Hugging Face's logo

ig1
/
Qwen2.5-VL-7B-Instruct-NVFP4

Image-Text-to-Text
Transformers
Safetensors
English
qwen2_5_vl
multimodal
conversational
text-generation-inference
8-bit precision
compressed-tensors
Model card Files
xet
 Community
ig1sa commited on
Commit
32326f3
·
verified ·
1 Parent(s): 941d122

Upload folder using huggingface_hub

Browse files
Files changed (15) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +24 -0
  3. chat_template.jinja +7 -0
  4. config.json +339 -0
  5. generation_config.json +12 -0
  6. merges.txt +0 -0
  7. model-00001-of-00002.safetensors +3 -0
  8. model-00002-of-00002.safetensors +3 -0
  9. model.safetensors.index.json +0 -0
  10. processor_config.json +86 -0
  11. recipe.yaml +6 -0
  12. special_tokens_map.json +31 -0
  13. tokenizer.json +3 -0
  14. tokenizer_config.json +208 -0
  15. 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.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% 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
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% 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|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
config.json ADDED
@@ -0,0 +1,339 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "image_token_id": 151655,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 18944,
14
+ "max_position_embeddings": 128000,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen2_5_vl",
17
+ "num_attention_heads": 28,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 4,
20
+ "quantization_config": {
21
+ "config_groups": {
22
+ "group_0": {
23
+ "format": "nvfp4-pack-quantized",
24
+ "input_activations": {
25
+ "actorder": null,
26
+ "block_structure": null,
27
+ "dynamic": "local",
28
+ "group_size": 16,
29
+ "num_bits": 4,
30
+ "observer": "minmax",
31
+ "observer_kwargs": {},
32
+ "strategy": "tensor_group",
33
+ "symmetric": true,
34
+ "type": "float"
35
+ },
36
+ "output_activations": null,
37
+ "targets": [
38
+ "Linear"
39
+ ],
40
+ "weights": {
41
+ "actorder": null,
42
+ "block_structure": null,
43
+ "dynamic": false,
44
+ "group_size": 16,
45
+ "num_bits": 4,
46
+ "observer": "minmax",
47
+ "observer_kwargs": {},
48
+ "strategy": "tensor_group",
49
+ "symmetric": true,
50
+ "type": "float"
51
+ }
52
+ }
53
+ },
54
+ "format": "nvfp4-pack-quantized",
55
+ "global_compression_ratio": null,
56
+ "ignore": [
57
+ "model.visual.blocks.0.attn.qkv",
58
+ "model.visual.blocks.0.attn.proj",
59
+ "model.visual.blocks.0.mlp.gate_proj",
60
+ "model.visual.blocks.0.mlp.up_proj",
61
+ "model.visual.blocks.0.mlp.down_proj",
62
+ "model.visual.blocks.1.attn.qkv",
63
+ "model.visual.blocks.1.attn.proj",
64
+ "model.visual.blocks.1.mlp.gate_proj",
65
+ "model.visual.blocks.1.mlp.up_proj",
66
+ "model.visual.blocks.1.mlp.down_proj",
67
+ "model.visual.blocks.2.attn.qkv",
68
+ "model.visual.blocks.2.attn.proj",
69
+ "model.visual.blocks.2.mlp.gate_proj",
70
+ "model.visual.blocks.2.mlp.up_proj",
71
+ "model.visual.blocks.2.mlp.down_proj",
72
+ "model.visual.blocks.3.attn.qkv",
73
+ "model.visual.blocks.3.attn.proj",
74
+ "model.visual.blocks.3.mlp.gate_proj",
75
+ "model.visual.blocks.3.mlp.up_proj",
76
+ "model.visual.blocks.3.mlp.down_proj",
77
+ "model.visual.blocks.4.attn.qkv",
78
+ "model.visual.blocks.4.attn.proj",
79
+ "model.visual.blocks.4.mlp.gate_proj",
80
+ "model.visual.blocks.4.mlp.up_proj",
81
+ "model.visual.blocks.4.mlp.down_proj",
82
+ "model.visual.blocks.5.attn.qkv",
83
+ "model.visual.blocks.5.attn.proj",
84
+ "model.visual.blocks.5.mlp.gate_proj",
85
+ "model.visual.blocks.5.mlp.up_proj",
86
+ "model.visual.blocks.5.mlp.down_proj",
87
+ "model.visual.blocks.6.attn.qkv",
88
+ "model.visual.blocks.6.attn.proj",
89
+ "model.visual.blocks.6.mlp.gate_proj",
90
+ "model.visual.blocks.6.mlp.up_proj",
91
+ "model.visual.blocks.6.mlp.down_proj",
92
+ "model.visual.blocks.7.attn.qkv",
93
+ "model.visual.blocks.7.attn.proj",
94
+ "model.visual.blocks.7.mlp.gate_proj",
95
+ "model.visual.blocks.7.mlp.up_proj",
96
+ "model.visual.blocks.7.mlp.down_proj",
97
+ "model.visual.blocks.8.attn.qkv",
98
+ "model.visual.blocks.8.attn.proj",
99
+ "model.visual.blocks.8.mlp.gate_proj",
100
+ "model.visual.blocks.8.mlp.up_proj",
101
+ "model.visual.blocks.8.mlp.down_proj",
102
+ "model.visual.blocks.9.attn.qkv",
103
+ "model.visual.blocks.9.attn.proj",
104
+ "model.visual.blocks.9.mlp.gate_proj",
105
+ "model.visual.blocks.9.mlp.up_proj",
106
+ "model.visual.blocks.9.mlp.down_proj",
107
+ "model.visual.blocks.10.attn.qkv",
108
+ "model.visual.blocks.10.attn.proj",
109
+ "model.visual.blocks.10.mlp.gate_proj",
110
+ "model.visual.blocks.10.mlp.up_proj",
111
+ "model.visual.blocks.10.mlp.down_proj",
112
+ "model.visual.blocks.11.attn.qkv",
113
+ "model.visual.blocks.11.attn.proj",
114
+ "model.visual.blocks.11.mlp.gate_proj",
115
+ "model.visual.blocks.11.mlp.up_proj",
116
+ "model.visual.blocks.11.mlp.down_proj",
117
+ "model.visual.blocks.12.attn.qkv",
118
+ "model.visual.blocks.12.attn.proj",
119
+ "model.visual.blocks.12.mlp.gate_proj",
120
+ "model.visual.blocks.12.mlp.up_proj",
121
+ "model.visual.blocks.12.mlp.down_proj",
122
+ "model.visual.blocks.13.attn.qkv",
123
+ "model.visual.blocks.13.attn.proj",
124
+ "model.visual.blocks.13.mlp.gate_proj",
125
+ "model.visual.blocks.13.mlp.up_proj",
126
+ "model.visual.blocks.13.mlp.down_proj",
127
+ "model.visual.blocks.14.attn.qkv",
128
+ "model.visual.blocks.14.attn.proj",
129
+ "model.visual.blocks.14.mlp.gate_proj",
130
+ "model.visual.blocks.14.mlp.up_proj",
131
+ "model.visual.blocks.14.mlp.down_proj",
132
+ "model.visual.blocks.15.attn.qkv",
133
+ "model.visual.blocks.15.attn.proj",
134
+ "model.visual.blocks.15.mlp.gate_proj",
135
+ "model.visual.blocks.15.mlp.up_proj",
136
+ "model.visual.blocks.15.mlp.down_proj",
137
+ "model.visual.blocks.16.attn.qkv",
138
+ "model.visual.blocks.16.attn.proj",
139
+ "model.visual.blocks.16.mlp.gate_proj",
140
+ "model.visual.blocks.16.mlp.up_proj",
141
+ "model.visual.blocks.16.mlp.down_proj",
142
+ "model.visual.blocks.17.attn.qkv",
143
+ "model.visual.blocks.17.attn.proj",
144
+ "model.visual.blocks.17.mlp.gate_proj",
145
+ "model.visual.blocks.17.mlp.up_proj",
146
+ "model.visual.blocks.17.mlp.down_proj",
147
+ "model.visual.blocks.18.attn.qkv",
148
+ "model.visual.blocks.18.attn.proj",
149
+ "model.visual.blocks.18.mlp.gate_proj",
150
+ "model.visual.blocks.18.mlp.up_proj",
151
+ "model.visual.blocks.18.mlp.down_proj",
152
+ "model.visual.blocks.19.attn.qkv",
153
+ "model.visual.blocks.19.attn.proj",
154
+ "model.visual.blocks.19.mlp.gate_proj",
155
+ "model.visual.blocks.19.mlp.up_proj",
156
+ "model.visual.blocks.19.mlp.down_proj",
157
+ "model.visual.blocks.20.attn.qkv",
158
+ "model.visual.blocks.20.attn.proj",
159
+ "model.visual.blocks.20.mlp.gate_proj",
160
+ "model.visual.blocks.20.mlp.up_proj",
161
+ "model.visual.blocks.20.mlp.down_proj",
162
+ "model.visual.blocks.21.attn.qkv",
163
+ "model.visual.blocks.21.attn.proj",
164
+ "model.visual.blocks.21.mlp.gate_proj",
165
+ "model.visual.blocks.21.mlp.up_proj",
166
+ "model.visual.blocks.21.mlp.down_proj",
167
+ "model.visual.blocks.22.attn.qkv",
168
+ "model.visual.blocks.22.attn.proj",
169
+ "model.visual.blocks.22.mlp.gate_proj",
170
+ "model.visual.blocks.22.mlp.up_proj",
171
+ "model.visual.blocks.22.mlp.down_proj",
172
+ "model.visual.blocks.23.attn.qkv",
173
+ "model.visual.blocks.23.attn.proj",
174
+ "model.visual.blocks.23.mlp.gate_proj",
175
+ "model.visual.blocks.23.mlp.up_proj",
176
+ "model.visual.blocks.23.mlp.down_proj",
177
+ "model.visual.blocks.24.attn.qkv",
178
+ "model.visual.blocks.24.attn.proj",
179
+ "model.visual.blocks.24.mlp.gate_proj",
180
+ "model.visual.blocks.24.mlp.up_proj",
181
+ "model.visual.blocks.24.mlp.down_proj",
182
+ "model.visual.blocks.25.attn.qkv",
183
+ "model.visual.blocks.25.attn.proj",
184
+ "model.visual.blocks.25.mlp.gate_proj",
185
+ "model.visual.blocks.25.mlp.up_proj",
186
+ "model.visual.blocks.25.mlp.down_proj",
187
+ "model.visual.blocks.26.attn.qkv",
188
+ "model.visual.blocks.26.attn.proj",
189
+ "model.visual.blocks.26.mlp.gate_proj",
190
+ "model.visual.blocks.26.mlp.up_proj",
191
+ "model.visual.blocks.26.mlp.down_proj",
192
+ "model.visual.blocks.27.attn.qkv",
193
+ "model.visual.blocks.27.attn.proj",
194
+ "model.visual.blocks.27.mlp.gate_proj",
195
+ "model.visual.blocks.27.mlp.up_proj",
196
+ "model.visual.blocks.27.mlp.down_proj",
197
+ "model.visual.blocks.28.attn.qkv",
198
+ "model.visual.blocks.28.attn.proj",
199
+ "model.visual.blocks.28.mlp.gate_proj",
200
+ "model.visual.blocks.28.mlp.up_proj",
201
+ "model.visual.blocks.28.mlp.down_proj",
202
+ "model.visual.blocks.29.attn.qkv",
203
+ "model.visual.blocks.29.attn.proj",
204
+ "model.visual.blocks.29.mlp.gate_proj",
205
+ "model.visual.blocks.29.mlp.up_proj",
206
+ "model.visual.blocks.29.mlp.down_proj",
207
+ "model.visual.blocks.30.attn.qkv",
208
+ "model.visual.blocks.30.attn.proj",
209
+ "model.visual.blocks.30.mlp.gate_proj",
210
+ "model.visual.blocks.30.mlp.up_proj",
211
+ "model.visual.blocks.30.mlp.down_proj",
212
+ "model.visual.blocks.31.attn.qkv",
213
+ "model.visual.blocks.31.attn.proj",
214
+ "model.visual.blocks.31.mlp.gate_proj",
215
+ "model.visual.blocks.31.mlp.up_proj",
216
+ "model.visual.blocks.31.mlp.down_proj",
217
+ "model.visual.merger.mlp.0",
218
+ "model.visual.merger.mlp.2",
219
+ "lm_head"
220
+ ],
221
+ "kv_cache_scheme": null,
222
+ "quant_method": "compressed-tensors",
223
+ "quantization_status": "compressed",
224
+ "sparsity_config": {},
225
+ "transform_config": {},
226
+ "version": "0.12.2"
227
+ },
228
+ "rms_norm_eps": 1e-06,
229
+ "rope_scaling": {
230
+ "mrope_section": [
231
+ 16,
232
+ 24,
233
+ 24
234
+ ],
235
+ "rope_type": "default",
236
+ "type": "default"
237
+ },
238
+ "rope_theta": 1000000.0,
239
+ "sliding_window": 32768,
240
+ "text_config": {
241
+ "_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
242
+ "architectures": [
243
+ "Qwen2_5_VLForConditionalGeneration"
244
+ ],
245
+ "attention_dropout": 0.0,
246
+ "bos_token_id": 151643,
247
+ "dtype": "bfloat16",
248
+ "eos_token_id": 151645,
249
+ "hidden_act": "silu",
250
+ "hidden_size": 3584,
251
+ "initializer_range": 0.02,
252
+ "intermediate_size": 18944,
253
+ "layer_types": [
254
+ "full_attention",
255
+ "full_attention",
256
+ "full_attention",
257
+ "full_attention",
258
+ "full_attention",
259
+ "full_attention",
260
+ "full_attention",
261
+ "full_attention",
262
+ "full_attention",
263
+ "full_attention",
264
+ "full_attention",
265
+ "full_attention",
266
+ "full_attention",
267
+ "full_attention",
268
+ "full_attention",
269
+ "full_attention",
270
+ "full_attention",
271
+ "full_attention",
272
+ "full_attention",
273
+ "full_attention",
274
+ "full_attention",
275
+ "full_attention",
276
+ "full_attention",
277
+ "full_attention",
278
+ "full_attention",
279
+ "full_attention",
280
+ "full_attention",
281
+ "full_attention"
282
+ ],
283
+ "max_position_embeddings": 128000,
284
+ "max_window_layers": 28,
285
+ "model_type": "qwen2_5_vl_text",
286
+ "num_attention_heads": 28,
287
+ "num_hidden_layers": 28,
288
+ "num_key_value_heads": 4,
289
+ "rms_norm_eps": 1e-06,
290
+ "rope_scaling": {
291
+ "mrope_section": [
292
+ 16,
293
+ 24,
294
+ 24
295
+ ],
296
+ "rope_type": "default",
297
+ "type": "default"
298
+ },
299
+ "rope_theta": 1000000.0,
300
+ "sliding_window": null,
301
+ "use_cache": true,
302
+ "use_sliding_window": false,
303
+ "vision_token_id": 151654,
304
+ "vocab_size": 152064
305
+ },
306
+ "tie_word_embeddings": false,
307
+ "transformers_version": "5.0.0.dev0",
308
+ "use_cache": true,
309
+ "use_sliding_window": false,
310
+ "video_token_id": 151656,
311
+ "vision_config": {
312
+ "depth": 32,
313
+ "fullatt_block_indexes": [
314
+ 7,
315
+ 15,
316
+ 23,
317
+ 31
318
+ ],
319
+ "hidden_act": "silu",
320
+ "hidden_size": 1280,
321
+ "in_channels": 3,
322
+ "in_chans": 3,
323
+ "initializer_range": 0.02,
324
+ "intermediate_size": 3420,
325
+ "model_type": "qwen2_5_vl",
326
+ "num_heads": 16,
327
+ "out_hidden_size": 3584,
328
+ "patch_size": 14,
329
+ "spatial_merge_size": 2,
330
+ "spatial_patch_size": 14,
331
+ "temporal_patch_size": 2,
332
+ "tokens_per_second": 2,
333
+ "window_size": 112
334
+ },
335
+ "vision_end_token_id": 151653,
336
+ "vision_start_token_id": 151652,
337
+ "vision_token_id": 151654,
338
+ "vocab_size": 152064
339
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "temperature": 1e-06,
11
+ "transformers_version": "5.0.0.dev0"
12
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:762f2cb94c78840722774f09110b11ba776a9dbf576c3d95de481b899a821574
3
+ size 4989054768
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c06b5425aa5dbe8e60f6763c1a8a8f5ae5ca2541a612497f827a3b38ab8425e
3
+ size 2215325872
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
processor_config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "crop_size": null,
4
+ "data_format": "channels_first",
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_pad": null,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_processor_type": "Qwen2VLImageProcessorFast",
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "max_pixels": 12845056,
26
+ "merge_size": 2,
27
+ "min_pixels": 3136,
28
+ "pad_size": null,
29
+ "patch_size": 14,
30
+ "processor_class": "Qwen2_5_VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_tensors": null,
34
+ "size": {
35
+ "longest_edge": 12845056,
36
+ "shortest_edge": 3136
37
+ },
38
+ "temporal_patch_size": 2
39
+ },
40
+ "processor_class": "Qwen2_5_VLProcessor",
41
+ "video_processor": {
42
+ "crop_size": null,
43
+ "data_format": "channels_first",
44
+ "default_to_square": true,
45
+ "device": null,
46
+ "do_center_crop": null,
47
+ "do_convert_rgb": true,
48
+ "do_normalize": true,
49
+ "do_pad": null,
50
+ "do_rescale": true,
51
+ "do_resize": true,
52
+ "do_sample_frames": false,
53
+ "fps": null,
54
+ "image_mean": [
55
+ 0.48145466,
56
+ 0.4578275,
57
+ 0.40821073
58
+ ],
59
+ "image_std": [
60
+ 0.26862954,
61
+ 0.26130258,
62
+ 0.27577711
63
+ ],
64
+ "input_data_format": null,
65
+ "max_frames": 768,
66
+ "max_pixels": 12845056,
67
+ "merge_size": 2,
68
+ "min_frames": 4,
69
+ "min_pixels": 3136,
70
+ "num_frames": null,
71
+ "pad_size": null,
72
+ "patch_size": 14,
73
+ "processor_class": "Qwen2_5_VLProcessor",
74
+ "resample": 3,
75
+ "rescale_factor": 0.00392156862745098,
76
+ "return_metadata": false,
77
+ "return_tensors": null,
78
+ "size": {
79
+ "longest_edge": 12845056,
80
+ "shortest_edge": 3136
81
+ },
82
+ "temporal_patch_size": 2,
83
+ "video_metadata": null,
84
+ "video_processor_type": "Qwen2VLVideoProcessor"
85
+ }
86
+ }
recipe.yaml ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ QuantizationModifier:
4
+ targets: [Linear]
5
+ ignore: [lm_head, 're:visual.*', 're:model.visual.*']
6
+ scheme: NVFP4
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 sha256:913950e4971737031da511cdd1b410daae4566f62eb845b3975bca5a102323d8
3
+ size 11421995
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
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "processor_class": "Qwen2_5_VLProcessor",
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