Hugging Face's logo

prudant
/
MinerU2.5-2509-1.2B-W8A8

Safetensors
qwen2_vl
compressed-tensors
Model card Files
xet
Community
prudant commited on
Commit
b2fc9c6
·
verified ·
1 Parent(s): 5b06629

Upload compressed model

Browse files
Files changed (15) hide show
  1. .gitattributes +1 -0
  2. README.md +13 -0
  3. added_tokens.json +33 -0
  4. chat_template.jinja +7 -0
  5. config.json +300 -0
  6. generation_config.json +13 -0
  7. merges.txt +0 -0
  8. model.safetensors +3 -0
  9. preprocessor_config.json +37 -0
  10. recipe.yaml +20 -0
  11. special_tokens_map.json +48 -0
  12. tokenizer.json +3 -0
  13. tokenizer_config.json +296 -0
  14. video_preprocessor_config.json +43 -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
README.md ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ # prudant/MinerU2.5-2509-1.2B-W8A8
3
+
4
+ This is a compressed version of opendatalab/MinerU2.5-2509-1.2B using llm-compressor with the following scheme: W8A8
5
+
6
+ ## Model Details
7
+
8
+ - **Original Model**: opendatalab/MinerU2.5-2509-1.2B
9
+ - **Quantization Method**: GPTQ
10
+ - **Compression Libraries**: [llm-compressor](https://github.com/vllm-project/llm-compressor)
11
+ - **Calibration Dataset**: lmms-lab/flickr30k (2048 samples)
12
+ - **Optimized For**: Inference with vLLM
13
+ - **License**: same as original model
added_tokens.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<ched>": 151661,
3
+ "<ecel>": 151662,
4
+ "<fcel>": 151663,
5
+ "<lcel>": 151664,
6
+ "<nl>": 151667,
7
+ "<ucel>": 151665,
8
+ "<xcel>": 151666,
9
+ "<|box_end|>": 151649,
10
+ "<|box_start|>": 151648,
11
+ "<|endoftext|>": 151643,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|md_end|>": 151660,
16
+ "<|md_start|>": 151659,
17
+ "<|object_ref_end|>": 151647,
18
+ "<|object_ref_start|>": 151646,
19
+ "<|paratext|>": 151673,
20
+ "<|quad_end|>": 151651,
21
+ "<|quad_start|>": 151650,
22
+ "<|ref_end|>": 151658,
23
+ "<|ref_start|>": 151657,
24
+ "<|rotate_down|>": 151669,
25
+ "<|rotate_left|>": 151670,
26
+ "<|rotate_right|>": 151671,
27
+ "<|rotate_up|>": 151668,
28
+ "<|txt_contd|>": 151672,
29
+ "<|video_pad|>": 151656,
30
+ "<|vision_end|>": 151653,
31
+ "<|vision_pad|>": 151654,
32
+ "<|vision_start|>": 151652
33
+ }
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 +1,300 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 896,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4864,
13
+ "max_position_embeddings": 16384,
14
+ "max_window_layers": 24,
15
+ "model_type": "qwen2_vl",
16
+ "num_attention_heads": 14,
17
+ "num_hidden_layers": 24,
18
+ "num_key_value_heads": 2,
19
+ "quantization_config": {
20
+ "config_groups": {
21
+ "group_0": {
22
+ "format": "int-quantized",
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": "int"
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": "int"
50
+ }
51
+ }
52
+ },
53
+ "format": "int-quantized",
54
+ "global_compression_ratio": null,
55
+ "ignore": [
56
+ "model.visual.blocks.0.attn.qkv",
57
+ "model.visual.blocks.0.attn.proj",
58
+ "model.visual.blocks.0.mlp.fc1",
59
+ "model.visual.blocks.0.mlp.fc2",
60
+ "model.visual.blocks.1.attn.qkv",
61
+ "model.visual.blocks.1.attn.proj",
62
+ "model.visual.blocks.1.mlp.fc1",
63
+ "model.visual.blocks.1.mlp.fc2",
64
+ "model.visual.blocks.2.attn.qkv",
65
+ "model.visual.blocks.2.attn.proj",
66
+ "model.visual.blocks.2.mlp.fc1",
67
+ "model.visual.blocks.2.mlp.fc2",
68
+ "model.visual.blocks.3.attn.qkv",
69
+ "model.visual.blocks.3.attn.proj",
70
+ "model.visual.blocks.3.mlp.fc1",
71
+ "model.visual.blocks.3.mlp.fc2",
72
+ "model.visual.blocks.4.attn.qkv",
73
+ "model.visual.blocks.4.attn.proj",
74
+ "model.visual.blocks.4.mlp.fc1",
75
+ "model.visual.blocks.4.mlp.fc2",
76
+ "model.visual.blocks.5.attn.qkv",
77
+ "model.visual.blocks.5.attn.proj",
78
+ "model.visual.blocks.5.mlp.fc1",
79
+ "model.visual.blocks.5.mlp.fc2",
80
+ "model.visual.blocks.6.attn.qkv",
81
+ "model.visual.blocks.6.attn.proj",
82
+ "model.visual.blocks.6.mlp.fc1",
83
+ "model.visual.blocks.6.mlp.fc2",
84
+ "model.visual.blocks.7.attn.qkv",
85
+ "model.visual.blocks.7.attn.proj",
86
+ "model.visual.blocks.7.mlp.fc1",
87
+ "model.visual.blocks.7.mlp.fc2",
88
+ "model.visual.blocks.8.attn.qkv",
89
+ "model.visual.blocks.8.attn.proj",
90
+ "model.visual.blocks.8.mlp.fc1",
91
+ "model.visual.blocks.8.mlp.fc2",
92
+ "model.visual.blocks.9.attn.qkv",
93
+ "model.visual.blocks.9.attn.proj",
94
+ "model.visual.blocks.9.mlp.fc1",
95
+ "model.visual.blocks.9.mlp.fc2",
96
+ "model.visual.blocks.10.attn.qkv",
97
+ "model.visual.blocks.10.attn.proj",
98
+ "model.visual.blocks.10.mlp.fc1",
99
+ "model.visual.blocks.10.mlp.fc2",
100
+ "model.visual.blocks.11.attn.qkv",
101
+ "model.visual.blocks.11.attn.proj",
102
+ "model.visual.blocks.11.mlp.fc1",
103
+ "model.visual.blocks.11.mlp.fc2",
104
+ "model.visual.blocks.12.attn.qkv",
105
+ "model.visual.blocks.12.attn.proj",
106
+ "model.visual.blocks.12.mlp.fc1",
107
+ "model.visual.blocks.12.mlp.fc2",
108
+ "model.visual.blocks.13.attn.qkv",
109
+ "model.visual.blocks.13.attn.proj",
110
+ "model.visual.blocks.13.mlp.fc1",
111
+ "model.visual.blocks.13.mlp.fc2",
112
+ "model.visual.blocks.14.attn.qkv",
113
+ "model.visual.blocks.14.attn.proj",
114
+ "model.visual.blocks.14.mlp.fc1",
115
+ "model.visual.blocks.14.mlp.fc2",
116
+ "model.visual.blocks.15.attn.qkv",
117
+ "model.visual.blocks.15.attn.proj",
118
+ "model.visual.blocks.15.mlp.fc1",
119
+ "model.visual.blocks.15.mlp.fc2",
120
+ "model.visual.blocks.16.attn.qkv",
121
+ "model.visual.blocks.16.attn.proj",
122
+ "model.visual.blocks.16.mlp.fc1",
123
+ "model.visual.blocks.16.mlp.fc2",
124
+ "model.visual.blocks.17.attn.qkv",
125
+ "model.visual.blocks.17.attn.proj",
126
+ "model.visual.blocks.17.mlp.fc1",
127
+ "model.visual.blocks.17.mlp.fc2",
128
+ "model.visual.blocks.18.attn.qkv",
129
+ "model.visual.blocks.18.attn.proj",
130
+ "model.visual.blocks.18.mlp.fc1",
131
+ "model.visual.blocks.18.mlp.fc2",
132
+ "model.visual.blocks.19.attn.qkv",
133
+ "model.visual.blocks.19.attn.proj",
134
+ "model.visual.blocks.19.mlp.fc1",
135
+ "model.visual.blocks.19.mlp.fc2",
136
+ "model.visual.blocks.20.attn.qkv",
137
+ "model.visual.blocks.20.attn.proj",
138
+ "model.visual.blocks.20.mlp.fc1",
139
+ "model.visual.blocks.20.mlp.fc2",
140
+ "model.visual.blocks.21.attn.qkv",
141
+ "model.visual.blocks.21.attn.proj",
142
+ "model.visual.blocks.21.mlp.fc1",
143
+ "model.visual.blocks.21.mlp.fc2",
144
+ "model.visual.blocks.22.attn.qkv",
145
+ "model.visual.blocks.22.attn.proj",
146
+ "model.visual.blocks.22.mlp.fc1",
147
+ "model.visual.blocks.22.mlp.fc2",
148
+ "model.visual.blocks.23.attn.qkv",
149
+ "model.visual.blocks.23.attn.proj",
150
+ "model.visual.blocks.23.mlp.fc1",
151
+ "model.visual.blocks.23.mlp.fc2",
152
+ "model.visual.blocks.24.attn.qkv",
153
+ "model.visual.blocks.24.attn.proj",
154
+ "model.visual.blocks.24.mlp.fc1",
155
+ "model.visual.blocks.24.mlp.fc2",
156
+ "model.visual.blocks.25.attn.qkv",
157
+ "model.visual.blocks.25.attn.proj",
158
+ "model.visual.blocks.25.mlp.fc1",
159
+ "model.visual.blocks.25.mlp.fc2",
160
+ "model.visual.blocks.26.attn.qkv",
161
+ "model.visual.blocks.26.attn.proj",
162
+ "model.visual.blocks.26.mlp.fc1",
163
+ "model.visual.blocks.26.mlp.fc2",
164
+ "model.visual.blocks.27.attn.qkv",
165
+ "model.visual.blocks.27.attn.proj",
166
+ "model.visual.blocks.27.mlp.fc1",
167
+ "model.visual.blocks.27.mlp.fc2",
168
+ "model.visual.blocks.28.attn.qkv",
169
+ "model.visual.blocks.28.attn.proj",
170
+ "model.visual.blocks.28.mlp.fc1",
171
+ "model.visual.blocks.28.mlp.fc2",
172
+ "model.visual.blocks.29.attn.qkv",
173
+ "model.visual.blocks.29.attn.proj",
174
+ "model.visual.blocks.29.mlp.fc1",
175
+ "model.visual.blocks.29.mlp.fc2",
176
+ "model.visual.blocks.30.attn.qkv",
177
+ "model.visual.blocks.30.attn.proj",
178
+ "model.visual.blocks.30.mlp.fc1",
179
+ "model.visual.blocks.30.mlp.fc2",
180
+ "model.visual.blocks.31.attn.qkv",
181
+ "model.visual.blocks.31.attn.proj",
182
+ "model.visual.blocks.31.mlp.fc1",
183
+ "model.visual.blocks.31.mlp.fc2",
184
+ "model.visual.merger.mlp.0",
185
+ "model.visual.merger.mlp.2",
186
+ "lm_head"
187
+ ],
188
+ "kv_cache_scheme": null,
189
+ "quant_method": "compressed-tensors",
190
+ "quantization_status": "compressed",
191
+ "sparsity_config": {},
192
+ "transform_config": {},
193
+ "version": "0.11.0"
194
+ },
195
+ "rms_norm_eps": 1e-06,
196
+ "rope_scaling": {
197
+ "mrope_section": [
198
+ 8,
199
+ 12,
200
+ 12
201
+ ],
202
+ "rope_type": "default",
203
+ "type": "default"
204
+ },
205
+ "rope_theta": 1000000.0,
206
+ "sliding_window": 16384,
207
+ "text_config": {
208
+ "architectures": [
209
+ "Qwen2VLForConditionalGeneration"
210
+ ],
211
+ "attention_dropout": 0.0,
212
+ "bos_token_id": 151643,
213
+ "eos_token_id": 151645,
214
+ "hidden_act": "silu",
215
+ "hidden_size": 896,
216
+ "image_token_id": null,
217
+ "initializer_range": 0.02,
218
+ "intermediate_size": 4864,
219
+ "layer_types": [
220
+ "full_attention",
221
+ "full_attention",
222
+ "full_attention",
223
+ "full_attention",
224
+ "full_attention",
225
+ "full_attention",
226
+ "full_attention",
227
+ "full_attention",
228
+ "full_attention",
229
+ "full_attention",
230
+ "full_attention",
231
+ "full_attention",
232
+ "full_attention",
233
+ "full_attention",
234
+ "full_attention",
235
+ "full_attention",
236
+ "full_attention",
237
+ "full_attention",
238
+ "full_attention",
239
+ "full_attention",
240
+ "full_attention",
241
+ "full_attention",
242
+ "full_attention",
243
+ "full_attention"
244
+ ],
245
+ "max_position_embeddings": 16384,
246
+ "max_window_layers": 24,
247
+ "model_type": "qwen2_vl_text",
248
+ "num_attention_heads": 14,
249
+ "num_hidden_layers": 24,
250
+ "num_key_value_heads": 2,
251
+ "rms_norm_eps": 1e-06,
252
+ "rope_scaling": {
253
+ "mrope_section": [
254
+ 8,
255
+ 12,
256
+ 12
257
+ ],
258
+ "rope_type": "default",
259
+ "type": "default"
260
+ },
261
+ "rope_theta": 1000000.0,
262
+ "sliding_window": null,
263
+ "tie_word_embeddings": true,
264
+ "torch_dtype": "bfloat16",
265
+ "use_cache": true,
266
+ "use_sliding_window": false,
267
+ "video_token_id": null,
268
+ "vision_end_token_id": 151653,
269
+ "vision_start_token_id": 151652,
270
+ "vision_token_id": 151654,
271
+ "vocab_size": 151936
272
+ },
273
+ "tie_word_embeddings": false,
274
+ "torch_dtype": "bfloat16",
275
+ "transformers_version": "4.55.2",
276
+ "use_cache": true,
277
+ "use_sliding_window": false,
278
+ "video_token_id": 151656,
279
+ "vision_config": {
280
+ "depth": 32,
281
+ "embed_dim": 1280,
282
+ "hidden_act": "quick_gelu",
283
+ "hidden_size": 896,
284
+ "in_channels": 3,
285
+ "in_chans": 3,
286
+ "initializer_range": 0.02,
287
+ "mlp_ratio": 4,
288
+ "model_type": "qwen2_vl",
289
+ "num_heads": 16,
290
+ "patch_size": 14,
291
+ "spatial_merge_size": 2,
292
+ "spatial_patch_size": 14,
293
+ "temporal_patch_size": 2,
294
+ "torch_dtype": "bfloat16"
295
+ },
296
+ "vision_end_token_id": 151653,
297
+ "vision_start_token_id": 151652,
298
+ "vision_token_id": 151654,
299
+ "vocab_size": 151936
300
+ }
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
+ "temperature": 0.01,
10
+ "top_k": 1,
11
+ "top_p": 0.001,
12
+ "transformers_version": "4.55.2"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8a39404b215e8513a075f1c76c3a979dcb0fe5cad2dcd25c9f50622340ddd89
3
+ size 2227197008
preprocessor_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "Qwen2VLImageProcessorFast",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "input_data_format": null,
24
+ "max_pixels": 1605632,
25
+ "merge_size": 2,
26
+ "min_pixels": 3136,
27
+ "patch_size": 14,
28
+ "processor_class": "Qwen2VLProcessor",
29
+ "resample": 3,
30
+ "rescale_factor": 0.00392156862745098,
31
+ "return_tensors": null,
32
+ "size": {
33
+ "longest_edge": 1605632,
34
+ "shortest_edge": 3136
35
+ },
36
+ "temporal_patch_size": 2
37
+ }
recipe.yaml ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ SmoothQuantModifier:
4
+ smoothing_strength: 0.8
5
+ mappings:
6
+ - !!python/tuple
7
+ - ['re:.*q_proj', 're:.*k_proj', 're:.*v_proj']
8
+ - re:.*input_layernorm
9
+ - !!python/tuple
10
+ - ['re:.*gate_proj', 're:.*up_proj']
11
+ - re:.*post_attention_layernorm
12
+ ignore: []
13
+ GPTQModifier:
14
+ targets: [Linear]
15
+ ignore: [lm_head, 're:visual.*', 're:model.visual.*']
16
+ scheme: W8A8
17
+ sequential_update: true
18
+ block_size: 128
19
+ dampening_frac: 0.01
20
+ offload_hessians: false
special_tokens_map.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<|ref_start|>",
17
+ "<|ref_end|>",
18
+ "<|md_start|>",
19
+ "<|md_end|>",
20
+ "<ched>",
21
+ "<ecel>",
22
+ "<fcel>",
23
+ "<lcel>",
24
+ "<ucel>",
25
+ "<xcel>",
26
+ "<nl>",
27
+ "<|rotate_up|>",
28
+ "<|rotate_down|>",
29
+ "<|rotate_left|>",
30
+ "<|rotate_right|>",
31
+ "<|txt_contd|>",
32
+ "<|paratext|>"
33
+ ],
34
+ "eos_token": {
35
+ "content": "<|im_end|>",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "pad_token": {
42
+ "content": "<|endoftext|>",
43
+ "lstrip": false,
44
+ "normalized": false,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ }
48
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dceac5fc54a795ee7570d17902b47bd05412dc2afa62bdf325c3f97fcb5b87fe
3
+ size 11423550
tokenizer_config.json ADDED
@@ -0,0 +1,296 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|ref_start|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "151658": {
125
+ "content": "<|ref_end|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "151659": {
133
+ "content": "<|md_start|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "151660": {
141
+ "content": "<|md_end|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "151661": {
149
+ "content": "<ched>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "151662": {
157
+ "content": "<ecel>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "151663": {
165
+ "content": "<fcel>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "151664": {
173
+ "content": "<lcel>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "151665": {
181
+ "content": "<ucel>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "151666": {
189
+ "content": "<xcel>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "151667": {
197
+ "content": "<nl>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "151668": {
205
+ "content": "<|rotate_up|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "151669": {
213
+ "content": "<|rotate_down|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "151670": {
221
+ "content": "<|rotate_left|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "151671": {
229
+ "content": "<|rotate_right|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "151672": {
237
+ "content": "<|txt_contd|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "151673": {
245
+ "content": "<|paratext|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ }
252
+ },
253
+ "additional_special_tokens": [
254
+ "<|im_start|>",
255
+ "<|im_end|>",
256
+ "<|object_ref_start|>",
257
+ "<|object_ref_end|>",
258
+ "<|box_start|>",
259
+ "<|box_end|>",
260
+ "<|quad_start|>",
261
+ "<|quad_end|>",
262
+ "<|vision_start|>",
263
+ "<|vision_end|>",
264
+ "<|vision_pad|>",
265
+ "<|image_pad|>",
266
+ "<|video_pad|>",
267
+ "<|ref_start|>",
268
+ "<|ref_end|>",
269
+ "<|md_start|>",
270
+ "<|md_end|>",
271
+ "<ched>",
272
+ "<ecel>",
273
+ "<fcel>",
274
+ "<lcel>",
275
+ "<ucel>",
276
+ "<xcel>",
277
+ "<nl>",
278
+ "<|rotate_up|>",
279
+ "<|rotate_down|>",
280
+ "<|rotate_left|>",
281
+ "<|rotate_right|>",
282
+ "<|txt_contd|>",
283
+ "<|paratext|>"
284
+ ],
285
+ "bos_token": null,
286
+ "clean_up_tokenization_spaces": false,
287
+ "eos_token": "<|im_end|>",
288
+ "errors": "replace",
289
+ "extra_special_tokens": {},
290
+ "model_max_length": 16384,
291
+ "pad_token": "<|endoftext|>",
292
+ "padding_side": "left",
293
+ "split_special_tokens": false,
294
+ "tokenizer_class": "Qwen2Tokenizer",
295
+ "unk_token": null
296
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_pad": null,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "do_sample_frames": false,
13
+ "fps": null,
14
+ "image_mean": [
15
+ 0.48145466,
16
+ 0.4578275,
17
+ 0.40821073
18
+ ],
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "max_frames": 768,
26
+ "max_pixels": 1605632,
27
+ "merge_size": 2,
28
+ "min_frames": 4,
29
+ "min_pixels": 3136,
30
+ "num_frames": null,
31
+ "patch_size": 14,
32
+ "processor_class": "Qwen2VLProcessor",
33
+ "resample": 3,
34
+ "rescale_factor": 0.00392156862745098,
35
+ "size": {
36
+ "longest_edge": 1605632,
37
+ "shortest_edge": 3136
38
+ },
39
+ "size_divisor": null,
40
+ "temporal_patch_size": 2,
41
+ "video_metadata": null,
42
+ "video_processor_type": "Qwen2VLVideoProcessor"
43
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff