Hugging Face's logo

ASLP-lab
/
WSChuan-ASR

Automatic Speech Recognition
Safetensors
Chinese
ASR
chinese
speech
Model card Files
xet
Community
ASLP-lab commited on
Commit
0fa1cc0
·
verified ·
1 Parent(s): b9d04c4

Upload 17 files

Browse files
Files changed (18) hide show
  1. .gitattributes +1 -0
  2. Qwen2.5-Omni-3B-Chuan/added_tokens.json +24 -0
  3. Qwen2.5-Omni-3B-Chuan/args.json +373 -0
  4. Qwen2.5-Omni-3B-Chuan/chat_template.jinja +7 -0
  5. Qwen2.5-Omni-3B-Chuan/config.json +644 -0
  6. Qwen2.5-Omni-3B-Chuan/generation_config.json +8 -0
  7. Qwen2.5-Omni-3B-Chuan/merges.txt +0 -0
  8. Qwen2.5-Omni-3B-Chuan/model-00001-of-00003.safetensors +3 -0
  9. Qwen2.5-Omni-3B-Chuan/model-00002-of-00003.safetensors +3 -0
  10. Qwen2.5-Omni-3B-Chuan/model-00003-of-00003.safetensors +3 -0
  11. Qwen2.5-Omni-3B-Chuan/model.safetensors.index.json +0 -0
  12. Qwen2.5-Omni-3B-Chuan/preprocessor_config.json +31 -0
  13. Qwen2.5-Omni-3B-Chuan/special_tokens_map.json +38 -0
  14. Qwen2.5-Omni-3B-Chuan/spk_dict.pt +3 -0
  15. Qwen2.5-Omni-3B-Chuan/tokenizer.json +3 -0
  16. Qwen2.5-Omni-3B-Chuan/tokenizer_config.json +222 -0
  17. Qwen2.5-Omni-3B-Chuan/video_preprocessor_config.json +56 -0
  18. Qwen2.5-Omni-3B-Chuan/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-3B-Chuan/tokenizer.json filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Omni-3B-Chuan/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-3B-Chuan/args.json ADDED
@@ -0,0 +1,373 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/home/work_nfs23/sywang/code/asr_rl/exp/sft_chuan2/v0-20250909-174359",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "no",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 2,
10
+ "per_device_eval_batch_size": 2,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 4,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 0.0001,
18
+ "weight_decay": 0.1,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.95,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 1.0,
23
+ "num_train_epochs": 5.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "cosine",
26
+ "lr_scheduler_kwargs": null,
27
+ "warmup_ratio": 0.05,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "/home/work_nfs23/sywang/code/asr_rl/exp/sft_chuan2/v0-20250909-174359/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 5,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "steps",
38
+ "save_steps": 2000.0,
39
+ "save_total_limit": null,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": false,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 42,
48
+ "data_seed": 42,
49
+ "jit_mode_eval": false,
50
+ "use_ipex": false,
51
+ "bf16": true,
52
+ "fp16": false,
53
+ "fp16_opt_level": "O1",
54
+ "half_precision_backend": "auto",
55
+ "bf16_full_eval": false,
56
+ "fp16_full_eval": false,
57
+ "tf32": null,
58
+ "local_rank": 0,
59
+ "ddp_backend": null,
60
+ "tpu_num_cores": null,
61
+ "tpu_metrics_debug": false,
62
+ "debug": null,
63
+ "dataloader_drop_last": false,
64
+ "eval_steps": 2000.0,
65
+ "dataloader_num_workers": 4,
66
+ "dataloader_prefetch_factor": null,
67
+ "past_index": -1,
68
+ "run_name": "/home/work_nfs23/sywang/code/asr_rl/exp/sft_chuan2/v0-20250909-174359",
69
+ "disable_tqdm": null,
70
+ "remove_unused_columns": true,
71
+ "label_names": null,
72
+ "load_best_model_at_end": false,
73
+ "metric_for_best_model": "loss",
74
+ "greater_is_better": false,
75
+ "ignore_data_skip": false,
76
+ "fsdp": "",
77
+ "fsdp_min_num_params": 0,
78
+ "fsdp_config": null,
79
+ "fsdp_transformer_layer_cls_to_wrap": null,
80
+ "accelerator_config": {
81
+ "dispatch_batches": false
82
+ },
83
+ "parallelism_config": null,
84
+ "deepspeed": {
85
+ "fp16": {
86
+ "enabled": "auto",
87
+ "loss_scale": 0,
88
+ "loss_scale_window": 1000,
89
+ "initial_scale_power": 16,
90
+ "hysteresis": 2,
91
+ "min_loss_scale": 1
92
+ },
93
+ "bf16": {
94
+ "enabled": "auto"
95
+ },
96
+ "zero_optimization": {
97
+ "stage": 2,
98
+ "offload_optimizer": {
99
+ "device": "none",
100
+ "pin_memory": true
101
+ },
102
+ "allgather_partitions": true,
103
+ "allgather_bucket_size": 200000000.0,
104
+ "overlap_comm": false,
105
+ "reduce_scatter": true,
106
+ "reduce_bucket_size": 200000000.0,
107
+ "contiguous_gradients": true
108
+ },
109
+ "gradient_accumulation_steps": "auto",
110
+ "gradient_clipping": "auto",
111
+ "steps_per_print": 2000,
112
+ "train_batch_size": "auto",
113
+ "train_micro_batch_size_per_gpu": "auto",
114
+ "wall_clock_breakdown": false
115
+ },
116
+ "label_smoothing_factor": 0.0,
117
+ "optim": "adamw_torch",
118
+ "optim_args": null,
119
+ "adafactor": false,
120
+ "group_by_length": false,
121
+ "length_column_name": "length",
122
+ "report_to": [
123
+ "tensorboard"
124
+ ],
125
+ "ddp_find_unused_parameters": null,
126
+ "ddp_bucket_cap_mb": null,
127
+ "ddp_broadcast_buffers": null,
128
+ "dataloader_pin_memory": true,
129
+ "dataloader_persistent_workers": false,
130
+ "skip_memory_metrics": true,
131
+ "use_legacy_prediction_loop": false,
132
+ "push_to_hub": false,
133
+ "resume_from_checkpoint": null,
134
+ "hub_model_id": null,
135
+ "hub_strategy": "every_save",
136
+ "hub_token": null,
137
+ "hub_private_repo": null,
138
+ "hub_always_push": false,
139
+ "hub_revision": null,
140
+ "gradient_checkpointing": true,
141
+ "gradient_checkpointing_kwargs": null,
142
+ "include_inputs_for_metrics": false,
143
+ "include_for_metrics": [],
144
+ "eval_do_concat_batches": true,
145
+ "fp16_backend": "auto",
146
+ "push_to_hub_model_id": null,
147
+ "push_to_hub_organization": null,
148
+ "push_to_hub_token": null,
149
+ "mp_parameters": "",
150
+ "auto_find_batch_size": false,
151
+ "full_determinism": false,
152
+ "torchdynamo": null,
153
+ "ray_scope": "last",
154
+ "ddp_timeout": 18000000,
155
+ "torch_compile": false,
156
+ "torch_compile_backend": null,
157
+ "torch_compile_mode": null,
158
+ "include_tokens_per_second": false,
159
+ "include_num_input_tokens_seen": false,
160
+ "neftune_noise_alpha": null,
161
+ "optim_target_modules": null,
162
+ "batch_eval_metrics": false,
163
+ "eval_on_start": false,
164
+ "use_liger_kernel": false,
165
+ "liger_kernel_config": null,
166
+ "eval_use_gather_object": false,
167
+ "average_tokens_across_devices": true,
168
+ "sortish_sampler": false,
169
+ "predict_with_generate": false,
170
+ "generation_max_length": null,
171
+ "generation_num_beams": null,
172
+ "generation_config": null,
173
+ "tuner_backend": "peft",
174
+ "vit_gradient_checkpointing": null,
175
+ "router_aux_loss_coef": 0.0,
176
+ "enable_dft_loss": false,
177
+ "enable_channel_loss": false,
178
+ "check_model": true,
179
+ "acc_strategy": "token",
180
+ "train_dataloader_shuffle": true,
181
+ "max_epochs": null,
182
+ "aligner_lr": null,
183
+ "vit_lr": null,
184
+ "use_logits_to_keep": null,
185
+ "ds3_gather_for_generation": true,
186
+ "resume_only_model": false,
187
+ "optimizer": null,
188
+ "loss_type": null,
189
+ "metric": null,
190
+ "eval_use_evalscope": false,
191
+ "eval_dataset": [],
192
+ "eval_dataset_args": null,
193
+ "eval_limit": null,
194
+ "eval_generation_config": null,
195
+ "extra_eval_args": null,
196
+ "use_flash_ckpt": false,
197
+ "model": "/home/work_nfs23/sywang/ckpt/Qwen2.5-Omni-3B",
198
+ "model_type": "qwen2_5_omni",
199
+ "model_revision": null,
200
+ "task_type": "causal_lm",
201
+ "torch_dtype": "bfloat16",
202
+ "attn_impl": "flash_attn",
203
+ "new_special_tokens": [],
204
+ "num_labels": null,
205
+ "problem_type": null,
206
+ "rope_scaling": null,
207
+ "device_map": null,
208
+ "max_memory": {},
209
+ "max_model_len": null,
210
+ "local_repo_path": null,
211
+ "init_strategy": null,
212
+ "template": "qwen2_5_omni",
213
+ "system": "You are a speech recognition model.",
214
+ "max_length": 2048,
215
+ "truncation_strategy": "delete",
216
+ "max_pixels": null,
217
+ "agent_template": null,
218
+ "norm_bbox": null,
219
+ "use_chat_template": true,
220
+ "padding_free": false,
221
+ "padding_side": "right",
222
+ "loss_scale": "default",
223
+ "sequence_parallel_size": 1,
224
+ "response_prefix": null,
225
+ "template_backend": "swift",
226
+ "dataset": [
227
+ "data/train/train_chuan2.jsonl"
228
+ ],
229
+ "val_dataset": [],
230
+ "split_dataset_ratio": 0.0,
231
+ "dataset_num_proc": 1,
232
+ "load_from_cache_file": true,
233
+ "dataset_shuffle": true,
234
+ "val_dataset_shuffle": false,
235
+ "streaming": false,
236
+ "interleave_prob": null,
237
+ "stopping_strategy": "first_exhausted",
238
+ "shuffle_buffer_size": 1000,
239
+ "download_mode": "reuse_dataset_if_exists",
240
+ "columns": {},
241
+ "strict": false,
242
+ "model_name": null,
243
+ "model_author": null,
244
+ "custom_dataset_info": [],
245
+ "quant_method": null,
246
+ "quant_bits": null,
247
+ "hqq_axis": null,
248
+ "bnb_4bit_compute_dtype": "bfloat16",
249
+ "bnb_4bit_quant_type": "nf4",
250
+ "bnb_4bit_use_double_quant": true,
251
+ "bnb_4bit_quant_storage": null,
252
+ "max_new_tokens": 64,
253
+ "temperature": 0.0,
254
+ "top_k": null,
255
+ "top_p": null,
256
+ "repetition_penalty": null,
257
+ "num_beams": 1,
258
+ "stream": false,
259
+ "stop_words": [],
260
+ "logprobs": false,
261
+ "top_logprobs": null,
262
+ "ckpt_dir": null,
263
+ "lora_modules": [],
264
+ "train_type": "lora",
265
+ "adapters": [],
266
+ "external_plugins": [],
267
+ "model_kwargs": {},
268
+ "load_args": false,
269
+ "load_data_args": false,
270
+ "packing": false,
271
+ "packing_length": null,
272
+ "lazy_tokenize": true,
273
+ "cached_dataset": [],
274
+ "custom_register_path": [],
275
+ "use_hf": false,
276
+ "ignore_args_error": false,
277
+ "use_swift_lora": false,
278
+ "freeze_parameters": [],
279
+ "freeze_parameters_regex": null,
280
+ "freeze_parameters_ratio": 0.0,
281
+ "trainable_parameters": [],
282
+ "trainable_parameters_regex": null,
283
+ "freeze_llm": false,
284
+ "freeze_vit": true,
285
+ "freeze_aligner": true,
286
+ "target_modules": [
287
+ "all-linear"
288
+ ],
289
+ "target_regex": null,
290
+ "target_parameters": null,
291
+ "modules_to_save": [],
292
+ "lora_rank": 8,
293
+ "lora_alpha": 32,
294
+ "lora_dropout": 0.05,
295
+ "lora_bias": "none",
296
+ "lora_dtype": null,
297
+ "lorap_lr_ratio": null,
298
+ "use_rslora": false,
299
+ "use_dora": false,
300
+ "lora_ga_batch_size": 2,
301
+ "lora_ga_iters": 2,
302
+ "lora_ga_max_length": 1024,
303
+ "lora_ga_direction": "ArB2r",
304
+ "lora_ga_scale": "stable",
305
+ "lora_ga_stable_gamma": 16,
306
+ "init_weights": true,
307
+ "fourier_n_frequency": 2000,
308
+ "fourier_scaling": 300.0,
309
+ "boft_block_size": 4,
310
+ "boft_block_num": 0,
311
+ "boft_n_butterfly_factor": 1,
312
+ "boft_dropout": 0.0,
313
+ "vera_rank": 256,
314
+ "vera_projection_prng_key": 0,
315
+ "vera_dropout": 0.0,
316
+ "vera_d_initial": 0.1,
317
+ "adapter_act": "gelu",
318
+ "adapter_length": 128,
319
+ "use_galore": false,
320
+ "galore_target_modules": null,
321
+ "galore_rank": 128,
322
+ "galore_update_proj_gap": 50,
323
+ "galore_scale": 1.0,
324
+ "galore_proj_type": "std",
325
+ "galore_optim_per_parameter": false,
326
+ "galore_with_embedding": false,
327
+ "galore_quantization": false,
328
+ "galore_proj_quant": false,
329
+ "galore_proj_bits": 4,
330
+ "galore_proj_group_size": 256,
331
+ "galore_cos_threshold": 0.4,
332
+ "galore_gamma_proj": 2,
333
+ "galore_queue_size": 5,
334
+ "adalora_target_r": 8,
335
+ "adalora_init_r": 12,
336
+ "adalora_tinit": 0,
337
+ "adalora_tfinal": 0,
338
+ "adalora_deltaT": 1,
339
+ "adalora_beta1": 0.85,
340
+ "adalora_beta2": 0.85,
341
+ "adalora_orth_reg_weight": 0.5,
342
+ "llamapro_num_new_blocks": 4,
343
+ "llamapro_num_groups": null,
344
+ "lisa_activated_layers": 0,
345
+ "lisa_step_interval": 20,
346
+ "reft_layer_key": null,
347
+ "reft_layers": null,
348
+ "reft_rank": 4,
349
+ "reft_intervention_type": "LoreftIntervention",
350
+ "reft_args": null,
351
+ "swanlab_token": null,
352
+ "swanlab_project": null,
353
+ "swanlab_workspace": null,
354
+ "swanlab_exp_name": null,
355
+ "swanlab_lark_webhook_url": null,
356
+ "swanlab_lark_secret": null,
357
+ "swanlab_mode": "cloud",
358
+ "add_version": true,
359
+ "create_checkpoint_symlink": false,
360
+ "zero_hpz_partition_size": null,
361
+ "deepspeed_autotp_size": null,
362
+ "early_stop_interval": null,
363
+ "rank": 0,
364
+ "global_world_size": 4,
365
+ "local_world_size": 4,
366
+ "model_suffix": "Qwen2.5-Omni-3B",
367
+ "model_info": "ModelInfo(model_type='qwen2_5_omni', model_dir='/home/work_nfs23/sywang/ckpt/Qwen2.5-Omni-3B', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling={'mrope_section': [16, 24, 24], 'rope_type': 'default', 'type': 'default'}, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)",
368
+ "model_meta": "ModelMeta(model_type='qwen2_5_omni', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-Omni-3B', hf_model_id='Qwen/Qwen2.5-Omni-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Omni-7B', hf_model_id='Qwen/Qwen2.5-Omni-7B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_omni', get_function=<function get_model_tokenizer_qwen2_5_omni at 0x7fe20f5868e0>, model_arch=MultiModelKeys(arch_name='qwen2_5_omni', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['thinker.model'], aligner=['thinker.audio_tower.proj', 'thinker.visual.merger'], vision_tower=['thinker.audio_tower', 'thinker.visual'], generator=['talker', 'token2wav']), architectures=['Qwen2_5OmniModel', 'Qwen2_5OmniForConditionalGeneration'], additional_saved_files=['spk_dict.pt'], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=[], requires=['transformers>=4.50', 'soundfile', 'qwen_omni_utils', 'decord'], tags=['vision', 'video', 'audio'])",
369
+ "model_dir": "/home/work_nfs23/sywang/ckpt/Qwen2.5-Omni-3B",
370
+ "hub": "<class 'swift.hub.hub.MSHub'>",
371
+ "evaluation_strategy": "steps",
372
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/home/work_nfs23/sywang/code/asr_rl/exp/sft_chuan2/v0-20250909-174359', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=2, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=5.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/work_nfs23/sywang/code/asr_rl/exp/sft_chuan2/v0-20250909-174359/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=2000, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=2000.0, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/home/work_nfs23/sywang/code/asr_rl/exp/sft_chuan2/v0-20250909-174359', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 2, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, train_type='lora', local_repo_path=None, galore_config=None)"
373
+ }
Qwen2.5-Omni-3B-Chuan/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-3B-Chuan/config.json ADDED
@@ -0,0 +1,644 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5OmniForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "enable_audio_output": true,
7
+ "enable_talker": true,
8
+ "hidden_size": 2048,
9
+ "keys_to_ignore_at_inference": [
10
+ "past_key_values",
11
+ "hidden_states",
12
+ "attention_mask"
13
+ ],
14
+ "model_type": "qwen2_5_omni",
15
+ "pad_token_id": 151643,
16
+ "talker_config": {
17
+ "_attn_implementation_autoset": true,
18
+ "_name_or_path": "Qwen2.5-Omni-3B/talker",
19
+ "architectures": [
20
+ "Qwen2OmniTalkerForConditionalGeneration"
21
+ ],
22
+ "attention_dropout": 0.0,
23
+ "audio_end_token_id": 151648,
24
+ "audio_start_token_id": 151647,
25
+ "audio_token_index": 151646,
26
+ "dtype": "bfloat16",
27
+ "embedding_size": 2048,
28
+ "head_dim": 64,
29
+ "hidden_act": "silu",
30
+ "hidden_size": 896,
31
+ "image_token_index": 151655,
32
+ "init_std": 0.02,
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 4864,
35
+ "layer_types": [
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
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention"
60
+ ],
61
+ "max_position_embeddings": 32768,
62
+ "max_window_layers": 28,
63
+ "model_type": "qwen2_5_omni_talker",
64
+ "num_attention_heads": 14,
65
+ "num_hidden_layers": 24,
66
+ "num_key_value_heads": 2,
67
+ "position_id_per_seconds": 25,
68
+ "rms_norm_eps": 1e-06,
69
+ "rope_scaling": {
70
+ "mrope_section": [
71
+ 16,
72
+ 16,
73
+ 0
74
+ ],
75
+ "rope_type": "default",
76
+ "type": "default"
77
+ },
78
+ "rope_theta": 1000000.0,
79
+ "seconds_per_chunk": 2,
80
+ "sliding_window": null,
81
+ "spatial_merge_size": 2,
82
+ "tts_codec_end_token_id": 8294,
83
+ "tts_codec_mask_token_id": 8296,
84
+ "tts_codec_pad_token_id": 8292,
85
+ "tts_codec_start_token_id": 8293,
86
+ "tts_text_end_token_id": 151861,
87
+ "tts_text_pad_token_id": 151859,
88
+ "tts_text_start_token_id": 151860,
89
+ "use_cache": true,
90
+ "use_sliding_window": false,
91
+ "video_token_index": 151656,
92
+ "vision_end_token_id": 151653,
93
+ "vision_start_token_id": 151652,
94
+ "vocab_size": 8448
95
+ },
96
+ "thinker_config": {
97
+ "_attn_implementation_autoset": true,
98
+ "_name_or_path": "Qwen2.5-Omni-3B/thinker",
99
+ "architectures": [
100
+ "Qwen2OmniNaViTThinkerForConditionalGeneration"
101
+ ],
102
+ "audio_config": {
103
+ "_attn_implementation_autoset": true,
104
+ "_name_or_path": "",
105
+ "activation_dropout": 0.0,
106
+ "activation_function": "gelu",
107
+ "add_cross_attention": false,
108
+ "architectures": null,
109
+ "attention_dropout": 0.0,
110
+ "bad_words_ids": null,
111
+ "begin_suppress_tokens": null,
112
+ "bos_token_id": null,
113
+ "chunk_size_feed_forward": 0,
114
+ "cross_attention_hidden_size": null,
115
+ "d_model": 1280,
116
+ "decoder_start_token_id": null,
117
+ "diversity_penalty": 0.0,
118
+ "do_sample": false,
119
+ "dropout": 0.0,
120
+ "dtype": "bfloat16",
121
+ "early_stopping": false,
122
+ "encoder_attention_heads": 20,
123
+ "encoder_ffn_dim": 5120,
124
+ "encoder_layerdrop": 0.0,
125
+ "encoder_layers": 32,
126
+ "encoder_no_repeat_ngram_size": 0,
127
+ "eos_token_id": null,
128
+ "exponential_decay_length_penalty": null,
129
+ "finetuning_task": null,
130
+ "forced_bos_token_id": null,
131
+ "forced_eos_token_id": null,
132
+ "id2label": {
133
+ "0": "LABEL_0",
134
+ "1": "LABEL_1"
135
+ },
136
+ "init_std": 0.02,
137
+ "initializer_range": 0.02,
138
+ "is_decoder": false,
139
+ "is_encoder_decoder": false,
140
+ "label2id": {
141
+ "LABEL_0": 0,
142
+ "LABEL_1": 1
143
+ },
144
+ "length_penalty": 1.0,
145
+ "max_length": 20,
146
+ "max_source_positions": 1500,
147
+ "min_length": 0,
148
+ "model_type": "qwen2_5_omni_audio_encoder",
149
+ "n_window": 100,
150
+ "no_repeat_ngram_size": 0,
151
+ "num_beam_groups": 1,
152
+ "num_beams": 1,
153
+ "num_hidden_layers": 32,
154
+ "num_mel_bins": 128,
155
+ "num_return_sequences": 1,
156
+ "output_attentions": false,
157
+ "output_dim": 2048,
158
+ "output_hidden_states": false,
159
+ "output_scores": false,
160
+ "pad_token_id": 151643,
161
+ "prefix": null,
162
+ "problem_type": null,
163
+ "pruned_heads": {},
164
+ "remove_invalid_values": false,
165
+ "repetition_penalty": 1.0,
166
+ "return_dict": true,
167
+ "return_dict_in_generate": false,
168
+ "scale_embedding": false,
169
+ "sep_token_id": null,
170
+ "suppress_tokens": null,
171
+ "task_specific_params": null,
172
+ "temperature": 1.0,
173
+ "tf_legacy_loss": false,
174
+ "tie_encoder_decoder": false,
175
+ "tie_word_embeddings": true,
176
+ "tokenizer_class": null,
177
+ "top_k": 50,
178
+ "top_p": 1.0,
179
+ "torchscript": false,
180
+ "typical_p": 1.0,
181
+ "use_bfloat16": false
182
+ },
183
+ "audio_end_token_id": 151648,
184
+ "audio_start_token_id": 151647,
185
+ "audio_token_index": 151646,
186
+ "bos_token_id": 151644,
187
+ "dtype": "bfloat16",
188
+ "eos_token_id": 151645,
189
+ "ignore_index": -100,
190
+ "image_token_index": 151655,
191
+ "init_std": 0.02,
192
+ "initializer_range": 0.02,
193
+ "model_type": "qwen2_5_omni_thinker",
194
+ "pad_token_id": 151643,
195
+ "position_id_per_seconds": 25,
196
+ "seconds_per_chunk": 2,
197
+ "text_config": {
198
+ "_name_or_path": "",
199
+ "add_cross_attention": false,
200
+ "architectures": null,
201
+ "attention_dropout": 0.0,
202
+ "bad_words_ids": null,
203
+ "begin_suppress_tokens": null,
204
+ "bos_token_id": null,
205
+ "chunk_size_feed_forward": 0,
206
+ "cross_attention_hidden_size": null,
207
+ "decoder_start_token_id": null,
208
+ "diversity_penalty": 0.0,
209
+ "do_sample": false,
210
+ "dtype": "bfloat16",
211
+ "early_stopping": false,
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
+ "hidden_act": "silu",
219
+ "hidden_size": 2048,
220
+ "id2label": {
221
+ "0": "LABEL_0",
222
+ "1": "LABEL_1"
223
+ },
224
+ "init_std": 0.02,
225
+ "initializer_range": 0.02,
226
+ "intermediate_size": 11008,
227
+ "is_decoder": false,
228
+ "is_encoder_decoder": false,
229
+ "label2id": {
230
+ "LABEL_0": 0,
231
+ "LABEL_1": 1
232
+ },
233
+ "layer_types": [
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
+ "full_attention",
256
+ "full_attention",
257
+ "full_attention",
258
+ "full_attention",
259
+ "full_attention",
260
+ "full_attention",
261
+ "full_attention",
262
+ "full_attention",
263
+ "full_attention",
264
+ "full_attention",
265
+ "full_attention",
266
+ "full_attention",
267
+ "full_attention",
268
+ "full_attention",
269
+ "full_attention"
270
+ ],
271
+ "length_penalty": 1.0,
272
+ "max_length": 20,
273
+ "max_position_embeddings": 32768,
274
+ "max_window_layers": 70,
275
+ "min_length": 0,
276
+ "model_type": "qwen2_5_omni_text",
277
+ "no_repeat_ngram_size": 0,
278
+ "num_attention_heads": 16,
279
+ "num_beam_groups": 1,
280
+ "num_beams": 1,
281
+ "num_hidden_layers": 36,
282
+ "num_key_value_heads": 2,
283
+ "num_return_sequences": 1,
284
+ "output_attentions": false,
285
+ "output_hidden_states": false,
286
+ "output_scores": false,
287
+ "pad_token_id": 151643,
288
+ "prefix": null,
289
+ "problem_type": null,
290
+ "pruned_heads": {},
291
+ "remove_invalid_values": false,
292
+ "repetition_penalty": 1.0,
293
+ "return_dict": true,
294
+ "return_dict_in_generate": false,
295
+ "rms_norm_eps": 1e-06,
296
+ "rope_scaling": {
297
+ "mrope_section": [
298
+ 16,
299
+ 24,
300
+ 24
301
+ ],
302
+ "rope_type": "default",
303
+ "type": "default"
304
+ },
305
+ "rope_theta": 1000000.0,
306
+ "sep_token_id": null,
307
+ "sliding_window": null,
308
+ "suppress_tokens": null,
309
+ "task_specific_params": null,
310
+ "temperature": 1.0,
311
+ "tf_legacy_loss": false,
312
+ "tie_encoder_decoder": false,
313
+ "tie_word_embeddings": false,
314
+ "tokenizer_class": null,
315
+ "top_k": 50,
316
+ "top_p": 1.0,
317
+ "torchscript": false,
318
+ "typical_p": 1.0,
319
+ "use_bfloat16": false,
320
+ "use_cache": true,
321
+ "use_sliding_window": false,
322
+ "vocab_size": 151936
323
+ },
324
+ "user_token_id": 872,
325
+ "video_token_index": 151656,
326
+ "vision_config": {
327
+ "_attn_implementation_autoset": true,
328
+ "_name_or_path": "",
329
+ "add_cross_attention": false,
330
+ "architectures": null,
331
+ "bad_words_ids": null,
332
+ "begin_suppress_tokens": null,
333
+ "bos_token_id": null,
334
+ "chunk_size_feed_forward": 0,
335
+ "cross_attention_hidden_size": null,
336
+ "decoder_start_token_id": null,
337
+ "depth": 32,
338
+ "diversity_penalty": 0.0,
339
+ "do_sample": false,
340
+ "dtype": "bfloat16",
341
+ "early_stopping": false,
342
+ "embed_dim": 1280,
343
+ "encoder_no_repeat_ngram_size": 0,
344
+ "eos_token_id": null,
345
+ "exponential_decay_length_penalty": null,
346
+ "finetuning_task": null,
347
+ "forced_bos_token_id": null,
348
+ "forced_eos_token_id": null,
349
+ "fullatt_block_indexes": [
350
+ 7,
351
+ 15,
352
+ 23,
353
+ 31
354
+ ],
355
+ "hidden_act": "silu",
356
+ "hidden_size": 1280,
357
+ "id2label": {
358
+ "0": "LABEL_0",
359
+ "1": "LABEL_1"
360
+ },
361
+ "in_channels": 3,
362
+ "in_chans": 3,
363
+ "init_std": 0.02,
364
+ "initializer_range": 0.02,
365
+ "intermediate_size": 3420,
366
+ "is_decoder": false,
367
+ "is_encoder_decoder": false,
368
+ "label2id": {
369
+ "LABEL_0": 0,
370
+ "LABEL_1": 1
371
+ },
372
+ "length_penalty": 1.0,
373
+ "max_length": 20,
374
+ "min_length": 0,
375
+ "model_type": "qwen2_5_omni_vision_encoder",
376
+ "no_repeat_ngram_size": 0,
377
+ "num_beam_groups": 1,
378
+ "num_beams": 1,
379
+ "num_heads": 16,
380
+ "num_return_sequences": 1,
381
+ "out_hidden_size": 2048,
382
+ "output_attentions": false,
383
+ "output_hidden_states": false,
384
+ "output_scores": false,
385
+ "pad_token_id": 151643,
386
+ "patch_size": 14,
387
+ "prefix": null,
388
+ "problem_type": null,
389
+ "pruned_heads": {},
390
+ "remove_invalid_values": false,
391
+ "repetition_penalty": 1.0,
392
+ "return_dict": true,
393
+ "return_dict_in_generate": false,
394
+ "sep_token_id": null,
395
+ "spatial_merge_size": 2,
396
+ "spatial_patch_size": 14,
397
+ "suppress_tokens": null,
398
+ "task_specific_params": null,
399
+ "temperature": 1.0,
400
+ "temporal_patch_size": 2,
401
+ "tf_legacy_loss": false,
402
+ "tie_encoder_decoder": false,
403
+ "tie_word_embeddings": true,
404
+ "tokenizer_class": null,
405
+ "tokens_per_second": 25,
406
+ "top_k": 50,
407
+ "top_p": 1.0,
408
+ "torchscript": false,
409
+ "typical_p": 1.0,
410
+ "use_bfloat16": false,
411
+ "window_size": 112
412
+ },
413
+ "vision_end_token_id": 151653,
414
+ "vision_start_token_id": 151652,
415
+ "vision_token_id": 151654
416
+ },
417
+ "token2wav_config": {
418
+ "_attn_implementation_autoset": true,
419
+ "bigvgan_config": {
420
+ "_attn_implementation_autoset": true,
421
+ "_name_or_path": "",
422
+ "add_cross_attention": false,
423
+ "architectures": null,
424
+ "bad_words_ids": null,
425
+ "begin_suppress_tokens": null,
426
+ "bos_token_id": null,
427
+ "chunk_size_feed_forward": 0,
428
+ "cross_attention_hidden_size": null,
429
+ "decoder_start_token_id": null,
430
+ "diversity_penalty": 0.0,
431
+ "do_sample": false,
432
+ "dtype": null,
433
+ "early_stopping": false,
434
+ "encoder_no_repeat_ngram_size": 0,
435
+ "eos_token_id": null,
436
+ "exponential_decay_length_penalty": null,
437
+ "finetuning_task": null,
438
+ "forced_bos_token_id": null,
439
+ "forced_eos_token_id": null,
440
+ "id2label": {
441
+ "0": "LABEL_0",
442
+ "1": "LABEL_1"
443
+ },
444
+ "is_decoder": false,
445
+ "is_encoder_decoder": false,
446
+ "label2id": {
447
+ "LABEL_0": 0,
448
+ "LABEL_1": 1
449
+ },
450
+ "length_penalty": 1.0,
451
+ "max_length": 20,
452
+ "mel_dim": 80,
453
+ "min_length": 0,
454
+ "model_type": "qwen2_5_omni_bigvgan",
455
+ "no_repeat_ngram_size": 0,
456
+ "num_beam_groups": 1,
457
+ "num_beams": 1,
458
+ "num_return_sequences": 1,
459
+ "output_attentions": false,
460
+ "output_hidden_states": false,
461
+ "output_scores": false,
462
+ "pad_token_id": 151643,
463
+ "prefix": null,
464
+ "problem_type": null,
465
+ "pruned_heads": {},
466
+ "remove_invalid_values": false,
467
+ "repetition_penalty": 1.0,
468
+ "resblock_dilation_sizes": [
469
+ [
470
+ 1,
471
+ 3,
472
+ 5
473
+ ],
474
+ [
475
+ 1,
476
+ 3,
477
+ 5
478
+ ],
479
+ [
480
+ 1,
481
+ 3,
482
+ 5
483
+ ]
484
+ ],
485
+ "resblock_kernel_sizes": [
486
+ 3,
487
+ 7,
488
+ 11
489
+ ],
490
+ "return_dict": true,
491
+ "return_dict_in_generate": false,
492
+ "sep_token_id": null,
493
+ "suppress_tokens": null,
494
+ "task_specific_params": null,
495
+ "temperature": 1.0,
496
+ "tf_legacy_loss": false,
497
+ "tie_encoder_decoder": false,
498
+ "tie_word_embeddings": true,
499
+ "tokenizer_class": null,
500
+ "top_k": 50,
501
+ "top_p": 1.0,
502
+ "torchscript": false,
503
+ "typical_p": 1.0,
504
+ "upsample_initial_channel": 1536,
505
+ "upsample_kernel_sizes": [
506
+ 11,
507
+ 7,
508
+ 4,
509
+ 4,
510
+ 4,
511
+ 4
512
+ ],
513
+ "upsample_rates": [
514
+ 5,
515
+ 3,
516
+ 2,
517
+ 2,
518
+ 2,
519
+ 2
520
+ ],
521
+ "use_bfloat16": false,
522
+ "use_bias_at_final": false
523
+ },
524
+ "dit_config": {
525
+ "_attn_implementation_autoset": true,
526
+ "_name_or_path": "",
527
+ "add_cross_attention": false,
528
+ "architectures": null,
529
+ "bad_words_ids": null,
530
+ "begin_suppress_tokens": null,
531
+ "block_size": 24,
532
+ "bos_token_id": null,
533
+ "chunk_size_feed_forward": 0,
534
+ "cross_attention_hidden_size": null,
535
+ "decoder_start_token_id": null,
536
+ "depth": 22,
537
+ "dim": 1024,
538
+ "diversity_penalty": 0.0,
539
+ "do_sample": false,
540
+ "dropout": 0.1,
541
+ "dtype": "float32",
542
+ "early_stopping": false,
543
+ "emb_dim": 512,
544
+ "enc_attention_channels": 64,
545
+ "enc_channels": [
546
+ 256,
547
+ 256,
548
+ 256,
549
+ 256,
550
+ 768
551
+ ],
552
+ "enc_dilations": [
553
+ 1,
554
+ 2,
555
+ 3,
556
+ 4,
557
+ 1
558
+ ],
559
+ "enc_dim": 128,
560
+ "enc_emb_dim": 192,
561
+ "enc_global_context": true,
562
+ "enc_kernel_sizes": [
563
+ 5,
564
+ 3,
565
+ 3,
566
+ 3,
567
+ 1
568
+ ],
569
+ "enc_lin_neurons": 192,
570
+ "enc_res2net_scale": 2,
571
+ "enc_se_channels": 64,
572
+ "encoder_no_repeat_ngram_size": 0,
573
+ "eos_token_id": null,
574
+ "exponential_decay_length_penalty": null,
575
+ "ff_mult": 2,
576
+ "finetuning_task": null,
577
+ "forced_bos_token_id": null,
578
+ "forced_eos_token_id": null,
579
+ "head_dim": 64,
580
+ "heads": 16,
581
+ "hidden_size": 1024,
582
+ "id2label": {
583
+ "0": "LABEL_0",
584
+ "1": "LABEL_1"
585
+ },
586
+ "is_decoder": false,
587
+ "is_encoder_decoder": false,
588
+ "label2id": {
589
+ "LABEL_0": 0,
590
+ "LABEL_1": 1
591
+ },
592
+ "length_penalty": 1.0,
593
+ "look_ahead_layers": [
594
+ 10
595
+ ],
596
+ "look_backward_layers": [
597
+ 0,
598
+ 20
599
+ ],
600
+ "max_length": 20,
601
+ "max_position_embeddings": 32768,
602
+ "mel_dim": 80,
603
+ "min_length": 0,
604
+ "model_type": "qwen2_5_omni_dit",
605
+ "no_repeat_ngram_size": 0,
606
+ "num_attention_heads": 16,
607
+ "num_beam_groups": 1,
608
+ "num_beams": 1,
609
+ "num_embeds": 8193,
610
+ "num_hidden_layers": 22,
611
+ "num_return_sequences": 1,
612
+ "output_attentions": false,
613
+ "output_hidden_states": false,
614
+ "output_scores": false,
615
+ "pad_token_id": 151643,
616
+ "prefix": null,
617
+ "problem_type": null,
618
+ "pruned_heads": {},
619
+ "remove_invalid_values": false,
620
+ "repeats": 2,
621
+ "repetition_penalty": 1.0,
622
+ "return_dict": true,
623
+ "return_dict_in_generate": false,
624
+ "rope_theta": 10000.0,
625
+ "sep_token_id": null,
626
+ "suppress_tokens": null,
627
+ "task_specific_params": null,
628
+ "temperature": 1.0,
629
+ "tf_legacy_loss": false,
630
+ "tie_encoder_decoder": false,
631
+ "tie_word_embeddings": true,
632
+ "tokenizer_class": null,
633
+ "top_k": 50,
634
+ "top_p": 1.0,
635
+ "torchscript": false,
636
+ "typical_p": 1.0,
637
+ "use_bfloat16": false
638
+ },
639
+ "dtype": "bfloat16",
640
+ "model_type": "qwen2_5_omni_token2wav",
641
+ "pad_token_id": 151643
642
+ },
643
+ "transformers_version": "4.56.0"
644
+ }
Qwen2.5-Omni-3B-Chuan/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 151643,
5
+ 151645
6
+ ],
7
+ "transformers_version": "4.56.0"
8
+ }
Qwen2.5-Omni-3B-Chuan/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
Qwen2.5-Omni-3B-Chuan/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee5ce647e0d4852a38d4a76408898e54374f9397c2dcefa7314537a55c1e6b21
3
+ size 1570766848
Qwen2.5-Omni-3B-Chuan/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:694f5ce71776f6caf0a94ace088cd7eeafd3c1a30e029c6e1c7a70f8221df4ba
3
+ size 1573912576
Qwen2.5-Omni-3B-Chuan/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aedb25618881ce9466eefb9872e19e81f30d281dd2b139b8c8111ae7a9025e7b
3
+ size 1582039040
Qwen2.5-Omni-3B-Chuan/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
Qwen2.5-Omni-3B-Chuan/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-3B-Chuan/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-3B-Chuan/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-3B-Chuan/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-3B-Chuan/tokenizer_config.json ADDED
@@ -0,0 +1,222 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "processor_class": "Qwen2_5OmniProcessor",
216
+ "split_special_tokens": false,
217
+ "tokenizer_class": "Qwen2Tokenizer",
218
+ "unk_token": null,
219
+ "video_token": "<|VIDEO|>",
220
+ "vision_bos_token": "<|vision_bos|>",
221
+ "vision_eos_token": "<|vision_eos|>"
222
+ }
Qwen2.5-Omni-3B-Chuan/video_preprocessor_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_pad": null,
12
+ "do_rescale": true,
13
+ "do_resize": true,
14
+ "do_sample_frames": false,
15
+ "feature_extractor_type": "WhisperFeatureExtractor",
16
+ "feature_size": 128,
17
+ "fps": null,
18
+ "hop_length": 160,
19
+ "image_mean": [
20
+ 0.48145466,
21
+ 0.4578275,
22
+ 0.40821073
23
+ ],
24
+ "image_std": [
25
+ 0.26862954,
26
+ 0.26130258,
27
+ 0.27577711
28
+ ],
29
+ "input_data_format": null,
30
+ "max_frames": 768,
31
+ "max_pixels": 12845056,
32
+ "merge_size": 2,
33
+ "min_frames": 4,
34
+ "min_pixels": 3136,
35
+ "n_fft": 400,
36
+ "n_samples": 4800000,
37
+ "nb_max_frames": 30000,
38
+ "num_frames": 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
+ "size_divisor": null,
53
+ "temporal_patch_size": 2,
54
+ "video_metadata": null,
55
+ "video_processor_type": "Qwen2VLVideoProcessor"
56
+ }
Qwen2.5-Omni-3B-Chuan/vocab.json ADDED
The diff for this file is too large to render. See raw diff