Hugging Face's logo

iiiiii123
/
AVBench_model

Transformers
Safetensors
English
Chinese
avbench
audio-text
video-text
audio-video
Model card Files
xet
 Community
iiiiii123 commited on
Commit
895a753
·
verified ·
1 Parent(s): 1cc7803

Upload Qwen2.5-Omni-7B-VideoTextMatching-Merged

Browse files
Files changed (18) hide show
  1. .gitattributes +1 -0
  2. Qwen2.5-Omni-7B-VideoTextMatching-Merged/added_tokens.json +24 -0
  3. Qwen2.5-Omni-7B-VideoTextMatching-Merged/chat_template.jinja +7 -0
  4. Qwen2.5-Omni-7B-VideoTextMatching-Merged/config.json +627 -0
  5. Qwen2.5-Omni-7B-VideoTextMatching-Merged/generation_config.json +4 -0
  6. Qwen2.5-Omni-7B-VideoTextMatching-Merged/merges.txt +0 -0
  7. Qwen2.5-Omni-7B-VideoTextMatching-Merged/model-00001-of-00004.safetensors +3 -0
  8. Qwen2.5-Omni-7B-VideoTextMatching-Merged/model-00002-of-00004.safetensors +3 -0
  9. Qwen2.5-Omni-7B-VideoTextMatching-Merged/model-00003-of-00004.safetensors +3 -0
  10. Qwen2.5-Omni-7B-VideoTextMatching-Merged/model-00004-of-00004.safetensors +3 -0
  11. Qwen2.5-Omni-7B-VideoTextMatching-Merged/model.safetensors.index.json +0 -0
  12. Qwen2.5-Omni-7B-VideoTextMatching-Merged/preprocessor_config.json +31 -0
  13. Qwen2.5-Omni-7B-VideoTextMatching-Merged/special_tokens_map.json +38 -0
  14. Qwen2.5-Omni-7B-VideoTextMatching-Merged/spk_dict.pt +3 -0
  15. Qwen2.5-Omni-7B-VideoTextMatching-Merged/tokenizer.json +3 -0
  16. Qwen2.5-Omni-7B-VideoTextMatching-Merged/tokenizer_config.json +223 -0
  17. Qwen2.5-Omni-7B-VideoTextMatching-Merged/video_preprocessor_config.json +55 -0
  18. Qwen2.5-Omni-7B-VideoTextMatching-Merged/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
+ Qwen2.5-Omni-7B-VideoTextMatching-Merged/tokenizer.json filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Omni-7B-VideoTextMatching-Merged/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|AUDIO|>": 151646,
5
+ "<|IMAGE|>": 151655,
6
+ "<|VIDEO|>": 151656,
7
+ "<|audio_bos|>": 151647,
8
+ "<|audio_eos|>": 151648,
9
+ "<|box_end|>": 151649,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|quad_end|>": 151651,
19
+ "<|quad_start|>": 151650,
20
+ "<|repo_name|>": 151663,
21
+ "<|vision_bos|>": 151652,
22
+ "<|vision_eos|>": 151653,
23
+ "<|vision_pad|>": 151654
24
+ }
Qwen2.5-Omni-7B-VideoTextMatching-Merged/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set audio_count = namespace(value=0) %}{% 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_bos|><|IMAGE|><|vision_eos|>{% elif content['type'] == 'audio' or 'audio' in content or 'audio_url' in content %}{% set audio_count.value = audio_count.value + 1 %}{% if add_audio_id %}Audio {{ audio_count.value }}: {% endif %}<|audio_bos|><|AUDIO|><|audio_eos|>{% 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_bos|><|VIDEO|><|vision_eos|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
Qwen2.5-Omni-7B-VideoTextMatching-Merged/config.json ADDED
@@ -0,0 +1,627 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5OmniForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "enable_audio_output": false,
7
+ "enable_talker": false,
8
+ "model_type": "qwen2_5_omni",
9
+ "talker_config": {
10
+ "_attn_implementation_autoset": true,
11
+ "_name_or_path": "Qwen2.5-Omni-7B/talker",
12
+ "architectures": [
13
+ "Qwen2OmniTalkerForConditionalGeneration"
14
+ ],
15
+ "attention_dropout": 0.0,
16
+ "audio_end_token_id": 151648,
17
+ "audio_start_token_id": 151647,
18
+ "audio_token_index": 151646,
19
+ "dtype": "bfloat16",
20
+ "embedding_size": 3584,
21
+ "head_dim": 128,
22
+ "hidden_act": "silu",
23
+ "hidden_size": 896,
24
+ "image_token_index": 151655,
25
+ "init_std": 0.02,
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 18944,
28
+ "layer_types": [
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention"
53
+ ],
54
+ "max_position_embeddings": 32768,
55
+ "max_window_layers": 28,
56
+ "model_type": "qwen2_5_omni_talker",
57
+ "num_attention_heads": 12,
58
+ "num_hidden_layers": 24,
59
+ "num_key_value_heads": 4,
60
+ "position_id_per_seconds": 25,
61
+ "rms_norm_eps": 1e-06,
62
+ "rope_scaling": {
63
+ "mrope_section": [
64
+ 16,
65
+ 24,
66
+ 24
67
+ ],
68
+ "rope_type": "default",
69
+ "type": "default"
70
+ },
71
+ "rope_theta": 1000000.0,
72
+ "seconds_per_chunk": 2,
73
+ "sliding_window": null,
74
+ "spatial_merge_size": 2,
75
+ "tts_codec_end_token_id": 8294,
76
+ "tts_codec_mask_token_id": 8296,
77
+ "tts_codec_pad_token_id": 8292,
78
+ "tts_codec_start_token_id": 8293,
79
+ "tts_text_end_token_id": 151861,
80
+ "tts_text_pad_token_id": 151859,
81
+ "tts_text_start_token_id": 151860,
82
+ "use_cache": true,
83
+ "use_sliding_window": false,
84
+ "video_token_index": 151656,
85
+ "vision_end_token_id": 151653,
86
+ "vision_start_token_id": 151652,
87
+ "vocab_size": 8448
88
+ },
89
+ "thinker_config": {
90
+ "_attn_implementation_autoset": true,
91
+ "_name_or_path": "Qwen2.5-Omni-7B/thinker",
92
+ "architectures": [
93
+ "Qwen2OmniNaViTThinkerForConditionalGeneration"
94
+ ],
95
+ "audio_config": {
96
+ "_attn_implementation_autoset": true,
97
+ "_name_or_path": "",
98
+ "activation_dropout": 0.0,
99
+ "activation_function": "gelu",
100
+ "add_cross_attention": false,
101
+ "architectures": null,
102
+ "attention_dropout": 0.0,
103
+ "bad_words_ids": null,
104
+ "begin_suppress_tokens": null,
105
+ "bos_token_id": null,
106
+ "chunk_size_feed_forward": 0,
107
+ "cross_attention_hidden_size": null,
108
+ "d_model": 1280,
109
+ "decoder_start_token_id": null,
110
+ "diversity_penalty": 0.0,
111
+ "do_sample": false,
112
+ "dropout": 0.0,
113
+ "dtype": null,
114
+ "early_stopping": false,
115
+ "encoder_attention_heads": 20,
116
+ "encoder_ffn_dim": 5120,
117
+ "encoder_layerdrop": 0.0,
118
+ "encoder_layers": 32,
119
+ "encoder_no_repeat_ngram_size": 0,
120
+ "eos_token_id": null,
121
+ "exponential_decay_length_penalty": null,
122
+ "finetuning_task": null,
123
+ "forced_bos_token_id": null,
124
+ "forced_eos_token_id": null,
125
+ "id2label": {
126
+ "0": "LABEL_0",
127
+ "1": "LABEL_1"
128
+ },
129
+ "init_std": 0.02,
130
+ "initializer_range": 0.02,
131
+ "is_decoder": false,
132
+ "is_encoder_decoder": false,
133
+ "label2id": {
134
+ "LABEL_0": 0,
135
+ "LABEL_1": 1
136
+ },
137
+ "length_penalty": 1.0,
138
+ "max_length": 20,
139
+ "max_source_positions": 1500,
140
+ "min_length": 0,
141
+ "model_type": "qwen2_5_omni_audio_encoder",
142
+ "n_window": 100,
143
+ "no_repeat_ngram_size": 0,
144
+ "num_beam_groups": 1,
145
+ "num_beams": 1,
146
+ "num_hidden_layers": 32,
147
+ "num_mel_bins": 128,
148
+ "num_return_sequences": 1,
149
+ "output_attentions": false,
150
+ "output_dim": 3584,
151
+ "output_hidden_states": false,
152
+ "output_scores": false,
153
+ "pad_token_id": null,
154
+ "prefix": null,
155
+ "problem_type": null,
156
+ "pruned_heads": {},
157
+ "remove_invalid_values": false,
158
+ "repetition_penalty": 1.0,
159
+ "return_dict": true,
160
+ "return_dict_in_generate": false,
161
+ "scale_embedding": false,
162
+ "sep_token_id": null,
163
+ "suppress_tokens": null,
164
+ "task_specific_params": null,
165
+ "temperature": 1.0,
166
+ "tf_legacy_loss": false,
167
+ "tie_encoder_decoder": false,
168
+ "tie_word_embeddings": true,
169
+ "tokenizer_class": null,
170
+ "top_k": 50,
171
+ "top_p": 1.0,
172
+ "torchscript": false,
173
+ "typical_p": 1.0,
174
+ "use_bfloat16": false
175
+ },
176
+ "audio_end_token_id": 151648,
177
+ "audio_start_token_id": 151647,
178
+ "audio_token_index": 151646,
179
+ "bos_token_id": 151644,
180
+ "dtype": "bfloat16",
181
+ "eos_token_id": 151645,
182
+ "ignore_index": -100,
183
+ "image_token_index": 151655,
184
+ "init_std": 0.02,
185
+ "initializer_range": 0.02,
186
+ "model_type": "qwen2_5_omni_thinker",
187
+ "pad_token_id": 151643,
188
+ "position_id_per_seconds": 25,
189
+ "seconds_per_chunk": 2,
190
+ "text_config": {
191
+ "_name_or_path": "",
192
+ "add_cross_attention": false,
193
+ "architectures": null,
194
+ "attention_dropout": 0.0,
195
+ "bad_words_ids": null,
196
+ "begin_suppress_tokens": null,
197
+ "bos_token_id": null,
198
+ "chunk_size_feed_forward": 0,
199
+ "cross_attention_hidden_size": null,
200
+ "decoder_start_token_id": null,
201
+ "diversity_penalty": 0.0,
202
+ "do_sample": false,
203
+ "dtype": null,
204
+ "early_stopping": false,
205
+ "encoder_no_repeat_ngram_size": 0,
206
+ "eos_token_id": null,
207
+ "exponential_decay_length_penalty": null,
208
+ "finetuning_task": null,
209
+ "forced_bos_token_id": null,
210
+ "forced_eos_token_id": null,
211
+ "hidden_act": "silu",
212
+ "hidden_size": 3584,
213
+ "id2label": {
214
+ "0": "LABEL_0",
215
+ "1": "LABEL_1"
216
+ },
217
+ "init_std": 0.02,
218
+ "initializer_range": 0.02,
219
+ "intermediate_size": 18944,
220
+ "is_decoder": false,
221
+ "is_encoder_decoder": false,
222
+ "label2id": {
223
+ "LABEL_0": 0,
224
+ "LABEL_1": 1
225
+ },
226
+ "layer_types": [
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
+ "full_attention",
245
+ "full_attention",
246
+ "full_attention",
247
+ "full_attention",
248
+ "full_attention",
249
+ "full_attention",
250
+ "full_attention",
251
+ "full_attention",
252
+ "full_attention",
253
+ "full_attention",
254
+ "full_attention"
255
+ ],
256
+ "length_penalty": 1.0,
257
+ "max_length": 20,
258
+ "max_position_embeddings": 32768,
259
+ "max_window_layers": 28,
260
+ "min_length": 0,
261
+ "model_type": "qwen2_5_omni_text",
262
+ "no_repeat_ngram_size": 0,
263
+ "num_attention_heads": 28,
264
+ "num_beam_groups": 1,
265
+ "num_beams": 1,
266
+ "num_hidden_layers": 28,
267
+ "num_key_value_heads": 4,
268
+ "num_return_sequences": 1,
269
+ "output_attentions": false,
270
+ "output_hidden_states": false,
271
+ "output_scores": false,
272
+ "pad_token_id": null,
273
+ "prefix": null,
274
+ "problem_type": null,
275
+ "pruned_heads": {},
276
+ "remove_invalid_values": false,
277
+ "repetition_penalty": 1.0,
278
+ "return_dict": true,
279
+ "return_dict_in_generate": false,
280
+ "rms_norm_eps": 1e-06,
281
+ "rope_scaling": {
282
+ "mrope_section": [
283
+ 16,
284
+ 24,
285
+ 24
286
+ ],
287
+ "rope_type": "default",
288
+ "type": "default"
289
+ },
290
+ "rope_theta": 1000000.0,
291
+ "sep_token_id": null,
292
+ "sliding_window": null,
293
+ "suppress_tokens": null,
294
+ "task_specific_params": null,
295
+ "temperature": 1.0,
296
+ "tf_legacy_loss": false,
297
+ "tie_encoder_decoder": false,
298
+ "tie_word_embeddings": false,
299
+ "tokenizer_class": null,
300
+ "top_k": 50,
301
+ "top_p": 1.0,
302
+ "torchscript": false,
303
+ "typical_p": 1.0,
304
+ "use_bfloat16": false,
305
+ "use_cache": true,
306
+ "use_sliding_window": false,
307
+ "vocab_size": 152064
308
+ },
309
+ "user_token_id": 872,
310
+ "video_token_index": 151656,
311
+ "vision_config": {
312
+ "_attn_implementation_autoset": true,
313
+ "_name_or_path": "",
314
+ "add_cross_attention": false,
315
+ "architectures": null,
316
+ "bad_words_ids": null,
317
+ "begin_suppress_tokens": null,
318
+ "bos_token_id": null,
319
+ "chunk_size_feed_forward": 0,
320
+ "cross_attention_hidden_size": null,
321
+ "decoder_start_token_id": null,
322
+ "depth": 32,
323
+ "diversity_penalty": 0.0,
324
+ "do_sample": false,
325
+ "dtype": null,
326
+ "early_stopping": false,
327
+ "embed_dim": 1280,
328
+ "encoder_no_repeat_ngram_size": 0,
329
+ "eos_token_id": null,
330
+ "exponential_decay_length_penalty": null,
331
+ "finetuning_task": null,
332
+ "forced_bos_token_id": null,
333
+ "forced_eos_token_id": null,
334
+ "fullatt_block_indexes": [
335
+ 7,
336
+ 15,
337
+ 23,
338
+ 31
339
+ ],
340
+ "hidden_act": "silu",
341
+ "hidden_size": 1280,
342
+ "id2label": {
343
+ "0": "LABEL_0",
344
+ "1": "LABEL_1"
345
+ },
346
+ "in_channels": 3,
347
+ "in_chans": 3,
348
+ "init_std": 0.02,
349
+ "initializer_range": 0.02,
350
+ "intermediate_size": 3420,
351
+ "is_decoder": false,
352
+ "is_encoder_decoder": false,
353
+ "label2id": {
354
+ "LABEL_0": 0,
355
+ "LABEL_1": 1
356
+ },
357
+ "length_penalty": 1.0,
358
+ "max_length": 20,
359
+ "min_length": 0,
360
+ "model_type": "qwen2_5_omni_vision_encoder",
361
+ "no_repeat_ngram_size": 0,
362
+ "num_beam_groups": 1,
363
+ "num_beams": 1,
364
+ "num_heads": 16,
365
+ "num_return_sequences": 1,
366
+ "out_hidden_size": 3584,
367
+ "output_attentions": false,
368
+ "output_hidden_states": false,
369
+ "output_scores": false,
370
+ "pad_token_id": null,
371
+ "patch_size": 14,
372
+ "prefix": null,
373
+ "problem_type": null,
374
+ "pruned_heads": {},
375
+ "remove_invalid_values": false,
376
+ "repetition_penalty": 1.0,
377
+ "return_dict": true,
378
+ "return_dict_in_generate": false,
379
+ "sep_token_id": null,
380
+ "spatial_merge_size": 2,
381
+ "spatial_patch_size": 14,
382
+ "suppress_tokens": null,
383
+ "task_specific_params": null,
384
+ "temperature": 1.0,
385
+ "temporal_patch_size": 2,
386
+ "tf_legacy_loss": false,
387
+ "tie_encoder_decoder": false,
388
+ "tie_word_embeddings": true,
389
+ "tokenizer_class": null,
390
+ "tokens_per_second": 25,
391
+ "top_k": 50,
392
+ "top_p": 1.0,
393
+ "torchscript": false,
394
+ "typical_p": 1.0,
395
+ "use_bfloat16": false,
396
+ "window_size": 112
397
+ },
398
+ "vision_end_token_id": 151653,
399
+ "vision_start_token_id": 151652,
400
+ "vision_token_id": 151654
401
+ },
402
+ "token2wav_config": {
403
+ "_attn_implementation_autoset": true,
404
+ "bigvgan_config": {
405
+ "_attn_implementation_autoset": true,
406
+ "_name_or_path": "",
407
+ "add_cross_attention": false,
408
+ "architectures": null,
409
+ "bad_words_ids": null,
410
+ "begin_suppress_tokens": null,
411
+ "bos_token_id": null,
412
+ "chunk_size_feed_forward": 0,
413
+ "cross_attention_hidden_size": null,
414
+ "decoder_start_token_id": null,
415
+ "diversity_penalty": 0.0,
416
+ "do_sample": false,
417
+ "dtype": null,
418
+ "early_stopping": false,
419
+ "encoder_no_repeat_ngram_size": 0,
420
+ "eos_token_id": null,
421
+ "exponential_decay_length_penalty": null,
422
+ "finetuning_task": null,
423
+ "forced_bos_token_id": null,
424
+ "forced_eos_token_id": null,
425
+ "id2label": {
426
+ "0": "LABEL_0",
427
+ "1": "LABEL_1"
428
+ },
429
+ "is_decoder": false,
430
+ "is_encoder_decoder": false,
431
+ "label2id": {
432
+ "LABEL_0": 0,
433
+ "LABEL_1": 1
434
+ },
435
+ "length_penalty": 1.0,
436
+ "max_length": 20,
437
+ "mel_dim": 80,
438
+ "min_length": 0,
439
+ "model_type": "qwen2_5_omni_bigvgan",
440
+ "no_repeat_ngram_size": 0,
441
+ "num_beam_groups": 1,
442
+ "num_beams": 1,
443
+ "num_return_sequences": 1,
444
+ "output_attentions": false,
445
+ "output_hidden_states": false,
446
+ "output_scores": false,
447
+ "pad_token_id": null,
448
+ "prefix": null,
449
+ "problem_type": null,
450
+ "pruned_heads": {},
451
+ "remove_invalid_values": false,
452
+ "repetition_penalty": 1.0,
453
+ "resblock_dilation_sizes": [
454
+ [
455
+ 1,
456
+ 3,
457
+ 5
458
+ ],
459
+ [
460
+ 1,
461
+ 3,
462
+ 5
463
+ ],
464
+ [
465
+ 1,
466
+ 3,
467
+ 5
468
+ ]
469
+ ],
470
+ "resblock_kernel_sizes": [
471
+ 3,
472
+ 7,
473
+ 11
474
+ ],
475
+ "return_dict": true,
476
+ "return_dict_in_generate": false,
477
+ "sep_token_id": null,
478
+ "suppress_tokens": null,
479
+ "task_specific_params": null,
480
+ "temperature": 1.0,
481
+ "tf_legacy_loss": false,
482
+ "tie_encoder_decoder": false,
483
+ "tie_word_embeddings": true,
484
+ "tokenizer_class": null,
485
+ "top_k": 50,
486
+ "top_p": 1.0,
487
+ "torchscript": false,
488
+ "typical_p": 1.0,
489
+ "upsample_initial_channel": 1536,
490
+ "upsample_kernel_sizes": [
491
+ 11,
492
+ 7,
493
+ 4,
494
+ 4,
495
+ 4,
496
+ 4
497
+ ],
498
+ "upsample_rates": [
499
+ 5,
500
+ 3,
501
+ 2,
502
+ 2,
503
+ 2,
504
+ 2
505
+ ],
506
+ "use_bfloat16": false,
507
+ "use_bias_at_final": false
508
+ },
509
+ "dit_config": {
510
+ "_attn_implementation_autoset": true,
511
+ "_name_or_path": "",
512
+ "add_cross_attention": false,
513
+ "architectures": null,
514
+ "bad_words_ids": null,
515
+ "begin_suppress_tokens": null,
516
+ "block_size": 24,
517
+ "bos_token_id": null,
518
+ "chunk_size_feed_forward": 0,
519
+ "cross_attention_hidden_size": null,
520
+ "decoder_start_token_id": null,
521
+ "depth": 22,
522
+ "dim": 1024,
523
+ "diversity_penalty": 0.0,
524
+ "do_sample": false,
525
+ "dropout": 0.1,
526
+ "dtype": "float32",
527
+ "early_stopping": false,
528
+ "emb_dim": 512,
529
+ "enc_attention_channels": 64,
530
+ "enc_channels": [
531
+ 256,
532
+ 256,
533
+ 256,
534
+ 256,
535
+ 768
536
+ ],
537
+ "enc_dilations": [
538
+ 1,
539
+ 2,
540
+ 3,
541
+ 4,
542
+ 1
543
+ ],
544
+ "enc_dim": 128,
545
+ "enc_emb_dim": 192,
546
+ "enc_global_context": true,
547
+ "enc_kernel_sizes": [
548
+ 5,
549
+ 3,
550
+ 3,
551
+ 3,
552
+ 1
553
+ ],
554
+ "enc_lin_neurons": 192,
555
+ "enc_res2net_scale": 2,
556
+ "enc_se_channels": 64,
557
+ "encoder_no_repeat_ngram_size": 0,
558
+ "eos_token_id": null,
559
+ "exponential_decay_length_penalty": null,
560
+ "ff_mult": 2,
561
+ "finetuning_task": null,
562
+ "forced_bos_token_id": null,
563
+ "forced_eos_token_id": null,
564
+ "head_dim": 64,
565
+ "heads": 16,
566
+ "hidden_size": 1024,
567
+ "id2label": {
568
+ "0": "LABEL_0",
569
+ "1": "LABEL_1"
570
+ },
571
+ "is_decoder": false,
572
+ "is_encoder_decoder": false,
573
+ "label2id": {
574
+ "LABEL_0": 0,
575
+ "LABEL_1": 1
576
+ },
577
+ "length_penalty": 1.0,
578
+ "look_ahead_layers": [
579
+ 10
580
+ ],
581
+ "look_backward_layers": [
582
+ 0,
583
+ 20
584
+ ],
585
+ "max_length": 20,
586
+ "max_position_embeddings": 32768,
587
+ "mel_dim": 80,
588
+ "min_length": 0,
589
+ "model_type": "qwen2_5_omni_dit",
590
+ "no_repeat_ngram_size": 0,
591
+ "num_attention_heads": 16,
592
+ "num_beam_groups": 1,
593
+ "num_beams": 1,
594
+ "num_embeds": 8193,
595
+ "num_hidden_layers": 22,
596
+ "num_return_sequences": 1,
597
+ "output_attentions": false,
598
+ "output_hidden_states": false,
599
+ "output_scores": false,
600
+ "pad_token_id": null,
601
+ "prefix": null,
602
+ "problem_type": null,
603
+ "pruned_heads": {},
604
+ "remove_invalid_values": false,
605
+ "repeats": 2,
606
+ "repetition_penalty": 1.0,
607
+ "return_dict": true,
608
+ "return_dict_in_generate": false,
609
+ "rope_theta": 10000.0,
610
+ "sep_token_id": null,
611
+ "suppress_tokens": null,
612
+ "task_specific_params": null,
613
+ "temperature": 1.0,
614
+ "tf_legacy_loss": false,
615
+ "tie_encoder_decoder": false,
616
+ "tie_word_embeddings": true,
617
+ "tokenizer_class": null,
618
+ "top_k": 50,
619
+ "top_p": 1.0,
620
+ "torchscript": false,
621
+ "typical_p": 1.0,
622
+ "use_bfloat16": false
623
+ },
624
+ "model_type": "qwen2_5_omni_token2wav"
625
+ },
626
+ "transformers_version": "4.57.1"
627
+ }
Qwen2.5-Omni-7B-VideoTextMatching-Merged/generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.57.1"
4
+ }
Qwen2.5-Omni-7B-VideoTextMatching-Merged/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
Qwen2.5-Omni-7B-VideoTextMatching-Merged/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de8a95fcdcdb99f497caa1778d330a0e1e0c4116d22f0c230198927129c123d1
3
+ size 4985055536
Qwen2.5-Omni-7B-VideoTextMatching-Merged/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28924f6a79660a5132bc2ca6b82f5b3e7733baaf603978d332de2541c463cc7b
3
+ size 4991496832
Qwen2.5-Omni-7B-VideoTextMatching-Merged/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb46ec6391225db6121316d9ec53c3dc4ddd9245b883cbf3a514f87a574a7ad1
3
+ size 4991496936
Qwen2.5-Omni-7B-VideoTextMatching-Merged/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c64f57d7a38746932ae2deaa963bf177040cf8544e2b86ae4465ea4bf881d12
3
+ size 2895740064
Qwen2.5-Omni-7B-VideoTextMatching-Merged/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
Qwen2.5-Omni-7B-VideoTextMatching-Merged/preprocessor_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 300,
3
+ "dither": 0.0,
4
+ "feature_extractor_type": "WhisperFeatureExtractor",
5
+ "feature_size": 128,
6
+ "hop_length": 160,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_processor_type": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.26862954,
15
+ 0.26130258,
16
+ 0.27577711
17
+ ],
18
+ "max_pixels": 12845056,
19
+ "merge_size": 2,
20
+ "min_pixels": 3136,
21
+ "n_fft": 400,
22
+ "n_samples": 4800000,
23
+ "nb_max_frames": 30000,
24
+ "padding_side": "right",
25
+ "padding_value": 0.0,
26
+ "patch_size": 14,
27
+ "processor_class": "Qwen2_5OmniProcessor",
28
+ "return_attention_mask": true,
29
+ "sampling_rate": 16000,
30
+ "temporal_patch_size": 2
31
+ }
Qwen2.5-Omni-7B-VideoTextMatching-Merged/special_tokens_map.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|AUDIO|>",
6
+ "<|audio_bos|>",
7
+ "<|audio_eos|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_bos|>",
12
+ "<|vision_eos|>",
13
+ "<|vision_pad|>",
14
+ "<|IMAGE|>",
15
+ "<|VIDEO|>"
16
+ ],
17
+ "audio_bos_token": "<|audio_bos|>",
18
+ "audio_eos_token": "<|audio_eos|>",
19
+ "audio_token": "<|AUDIO|>",
20
+ "eos_token": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "image_token": "<|IMAGE|>",
28
+ "pad_token": {
29
+ "content": "<|endoftext|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "video_token": "<|VIDEO|>",
36
+ "vision_bos_token": "<|vision_bos|>",
37
+ "vision_eos_token": "<|vision_eos|>"
38
+ }
Qwen2.5-Omni-7B-VideoTextMatching-Merged/spk_dict.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a05609b28f5d42b7b748f0f07592545c8f1f6885b9ae8fff64baf56e86b2a18
3
+ size 259544
Qwen2.5-Omni-7B-VideoTextMatching-Merged/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8441917e39ae0244e06d704b95b3124795cec478e297f9afac39ba670d7e9d99
3
+ size 11421870
Qwen2.5-Omni-7B-VideoTextMatching-Merged/tokenizer_config.json ADDED
@@ -0,0 +1,223 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|AUDIO|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|audio_bos|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|audio_eos|>",
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_bos|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_eos|>",
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|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|VIDEO|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "151657": {
117
+ "content": "<tool_call>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "151658": {
125
+ "content": "</tool_call>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "151659": {
133
+ "content": "<|fim_prefix|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "151660": {
141
+ "content": "<|fim_middle|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "151661": {
149
+ "content": "<|fim_suffix|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "151662": {
157
+ "content": "<|fim_pad|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "151663": {
165
+ "content": "<|repo_name|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "151664": {
173
+ "content": "<|file_sep|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ }
180
+ },
181
+ "additional_special_tokens": [
182
+ "<|im_start|>",
183
+ "<|im_end|>",
184
+ "<|AUDIO|>",
185
+ "<|audio_bos|>",
186
+ "<|audio_eos|>",
187
+ "<|box_end|>",
188
+ "<|quad_start|>",
189
+ "<|quad_end|>",
190
+ "<|vision_bos|>",
191
+ "<|vision_eos|>",
192
+ "<|vision_pad|>",
193
+ "<|IMAGE|>",
194
+ "<|VIDEO|>"
195
+ ],
196
+ "audio_bos_token": "<|audio_bos|>",
197
+ "audio_eos_token": "<|audio_eos|>",
198
+ "audio_token": "<|AUDIO|>",
199
+ "bos_token": null,
200
+ "clean_up_tokenization_spaces": false,
201
+ "eos_token": "<|im_end|>",
202
+ "errors": "replace",
203
+ "extra_special_tokens": {
204
+ "audio_bos_token": "<|audio_bos|>",
205
+ "audio_eos_token": "<|audio_eos|>",
206
+ "audio_token": "<|AUDIO|>",
207
+ "image_token": "<|IMAGE|>",
208
+ "video_token": "<|VIDEO|>",
209
+ "vision_bos_token": "<|vision_bos|>",
210
+ "vision_eos_token": "<|vision_eos|>"
211
+ },
212
+ "image_token": "<|IMAGE|>",
213
+ "model_max_length": 32768,
214
+ "pad_token": "<|endoftext|>",
215
+ "padding_side": "right",
216
+ "processor_class": "Qwen2_5OmniProcessor",
217
+ "split_special_tokens": false,
218
+ "tokenizer_class": "Qwen2Tokenizer",
219
+ "unk_token": null,
220
+ "video_token": "<|VIDEO|>",
221
+ "vision_bos_token": "<|vision_bos|>",
222
+ "vision_eos_token": "<|vision_eos|>"
223
+ }
Qwen2.5-Omni-7B-VideoTextMatching-Merged/video_preprocessor_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 300,
3
+ "crop_size": null,
4
+ "data_format": "channels_first",
5
+ "default_to_square": true,
6
+ "device": null,
7
+ "dither": 0.0,
8
+ "do_center_crop": null,
9
+ "do_convert_rgb": true,
10
+ "do_normalize": true,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "do_sample_frames": false,
14
+ "feature_extractor_type": "WhisperFeatureExtractor",
15
+ "feature_size": 128,
16
+ "fps": null,
17
+ "hop_length": 160,
18
+ "image_mean": [
19
+ 0.48145466,
20
+ 0.4578275,
21
+ 0.40821073
22
+ ],
23
+ "image_std": [
24
+ 0.26862954,
25
+ 0.26130258,
26
+ 0.27577711
27
+ ],
28
+ "input_data_format": null,
29
+ "max_frames": 768,
30
+ "max_pixels": 12845056,
31
+ "merge_size": 2,
32
+ "min_frames": 4,
33
+ "min_pixels": 3136,
34
+ "n_fft": 400,
35
+ "n_samples": 4800000,
36
+ "nb_max_frames": 30000,
37
+ "num_frames": null,
38
+ "pad_size": null,
39
+ "padding_side": "right",
40
+ "padding_value": 0.0,
41
+ "patch_size": 14,
42
+ "processor_class": "Qwen2_5OmniProcessor",
43
+ "resample": 3,
44
+ "rescale_factor": 0.00392156862745098,
45
+ "return_attention_mask": true,
46
+ "return_metadata": false,
47
+ "sampling_rate": 16000,
48
+ "size": {
49
+ "longest_edge": 12845056,
50
+ "shortest_edge": 3136
51
+ },
52
+ "temporal_patch_size": 2,
53
+ "video_metadata": null,
54
+ "video_processor_type": "Qwen2VLVideoProcessor"
55
+ }
Qwen2.5-Omni-7B-VideoTextMatching-Merged/vocab.json ADDED
The diff for this file is too large to render. See raw diff