giangndm commited on
Commit
c097d66
·
verified ·
1 Parent(s): 2780881

Add files using upload-large-folder tool

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
README.md ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: apache-2.0
4
+ license_link: https://huggingface.co/Qwen/Qwen2.5-Omni-7B/blob/main/LICENSE
5
+ language:
6
+ - en
7
+ tags:
8
+ - multimodal
9
+ - mlx
10
+ library_name: mlx
11
+ pipeline_tag: text-generation
12
+ base_model: Qwen/Qwen2.5-Omni-7B
13
+ ---
14
+
15
+ # giangndm/qwen2.5-omni-7b-mlx
16
+
17
+ This model [giangndm/qwen2.5-omni-7b-mlx](https://huggingface.co/giangndm/qwen2.5-omni-7b-mlx) was
18
+ converted to MLX format from [Qwen/Qwen2.5-Omni-7B](https://huggingface.co/Qwen/Qwen2.5-Omni-7B)
19
+ using mlx-lm version **0.24.0**.
20
+
21
+ ## Use with mlx
22
+
23
+ ```bash
24
+ pip install mlx-lm
25
+ ```
26
+
27
+ ```python
28
+ from mlx_lm import load, generate
29
+
30
+ model, tokenizer = load("giangndm/qwen2.5-omni-7b-mlx")
31
+
32
+ prompt = "hello"
33
+
34
+ if tokenizer.chat_template is not None:
35
+ messages = [{"role": "user", "content": prompt}]
36
+ prompt = tokenizer.apply_chat_template(
37
+ messages, add_generation_prompt=True
38
+ )
39
+
40
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
41
+ ```
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
+ }
config.json ADDED
@@ -0,0 +1,499 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5OmniModel"
4
+ ],
5
+ "enable_audio_output": true,
6
+ "enable_talker": true,
7
+ "model_type": "qwen2_5_omni",
8
+ "quantization": {
9
+ "group_size": 64,
10
+ "bits": 4
11
+ },
12
+ "talker_config": {
13
+ "_attn_implementation_autoset": true,
14
+ "_name_or_path": "Qwen2.5-Omni-7B/talker",
15
+ "architectures": [
16
+ "Qwen2OmniTalkerForConditionalGeneration"
17
+ ],
18
+ "attention_dropout": 0.0,
19
+ "audio_end_token_id": 151648,
20
+ "audio_start_token_id": 151647,
21
+ "audio_token_index": 151646,
22
+ "embedding_size": 3584,
23
+ "head_dim": 128,
24
+ "hidden_act": "silu",
25
+ "hidden_size": 896,
26
+ "image_token_index": 151655,
27
+ "init_std": 0.02,
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 18944,
30
+ "max_position_embeddings": 32768,
31
+ "max_window_layers": 28,
32
+ "model_type": "qwen2_5_omni_talker",
33
+ "num_attention_heads": 12,
34
+ "num_hidden_layers": 24,
35
+ "num_key_value_heads": 4,
36
+ "position_id_per_seconds": 25,
37
+ "rms_norm_eps": 1e-06,
38
+ "rope_scaling": {
39
+ "mrope_section": [
40
+ 16,
41
+ 24,
42
+ 24
43
+ ],
44
+ "rope_type": "default",
45
+ "type": "default"
46
+ },
47
+ "rope_theta": 1000000.0,
48
+ "seconds_per_chunk": 2,
49
+ "sliding_window": 32768,
50
+ "spatial_merge_size": 2,
51
+ "torch_dtype": "bfloat16",
52
+ "tts_codec_end_token_id": 8294,
53
+ "tts_codec_mask_token_id": 8296,
54
+ "tts_codec_pad_token_id": 8292,
55
+ "tts_codec_start_token_id": 8293,
56
+ "tts_text_end_token_id": 151861,
57
+ "tts_text_pad_token_id": 151859,
58
+ "tts_text_start_token_id": 151860,
59
+ "use_cache": true,
60
+ "use_sliding_window": false,
61
+ "video_token_index": 151656,
62
+ "vision_end_token_id": 151653,
63
+ "vision_start_token_id": 151652,
64
+ "vocab_size": 8448
65
+ },
66
+ "thinker_config": {
67
+ "_attn_implementation_autoset": true,
68
+ "_name_or_path": "Qwen2.5-Omni-7B/thinker",
69
+ "architectures": [
70
+ "Qwen2OmniNaViTThinkerForConditionalGeneration"
71
+ ],
72
+ "audio_config": {
73
+ "_attn_implementation_autoset": true,
74
+ "_name_or_path": "",
75
+ "activation_dropout": 0.0,
76
+ "activation_function": "gelu",
77
+ "add_cross_attention": false,
78
+ "architectures": null,
79
+ "attention_dropout": 0.0,
80
+ "bad_words_ids": null,
81
+ "begin_suppress_tokens": null,
82
+ "bos_token_id": null,
83
+ "chunk_size_feed_forward": 0,
84
+ "cross_attention_hidden_size": null,
85
+ "d_model": 1280,
86
+ "decoder_start_token_id": null,
87
+ "diversity_penalty": 0.0,
88
+ "do_sample": false,
89
+ "dropout": 0.0,
90
+ "early_stopping": false,
91
+ "encoder_attention_heads": 20,
92
+ "encoder_ffn_dim": 5120,
93
+ "encoder_layerdrop": 0.0,
94
+ "encoder_layers": 32,
95
+ "encoder_no_repeat_ngram_size": 0,
96
+ "eos_token_id": null,
97
+ "exponential_decay_length_penalty": null,
98
+ "finetuning_task": null,
99
+ "forced_bos_token_id": null,
100
+ "forced_eos_token_id": null,
101
+ "id2label": {
102
+ "0": "LABEL_0",
103
+ "1": "LABEL_1"
104
+ },
105
+ "init_std": 0.02,
106
+ "is_decoder": false,
107
+ "is_encoder_decoder": false,
108
+ "label2id": {
109
+ "LABEL_0": 0,
110
+ "LABEL_1": 1
111
+ },
112
+ "length_penalty": 1.0,
113
+ "max_length": 20,
114
+ "max_source_positions": 1500,
115
+ "min_length": 0,
116
+ "model_type": "qwen2_5_omni_audio_encoder",
117
+ "n_window": 100,
118
+ "no_repeat_ngram_size": 0,
119
+ "num_beam_groups": 1,
120
+ "num_beams": 1,
121
+ "num_hidden_layers": 32,
122
+ "num_mel_bins": 128,
123
+ "num_return_sequences": 1,
124
+ "output_attentions": false,
125
+ "output_dim": 3584,
126
+ "output_hidden_states": false,
127
+ "output_scores": false,
128
+ "pad_token_id": null,
129
+ "prefix": null,
130
+ "problem_type": null,
131
+ "pruned_heads": {},
132
+ "remove_invalid_values": false,
133
+ "repetition_penalty": 1.0,
134
+ "return_dict": true,
135
+ "return_dict_in_generate": false,
136
+ "scale_embedding": false,
137
+ "sep_token_id": null,
138
+ "suppress_tokens": null,
139
+ "task_specific_params": null,
140
+ "temperature": 1.0,
141
+ "tf_legacy_loss": false,
142
+ "tie_encoder_decoder": false,
143
+ "tie_word_embeddings": true,
144
+ "tokenizer_class": null,
145
+ "top_k": 50,
146
+ "top_p": 1.0,
147
+ "torch_dtype": null,
148
+ "torchscript": false,
149
+ "typical_p": 1.0,
150
+ "use_bfloat16": false
151
+ },
152
+ "text_config": {
153
+ "model_type": "qwen2_5_omni_text",
154
+ "hidden_act": "silu",
155
+ "hidden_size": 3584,
156
+ "init_std": 0.02,
157
+ "intermediate_size": 18944,
158
+ "vocab_size": 152064,
159
+ "num_attention_heads": 28,
160
+ "num_hidden_layers": 28,
161
+ "num_key_value_heads": 4,
162
+ "max_position_embeddings": 32768,
163
+ "max_window_layers": 28,
164
+ "rms_norm_eps": 1e-06,
165
+ "rope_scaling": {
166
+ "mrope_section": [
167
+ 16,
168
+ 24,
169
+ 24
170
+ ],
171
+ "rope_type": "default",
172
+ "type": "default"
173
+ },
174
+ "use_cache": true,
175
+ "rope_theta": 1000000.0,
176
+ "use_sliding_window": false,
177
+ "sliding_window": 32768,
178
+ "attention_dropout": 0.0,
179
+ "tie_word_embeddings": false
180
+ },
181
+ "audio_end_token_id": 151648,
182
+ "audio_start_token_id": 151647,
183
+ "audio_token_index": 151646,
184
+ "bos_token_id": 151644,
185
+ "eos_token_id": 151645,
186
+ "ignore_index": -100,
187
+ "image_token_index": 151655,
188
+ "init_std": 0.02,
189
+ "model_type": "qwen2_5_omni_thinker",
190
+ "pad_token_id": 151643,
191
+ "position_id_per_seconds": 25,
192
+ "seconds_per_chunk": 2,
193
+ "torch_dtype": "bfloat16",
194
+ "user_token_id": 872,
195
+ "video_token_index": 151656,
196
+ "vision_config": {
197
+ "_attn_implementation_autoset": true,
198
+ "_name_or_path": "",
199
+ "add_cross_attention": false,
200
+ "architectures": null,
201
+ "bad_words_ids": null,
202
+ "begin_suppress_tokens": null,
203
+ "bos_token_id": null,
204
+ "chunk_size_feed_forward": 0,
205
+ "cross_attention_hidden_size": null,
206
+ "decoder_start_token_id": null,
207
+ "depth": 32,
208
+ "diversity_penalty": 0.0,
209
+ "do_sample": false,
210
+ "early_stopping": false,
211
+ "embed_dim": 1280,
212
+ "encoder_no_repeat_ngram_size": 0,
213
+ "eos_token_id": null,
214
+ "exponential_decay_length_penalty": null,
215
+ "finetuning_task": null,
216
+ "forced_bos_token_id": null,
217
+ "forced_eos_token_id": null,
218
+ "fullatt_block_indexes": [
219
+ 7,
220
+ 15,
221
+ 23,
222
+ 31
223
+ ],
224
+ "hidden_act": "silu",
225
+ "hidden_size": 1280,
226
+ "id2label": {
227
+ "0": "LABEL_0",
228
+ "1": "LABEL_1"
229
+ },
230
+ "in_channels": 3,
231
+ "in_chans": 3,
232
+ "init_std": 0.02,
233
+ "intermediate_size": 3420,
234
+ "is_decoder": false,
235
+ "is_encoder_decoder": false,
236
+ "label2id": {
237
+ "LABEL_0": 0,
238
+ "LABEL_1": 1
239
+ },
240
+ "length_penalty": 1.0,
241
+ "max_length": 20,
242
+ "min_length": 0,
243
+ "model_type": "qwen2_5_omni_vision_encoder",
244
+ "no_repeat_ngram_size": 0,
245
+ "num_beam_groups": 1,
246
+ "num_beams": 1,
247
+ "num_heads": 16,
248
+ "num_return_sequences": 1,
249
+ "out_hidden_size": 3584,
250
+ "output_attentions": false,
251
+ "output_hidden_states": false,
252
+ "output_scores": false,
253
+ "pad_token_id": null,
254
+ "patch_size": 14,
255
+ "prefix": null,
256
+ "problem_type": null,
257
+ "pruned_heads": {},
258
+ "remove_invalid_values": false,
259
+ "repetition_penalty": 1.0,
260
+ "return_dict": true,
261
+ "return_dict_in_generate": false,
262
+ "sep_token_id": null,
263
+ "spatial_merge_size": 2,
264
+ "spatial_patch_size": 14,
265
+ "suppress_tokens": null,
266
+ "task_specific_params": null,
267
+ "temperature": 1.0,
268
+ "temporal_patch_size": 2,
269
+ "tf_legacy_loss": false,
270
+ "tie_encoder_decoder": false,
271
+ "tie_word_embeddings": true,
272
+ "tokenizer_class": null,
273
+ "tokens_per_second": 25,
274
+ "top_k": 50,
275
+ "top_p": 1.0,
276
+ "torch_dtype": null,
277
+ "torchscript": false,
278
+ "typical_p": 1.0,
279
+ "use_bfloat16": false,
280
+ "window_size": 112
281
+ },
282
+ "vision_end_token_id": 151653,
283
+ "vision_start_token_id": 151652,
284
+ "vision_token_id": 151654
285
+ },
286
+ "token2wav_config": {
287
+ "_attn_implementation_autoset": true,
288
+ "bigvgan_config": {
289
+ "_attn_implementation_autoset": true,
290
+ "_name_or_path": "",
291
+ "add_cross_attention": false,
292
+ "architectures": null,
293
+ "bad_words_ids": null,
294
+ "begin_suppress_tokens": null,
295
+ "bos_token_id": null,
296
+ "chunk_size_feed_forward": 0,
297
+ "cross_attention_hidden_size": null,
298
+ "decoder_start_token_id": null,
299
+ "diversity_penalty": 0.0,
300
+ "do_sample": false,
301
+ "early_stopping": false,
302
+ "encoder_no_repeat_ngram_size": 0,
303
+ "eos_token_id": null,
304
+ "exponential_decay_length_penalty": null,
305
+ "finetuning_task": null,
306
+ "forced_bos_token_id": null,
307
+ "forced_eos_token_id": null,
308
+ "id2label": {
309
+ "0": "LABEL_0",
310
+ "1": "LABEL_1"
311
+ },
312
+ "is_decoder": false,
313
+ "is_encoder_decoder": false,
314
+ "label2id": {
315
+ "LABEL_0": 0,
316
+ "LABEL_1": 1
317
+ },
318
+ "length_penalty": 1.0,
319
+ "max_length": 20,
320
+ "mel_dim": 80,
321
+ "min_length": 0,
322
+ "model_type": "qwen2_5_omni_bigvgan",
323
+ "no_repeat_ngram_size": 0,
324
+ "num_beam_groups": 1,
325
+ "num_beams": 1,
326
+ "num_return_sequences": 1,
327
+ "output_attentions": false,
328
+ "output_hidden_states": false,
329
+ "output_scores": false,
330
+ "pad_token_id": null,
331
+ "prefix": null,
332
+ "problem_type": null,
333
+ "pruned_heads": {},
334
+ "remove_invalid_values": false,
335
+ "repetition_penalty": 1.0,
336
+ "resblock_dilation_sizes": [
337
+ [
338
+ 1,
339
+ 3,
340
+ 5
341
+ ],
342
+ [
343
+ 1,
344
+ 3,
345
+ 5
346
+ ],
347
+ [
348
+ 1,
349
+ 3,
350
+ 5
351
+ ]
352
+ ],
353
+ "resblock_kernel_sizes": [
354
+ 3,
355
+ 7,
356
+ 11
357
+ ],
358
+ "return_dict": true,
359
+ "return_dict_in_generate": false,
360
+ "sep_token_id": null,
361
+ "suppress_tokens": null,
362
+ "task_specific_params": null,
363
+ "temperature": 1.0,
364
+ "tf_legacy_loss": false,
365
+ "tie_encoder_decoder": false,
366
+ "tie_word_embeddings": true,
367
+ "tokenizer_class": null,
368
+ "top_k": 50,
369
+ "top_p": 1.0,
370
+ "torch_dtype": null,
371
+ "torchscript": false,
372
+ "typical_p": 1.0,
373
+ "upsample_initial_channel": 1536,
374
+ "upsample_kernel_sizes": [
375
+ 11,
376
+ 7,
377
+ 4,
378
+ 4,
379
+ 4,
380
+ 4
381
+ ],
382
+ "upsample_rates": [
383
+ 5,
384
+ 3,
385
+ 2,
386
+ 2,
387
+ 2,
388
+ 2
389
+ ],
390
+ "use_bfloat16": false,
391
+ "use_bias_at_final": false
392
+ },
393
+ "dit_config": {
394
+ "_attn_implementation_autoset": true,
395
+ "_name_or_path": "",
396
+ "add_cross_attention": false,
397
+ "architectures": null,
398
+ "bad_words_ids": null,
399
+ "begin_suppress_tokens": null,
400
+ "bos_token_id": null,
401
+ "chunk_size_feed_forward": 0,
402
+ "cross_attention_hidden_size": null,
403
+ "decoder_start_token_id": null,
404
+ "depth": 22,
405
+ "dim": 1024,
406
+ "diversity_penalty": 0.0,
407
+ "do_sample": false,
408
+ "dropout": 0.1,
409
+ "early_stopping": false,
410
+ "emb_dim": 512,
411
+ "enc_attention_channels": 64,
412
+ "enc_channels": [
413
+ 256,
414
+ 256,
415
+ 256,
416
+ 256,
417
+ 768
418
+ ],
419
+ "enc_dilations": [
420
+ 1,
421
+ 2,
422
+ 3,
423
+ 4,
424
+ 1
425
+ ],
426
+ "enc_dim": 128,
427
+ "enc_emb_dim": 192,
428
+ "enc_global_context": true,
429
+ "enc_kernel_sizes": [
430
+ 5,
431
+ 3,
432
+ 3,
433
+ 3,
434
+ 1
435
+ ],
436
+ "enc_lin_neurons": 192,
437
+ "enc_res2net_scale": 2,
438
+ "enc_se_channels": 64,
439
+ "encoder_no_repeat_ngram_size": 0,
440
+ "eos_token_id": null,
441
+ "exponential_decay_length_penalty": null,
442
+ "ff_mult": 2,
443
+ "finetuning_task": null,
444
+ "forced_bos_token_id": null,
445
+ "forced_eos_token_id": null,
446
+ "head_dim": 64,
447
+ "heads": 16,
448
+ "id2label": {
449
+ "0": "LABEL_0",
450
+ "1": "LABEL_1"
451
+ },
452
+ "is_decoder": false,
453
+ "is_encoder_decoder": false,
454
+ "label2id": {
455
+ "LABEL_0": 0,
456
+ "LABEL_1": 1
457
+ },
458
+ "length_penalty": 1.0,
459
+ "max_length": 20,
460
+ "mel_dim": 80,
461
+ "min_length": 0,
462
+ "model_type": "qwen2_5_omni_dit",
463
+ "no_repeat_ngram_size": 0,
464
+ "num_beam_groups": 1,
465
+ "num_beams": 1,
466
+ "num_embeds": 8193,
467
+ "num_return_sequences": 1,
468
+ "output_attentions": false,
469
+ "output_hidden_states": false,
470
+ "output_scores": false,
471
+ "pad_token_id": null,
472
+ "prefix": null,
473
+ "problem_type": null,
474
+ "pruned_heads": {},
475
+ "remove_invalid_values": false,
476
+ "repeats": 2,
477
+ "repetition_penalty": 1.0,
478
+ "return_dict": true,
479
+ "return_dict_in_generate": false,
480
+ "sep_token_id": null,
481
+ "suppress_tokens": null,
482
+ "task_specific_params": null,
483
+ "temperature": 1.0,
484
+ "tf_legacy_loss": false,
485
+ "tie_encoder_decoder": false,
486
+ "tie_word_embeddings": true,
487
+ "tokenizer_class": null,
488
+ "top_k": 50,
489
+ "top_p": 1.0,
490
+ "torch_dtype": "float32",
491
+ "torchscript": false,
492
+ "typical_p": 1.0,
493
+ "use_bfloat16": false
494
+ },
495
+ "model_type": "qwen2_5_omni_token2wav"
496
+ },
497
+ "torch_dtype": "bfloat16",
498
+ "transformers_version": "4.50.0.dev0"
499
+ }
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:dd73a1681de32cf91ced82166583617635f12d1e55da068dbaf3962764ffac35
3
+ size 4652749012
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
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8441917e39ae0244e06d704b95b3124795cec478e297f9afac39ba670d7e9d99
3
+ size 11421870
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
+ "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
201
+ "clean_up_tokenization_spaces": false,
202
+ "eos_token": "<|im_end|>",
203
+ "errors": "replace",
204
+ "extra_special_tokens": {
205
+ "audio_bos_token": "<|audio_bos|>",
206
+ "audio_eos_token": "<|audio_eos|>",
207
+ "audio_token": "<|AUDIO|>",
208
+ "image_token": "<|IMAGE|>",
209
+ "video_token": "<|VIDEO|>",
210
+ "vision_bos_token": "<|vision_bos|>",
211
+ "vision_eos_token": "<|vision_eos|>"
212
+ },
213
+ "image_token": "<|IMAGE|>",
214
+ "model_max_length": 32768,
215
+ "pad_token": "<|endoftext|>",
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
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff