jester6136 commited on
Commit
e529d5e
·
verified ·
1 Parent(s): 2220973

Upload folder using huggingface_hub

Browse files
.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 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 2048,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 128000,
14
+ "max_window_layers": 70,
15
+ "model_type": "qwen2_5_vl",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 36,
18
+ "num_key_value_heads": 2,
19
+ "quantization_config": {
20
+ "config_groups": {
21
+ "group_0": {
22
+ "input_activations": null,
23
+ "output_activations": null,
24
+ "targets": [
25
+ "Linear"
26
+ ],
27
+ "weights": {
28
+ "actorder": null,
29
+ "block_structure": null,
30
+ "dynamic": false,
31
+ "group_size": 128,
32
+ "num_bits": 4,
33
+ "observer": "minmax",
34
+ "observer_kwargs": {},
35
+ "strategy": "group",
36
+ "symmetric": true,
37
+ "type": "int"
38
+ }
39
+ }
40
+ },
41
+ "format": "pack-quantized",
42
+ "global_compression_ratio": null,
43
+ "ignore": [
44
+ "model.visual.blocks.0.attn.qkv",
45
+ "model.visual.blocks.0.attn.proj",
46
+ "model.visual.blocks.0.mlp.gate_proj",
47
+ "model.visual.blocks.0.mlp.up_proj",
48
+ "model.visual.blocks.0.mlp.down_proj",
49
+ "model.visual.blocks.1.attn.qkv",
50
+ "model.visual.blocks.1.attn.proj",
51
+ "model.visual.blocks.1.mlp.gate_proj",
52
+ "model.visual.blocks.1.mlp.up_proj",
53
+ "model.visual.blocks.1.mlp.down_proj",
54
+ "model.visual.blocks.2.attn.qkv",
55
+ "model.visual.blocks.2.attn.proj",
56
+ "model.visual.blocks.2.mlp.gate_proj",
57
+ "model.visual.blocks.2.mlp.up_proj",
58
+ "model.visual.blocks.2.mlp.down_proj",
59
+ "model.visual.blocks.3.attn.qkv",
60
+ "model.visual.blocks.3.attn.proj",
61
+ "model.visual.blocks.3.mlp.gate_proj",
62
+ "model.visual.blocks.3.mlp.up_proj",
63
+ "model.visual.blocks.3.mlp.down_proj",
64
+ "model.visual.blocks.4.attn.qkv",
65
+ "model.visual.blocks.4.attn.proj",
66
+ "model.visual.blocks.4.mlp.gate_proj",
67
+ "model.visual.blocks.4.mlp.up_proj",
68
+ "model.visual.blocks.4.mlp.down_proj",
69
+ "model.visual.blocks.5.attn.qkv",
70
+ "model.visual.blocks.5.attn.proj",
71
+ "model.visual.blocks.5.mlp.gate_proj",
72
+ "model.visual.blocks.5.mlp.up_proj",
73
+ "model.visual.blocks.5.mlp.down_proj",
74
+ "model.visual.blocks.6.attn.qkv",
75
+ "model.visual.blocks.6.attn.proj",
76
+ "model.visual.blocks.6.mlp.gate_proj",
77
+ "model.visual.blocks.6.mlp.up_proj",
78
+ "model.visual.blocks.6.mlp.down_proj",
79
+ "model.visual.blocks.7.attn.qkv",
80
+ "model.visual.blocks.7.attn.proj",
81
+ "model.visual.blocks.7.mlp.gate_proj",
82
+ "model.visual.blocks.7.mlp.up_proj",
83
+ "model.visual.blocks.7.mlp.down_proj",
84
+ "model.visual.blocks.8.attn.qkv",
85
+ "model.visual.blocks.8.attn.proj",
86
+ "model.visual.blocks.8.mlp.gate_proj",
87
+ "model.visual.blocks.8.mlp.up_proj",
88
+ "model.visual.blocks.8.mlp.down_proj",
89
+ "model.visual.blocks.9.attn.qkv",
90
+ "model.visual.blocks.9.attn.proj",
91
+ "model.visual.blocks.9.mlp.gate_proj",
92
+ "model.visual.blocks.9.mlp.up_proj",
93
+ "model.visual.blocks.9.mlp.down_proj",
94
+ "model.visual.blocks.10.attn.qkv",
95
+ "model.visual.blocks.10.attn.proj",
96
+ "model.visual.blocks.10.mlp.gate_proj",
97
+ "model.visual.blocks.10.mlp.up_proj",
98
+ "model.visual.blocks.10.mlp.down_proj",
99
+ "model.visual.blocks.11.attn.qkv",
100
+ "model.visual.blocks.11.attn.proj",
101
+ "model.visual.blocks.11.mlp.gate_proj",
102
+ "model.visual.blocks.11.mlp.up_proj",
103
+ "model.visual.blocks.11.mlp.down_proj",
104
+ "model.visual.blocks.12.attn.qkv",
105
+ "model.visual.blocks.12.attn.proj",
106
+ "model.visual.blocks.12.mlp.gate_proj",
107
+ "model.visual.blocks.12.mlp.up_proj",
108
+ "model.visual.blocks.12.mlp.down_proj",
109
+ "model.visual.blocks.13.attn.qkv",
110
+ "model.visual.blocks.13.attn.proj",
111
+ "model.visual.blocks.13.mlp.gate_proj",
112
+ "model.visual.blocks.13.mlp.up_proj",
113
+ "model.visual.blocks.13.mlp.down_proj",
114
+ "model.visual.blocks.14.attn.qkv",
115
+ "model.visual.blocks.14.attn.proj",
116
+ "model.visual.blocks.14.mlp.gate_proj",
117
+ "model.visual.blocks.14.mlp.up_proj",
118
+ "model.visual.blocks.14.mlp.down_proj",
119
+ "model.visual.blocks.15.attn.qkv",
120
+ "model.visual.blocks.15.attn.proj",
121
+ "model.visual.blocks.15.mlp.gate_proj",
122
+ "model.visual.blocks.15.mlp.up_proj",
123
+ "model.visual.blocks.15.mlp.down_proj",
124
+ "model.visual.blocks.16.attn.qkv",
125
+ "model.visual.blocks.16.attn.proj",
126
+ "model.visual.blocks.16.mlp.gate_proj",
127
+ "model.visual.blocks.16.mlp.up_proj",
128
+ "model.visual.blocks.16.mlp.down_proj",
129
+ "model.visual.blocks.17.attn.qkv",
130
+ "model.visual.blocks.17.attn.proj",
131
+ "model.visual.blocks.17.mlp.gate_proj",
132
+ "model.visual.blocks.17.mlp.up_proj",
133
+ "model.visual.blocks.17.mlp.down_proj",
134
+ "model.visual.blocks.18.attn.qkv",
135
+ "model.visual.blocks.18.attn.proj",
136
+ "model.visual.blocks.18.mlp.gate_proj",
137
+ "model.visual.blocks.18.mlp.up_proj",
138
+ "model.visual.blocks.18.mlp.down_proj",
139
+ "model.visual.blocks.19.attn.qkv",
140
+ "model.visual.blocks.19.attn.proj",
141
+ "model.visual.blocks.19.mlp.gate_proj",
142
+ "model.visual.blocks.19.mlp.up_proj",
143
+ "model.visual.blocks.19.mlp.down_proj",
144
+ "model.visual.blocks.20.attn.qkv",
145
+ "model.visual.blocks.20.attn.proj",
146
+ "model.visual.blocks.20.mlp.gate_proj",
147
+ "model.visual.blocks.20.mlp.up_proj",
148
+ "model.visual.blocks.20.mlp.down_proj",
149
+ "model.visual.blocks.21.attn.qkv",
150
+ "model.visual.blocks.21.attn.proj",
151
+ "model.visual.blocks.21.mlp.gate_proj",
152
+ "model.visual.blocks.21.mlp.up_proj",
153
+ "model.visual.blocks.21.mlp.down_proj",
154
+ "model.visual.blocks.22.attn.qkv",
155
+ "model.visual.blocks.22.attn.proj",
156
+ "model.visual.blocks.22.mlp.gate_proj",
157
+ "model.visual.blocks.22.mlp.up_proj",
158
+ "model.visual.blocks.22.mlp.down_proj",
159
+ "model.visual.blocks.23.attn.qkv",
160
+ "model.visual.blocks.23.attn.proj",
161
+ "model.visual.blocks.23.mlp.gate_proj",
162
+ "model.visual.blocks.23.mlp.up_proj",
163
+ "model.visual.blocks.23.mlp.down_proj",
164
+ "model.visual.blocks.24.attn.qkv",
165
+ "model.visual.blocks.24.attn.proj",
166
+ "model.visual.blocks.24.mlp.gate_proj",
167
+ "model.visual.blocks.24.mlp.up_proj",
168
+ "model.visual.blocks.24.mlp.down_proj",
169
+ "model.visual.blocks.25.attn.qkv",
170
+ "model.visual.blocks.25.attn.proj",
171
+ "model.visual.blocks.25.mlp.gate_proj",
172
+ "model.visual.blocks.25.mlp.up_proj",
173
+ "model.visual.blocks.25.mlp.down_proj",
174
+ "model.visual.blocks.26.attn.qkv",
175
+ "model.visual.blocks.26.attn.proj",
176
+ "model.visual.blocks.26.mlp.gate_proj",
177
+ "model.visual.blocks.26.mlp.up_proj",
178
+ "model.visual.blocks.26.mlp.down_proj",
179
+ "model.visual.blocks.27.attn.qkv",
180
+ "model.visual.blocks.27.attn.proj",
181
+ "model.visual.blocks.27.mlp.gate_proj",
182
+ "model.visual.blocks.27.mlp.up_proj",
183
+ "model.visual.blocks.27.mlp.down_proj",
184
+ "model.visual.blocks.28.attn.qkv",
185
+ "model.visual.blocks.28.attn.proj",
186
+ "model.visual.blocks.28.mlp.gate_proj",
187
+ "model.visual.blocks.28.mlp.up_proj",
188
+ "model.visual.blocks.28.mlp.down_proj",
189
+ "model.visual.blocks.29.attn.qkv",
190
+ "model.visual.blocks.29.attn.proj",
191
+ "model.visual.blocks.29.mlp.gate_proj",
192
+ "model.visual.blocks.29.mlp.up_proj",
193
+ "model.visual.blocks.29.mlp.down_proj",
194
+ "model.visual.blocks.30.attn.qkv",
195
+ "model.visual.blocks.30.attn.proj",
196
+ "model.visual.blocks.30.mlp.gate_proj",
197
+ "model.visual.blocks.30.mlp.up_proj",
198
+ "model.visual.blocks.30.mlp.down_proj",
199
+ "model.visual.blocks.31.attn.qkv",
200
+ "model.visual.blocks.31.attn.proj",
201
+ "model.visual.blocks.31.mlp.gate_proj",
202
+ "model.visual.blocks.31.mlp.up_proj",
203
+ "model.visual.blocks.31.mlp.down_proj",
204
+ "model.visual.merger.mlp.0",
205
+ "model.visual.merger.mlp.2",
206
+ "lm_head"
207
+ ],
208
+ "kv_cache_scheme": null,
209
+ "quant_method": "compressed-tensors",
210
+ "quantization_status": "compressed"
211
+ },
212
+ "rms_norm_eps": 1e-06,
213
+ "rope_scaling": {
214
+ "mrope_section": [
215
+ 16,
216
+ 24,
217
+ 24
218
+ ],
219
+ "rope_type": "default",
220
+ "type": "default"
221
+ },
222
+ "rope_theta": 1000000.0,
223
+ "sliding_window": 32768,
224
+ "text_config": {
225
+ "architectures": [
226
+ "Qwen2_5_VLForConditionalGeneration"
227
+ ],
228
+ "attention_dropout": 0.0,
229
+ "bos_token_id": 151643,
230
+ "eos_token_id": 151645,
231
+ "hidden_act": "silu",
232
+ "hidden_size": 2048,
233
+ "image_token_id": null,
234
+ "initializer_range": 0.02,
235
+ "intermediate_size": 11008,
236
+ "max_position_embeddings": 128000,
237
+ "max_window_layers": 70,
238
+ "model_type": "qwen2_5_vl_text",
239
+ "num_attention_heads": 16,
240
+ "num_hidden_layers": 36,
241
+ "num_key_value_heads": 2,
242
+ "rms_norm_eps": 1e-06,
243
+ "rope_scaling": {
244
+ "mrope_section": [
245
+ 16,
246
+ 24,
247
+ 24
248
+ ],
249
+ "rope_type": "default",
250
+ "type": "default"
251
+ },
252
+ "rope_theta": 1000000.0,
253
+ "sliding_window": 32768,
254
+ "tie_word_embeddings": true,
255
+ "torch_dtype": "bfloat16",
256
+ "use_cache": true,
257
+ "use_sliding_window": false,
258
+ "video_token_id": null,
259
+ "vision_end_token_id": 151653,
260
+ "vision_start_token_id": 151652,
261
+ "vision_token_id": 151654,
262
+ "vocab_size": 151936
263
+ },
264
+ "torch_dtype": "bfloat16",
265
+ "transformers_version": "4.52.4",
266
+ "use_cache": true,
267
+ "use_sliding_window": false,
268
+ "video_token_id": 151656,
269
+ "vision_config": {
270
+ "depth": 32,
271
+ "fullatt_block_indexes": [
272
+ 7,
273
+ 15,
274
+ 23,
275
+ 31
276
+ ],
277
+ "hidden_act": "silu",
278
+ "hidden_size": 1280,
279
+ "in_channels": 3,
280
+ "in_chans": 3,
281
+ "initializer_range": 0.02,
282
+ "intermediate_size": 3420,
283
+ "model_type": "qwen2_5_vl",
284
+ "num_heads": 16,
285
+ "out_hidden_size": 2048,
286
+ "patch_size": 14,
287
+ "spatial_merge_size": 2,
288
+ "spatial_patch_size": 14,
289
+ "temporal_patch_size": 2,
290
+ "tokens_per_second": 2,
291
+ "torch_dtype": "bfloat16",
292
+ "window_size": 112
293
+ },
294
+ "vision_end_token_id": 151653,
295
+ "vision_start_token_id": 151652,
296
+ "vision_token_id": 151654,
297
+ "vocab_size": 151936
298
+ }
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": "4.52.4"
12
+ }
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:e9cb5163a83e8e20935d84ed6bc4d113326956b3831b19c4dc2e2a007e2dd059
3
+ size 4013282536
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": "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
+ GPTQModifier:
4
+ targets: [Linear]
5
+ ignore: [lm_head, 're:visual.*', 're:model.visual.*']
6
+ scheme: W4A16
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:f65d6b9edd97a2ce5a226c36f3b22ef8adba66248044d297fc284589c29f6ba6
3
+ size 11421996
tokenizer_config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "padding_side": "left",
205
+ "processor_class": "Qwen2_5_VLProcessor",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_kwargs_names": [
3
+ "do_convert_rgb",
4
+ "do_resize",
5
+ "size",
6
+ "size_divisor",
7
+ "default_to_square",
8
+ "resample",
9
+ "do_rescale",
10
+ "rescale_factor",
11
+ "do_normalize",
12
+ "image_mean",
13
+ "image_std",
14
+ "do_pad",
15
+ "do_center_crop",
16
+ "crop_size",
17
+ "data_format",
18
+ "input_data_format",
19
+ "device",
20
+ "min_pixels",
21
+ "max_pixels",
22
+ "patch_size",
23
+ "temporal_patch_size",
24
+ "merge_size"
25
+ ],
26
+ "crop_size": null,
27
+ "data_format": "channels_first",
28
+ "default_to_square": true,
29
+ "device": null,
30
+ "do_center_crop": null,
31
+ "do_convert_rgb": true,
32
+ "do_normalize": true,
33
+ "do_pad": null,
34
+ "do_rescale": true,
35
+ "do_resize": true,
36
+ "image_mean": [
37
+ 0.48145466,
38
+ 0.4578275,
39
+ 0.40821073
40
+ ],
41
+ "image_processor_type": "Qwen2VLImageProcessor",
42
+ "image_std": [
43
+ 0.26862954,
44
+ 0.26130258,
45
+ 0.27577711
46
+ ],
47
+ "input_data_format": null,
48
+ "max_pixels": 12845056,
49
+ "merge_size": 2,
50
+ "min_pixels": 3136,
51
+ "model_valid_processing_keys": [
52
+ "do_convert_rgb",
53
+ "do_resize",
54
+ "size",
55
+ "size_divisor",
56
+ "default_to_square",
57
+ "resample",
58
+ "do_rescale",
59
+ "rescale_factor",
60
+ "do_normalize",
61
+ "image_mean",
62
+ "image_std",
63
+ "do_pad",
64
+ "do_center_crop",
65
+ "crop_size",
66
+ "data_format",
67
+ "input_data_format",
68
+ "device",
69
+ "min_pixels",
70
+ "max_pixels",
71
+ "patch_size",
72
+ "temporal_patch_size",
73
+ "merge_size"
74
+ ],
75
+ "patch_size": 14,
76
+ "processor_class": "Qwen2_5_VLProcessor",
77
+ "resample": 3,
78
+ "rescale_factor": 0.00392156862745098,
79
+ "size": {
80
+ "longest_edge": 12845056,
81
+ "shortest_edge": 3136
82
+ },
83
+ "size_divisor": null,
84
+ "temporal_patch_size": 2,
85
+ "video_processor_type": "Qwen2VLVideoProcessor"
86
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff