks.15.mlp.up_proj",
135
+ "visual.blocks.15.mlp.down_proj",
136
+ "visual.blocks.16.attn.qkv",
137
+ "visual.blocks.16.attn.proj",
138
+ "visual.blocks.16.mlp.gate_proj",
139
+ "visual.blocks.16.mlp.up_proj",
140
+ "visual.blocks.16.mlp.down_proj",
141
+ "visual.blocks.17.attn.qkv",
142
+ "visual.blocks.17.attn.proj",
143
+ "visual.blocks.17.mlp.gate_proj",
144
+ "visual.blocks.17.mlp.up_proj",
145
+ "visual.blocks.17.mlp.down_proj",
146
+ "visual.blocks.18.attn.qkv",
147
+ "visual.blocks.18.attn.proj",
148
+ "visual.blocks.18.mlp.gate_proj",
149
+ "visual.blocks.18.mlp.up_proj",
150
+ "visual.blocks.18.mlp.down_proj",
151
+ "visual.blocks.19.attn.qkv",
152
+ "visual.blocks.19.attn.proj",
153
+ "visual.blocks.19.mlp.gate_proj",
154
+ "visual.blocks.19.mlp.up_proj",
155
+ "visual.blocks.19.mlp.down_proj",
156
+ "visual.blocks.20.attn.qkv",
157
+ "visual.blocks.20.attn.proj",
158
+ "visual.blocks.20.mlp.gate_proj",
159
+ "visual.blocks.20.mlp.up_proj",
160
+ "visual.blocks.20.mlp.down_proj",
161
+ "visual.blocks.21.attn.qkv",
162
+ "visual.blocks.21.attn.proj",
163
+ "visual.blocks.21.mlp.gate_proj",
164
+ "visual.blocks.21.mlp.up_proj",
165
+ "visual.blocks.21.mlp.down_proj",
166
+ "visual.blocks.22.attn.qkv",
167
+ "visual.blocks.22.attn.proj",
168
+ "visual.blocks.22.mlp.gate_proj",
169
+ "visual.blocks.22.mlp.up_proj",
170
+ "visual.blocks.22.mlp.down_proj",
171
+ "visual.blocks.23.attn.qkv",
172
+ "visual.blocks.23.attn.proj",
173
+ "visual.blocks.23.mlp.gate_proj",
174
+ "visual.blocks.23.mlp.up_proj",
175
+ "visual.blocks.23.mlp.down_proj",
176
+ "visual.blocks.24.attn.qkv",
177
+ "visual.blocks.24.attn.proj",
178
+ "visual.blocks.24.mlp.gate_proj",
179
+ "visual.blocks.24.mlp.up_proj",
180
+ "visual.blocks.24.mlp.down_proj",
181
+ "visual.blocks.25.attn.qkv",
182
+ "visual.blocks.25.attn.proj",
183
+ "visual.blocks.25.mlp.gate_proj",
184
+ "visual.blocks.25.mlp.up_proj",
185
+ "visual.blocks.25.mlp.down_proj",
186
+ "visual.blocks.26.attn.qkv",
187
+ "visual.blocks.26.attn.proj",
188
+ "visual.blocks.26.mlp.gate_proj",
189
+ "visual.blocks.26.mlp.up_proj",
190
+ "visual.blocks.26.mlp.down_proj",
191
+ "visual.blocks.27.attn.qkv",
192
+ "visual.blocks.27.attn.proj",
193
+ "visual.blocks.27.mlp.gate_proj",
194
+ "visual.blocks.27.mlp.up_proj",
195
+ "visual.blocks.27.mlp.down_proj",
196
+ "visual.blocks.28.attn.qkv",
197
+ "visual.blocks.28.attn.proj",
198
+ "visual.blocks.28.mlp.gate_proj",
199
+ "visual.blocks.28.mlp.up_proj",
200
+ "visual.blocks.28.mlp.down_proj",
201
+ "visual.blocks.29.attn.qkv",
202
+ "visual.blocks.29.attn.proj",
203
+ "visual.blocks.29.mlp.gate_proj",
204
+ "visual.blocks.29.mlp.up_proj",
205
+ "visual.blocks.29.mlp.down_proj",
206
+ "visual.blocks.30.attn.qkv",
207
+ "visual.blocks.30.attn.proj",
208
+ "visual.blocks.30.mlp.gate_proj",
209
+ "visual.blocks.30.mlp.up_proj",
210
+ "visual.blocks.30.mlp.down_proj",
211
+ "visual.blocks.31.attn.qkv",
212
+ "visual.blocks.31.attn.proj",
213
+ "visual.blocks.31.mlp.gate_proj",
214
+ "visual.blocks.31.mlp.up_proj",
215
+ "visual.blocks.31.mlp.down_proj",
216
+ "visual.merger.mlp.0",
217
+ "visual.merger.mlp.2",
218
+ "lm_head"
219
+ ],
220
+ "kv_cache_scheme": null,
221
+ "quant_method": "compressed-tensors",
222
+ "quantization_status": "compressed"
223
+ },
224
+ "rms_norm_eps": 1e-06,
225
+ "rope_scaling": {
226
+ "mrope_section": [
227
+ 16,
228
+ 24,
229
+ 24
230
+ ],
231
+ "rope_type": "default",
232
+ "type": "default"
233
+ },
234
+ "rope_theta": 1000000.0,
235
+ "sliding_window": 32768,
236
+ "tie_word_embeddings": false,
237
+ "torch_dtype": "bfloat16",
238
+ "transformers_version": "4.49.0.dev0",
239
+ "use_cache": true,
240
+ "use_sliding_window": false,
241
+ "video_token_id": 151656,
242
+ "vision_config": {
243
+ "hidden_size": 1280,
244
+ "in_chans": 3,
245
+ "intermediate_size": 3456,
246
+ "model_type": "qwen2_5_vl",
247
+ "out_hidden_size": 8192,
248
+ "spatial_patch_size": 14,
249
+ "tokens_per_second": 2
250
+ },
251
+ "vision_end_token_id": 151653,
252
+ "vision_start_token_id": 151652,
253
+ "vision_token_id": 151654,
254
+ "vocab_size": 152064
255
+ }
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": "4.49.0.dev0"
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:c4fdcf55d00ffa11e55fcc79ab5cca51d50a1d267219820ac66c36be0177fb23
3
+ size 4929545176
model-00002-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66dcd62e9496e9b8c456f6c95df848034fe648f4414ff1088a35f7a6efa44156
3
+ size 4873985928
model-00003-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f76e418f06f6b9b7f8a524f6405b1baee70ca7418a9a660f7537c490263ae35
3
+ size 4782749304
model-00004-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09782507221803a2287fcacb4ef166317fee2e62839ad43caa4c2f9ec461f77c
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:ab1e3dfb60f12733be7aae9274996f14814cc4680a707e1a201a0b627b4373ea
3
+ size 4782749368
model-00006-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39f8a745a63bdd2552d0aaa25728108ccd66718611bb8f1b1d1998a86e5054a1
3
+ size 4873986032
model-00007-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f452321174378d32090e7c94cffa3b43a4539e2f407f936b12a35639122005a
3
+ size 4782749368
model-00008-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87afe66c34acb2c5a7b118db74939afe8f47613f442eca4ed0f38a02e4e93fed
3
+ size 4873986032
model-00009-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a79addd10e3e66dcc4b53822ed86a7e31197ca3a54eaacc2a8140921d158f47
3
+ size 4782749368
model-00010-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83154d2dd5e7064947716c0930013e17943c378f80343c5f6067e8afdc291c1f
3
+ size 4873986032
model-00011-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48dd3dd98f76920c997a634e4f390f4ab11e629c7d76d752ef94844477bea183
3
+ size 4782749368
model-00012-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3168a6cbc214a1e83a04235e676fad12952ef36010442e02e007701ea23037e4
3
+ size 4873986032
model-00013-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98d1b9f92f0154fc8f7cbfe0c6d7d3955b088cf2c520e1a41c2f157c07c5b6bf
3
+ size 4782749368
model-00014-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46d25976bd3a6cb3055a1376a5a3ffec0f350d6a34a9749cbdd0495409e5e744
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:d17169ad645848ed1c32ef9d34529d80bbe052b3f5309d9f7973ed0fde30c09a
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:f3611e6a6ce31c332c9fcbaa2d5975ad981a6aa05470b66df74dab8811f7cb0a
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": "Qwen2_5_VLImageProcessor",
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": "Qwen2_5_VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 12845056,
26
+ "shortest_edge": 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: [lm_head, '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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff