ASLP-lab commited on
Commit
aaae1ad
·
verified ·
1 Parent(s): 665edce

Upload folder using huggingface_hub

Browse files
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 +1,370 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/home/work_nfs23/sywang/code/asr_rl/sft_chuan/v0-20250729-234858",
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": 2,
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": 1.0,
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/sft_chuan/v0-20250729-234858/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": 1000.0,
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": 1000.0,
65
+ "dataloader_num_workers": 4,
66
+ "dataloader_prefetch_factor": null,
67
+ "past_index": -1,
68
+ "run_name": "/home/work_nfs23/sywang/code/asr_rl/sft_chuan/v0-20250729-234858",
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
+ "deepspeed": {
84
+ "fp16": {
85
+ "enabled": "auto",
86
+ "loss_scale": 0,
87
+ "loss_scale_window": 1000,
88
+ "initial_scale_power": 16,
89
+ "hysteresis": 2,
90
+ "min_loss_scale": 1
91
+ },
92
+ "bf16": {
93
+ "enabled": "auto"
94
+ },
95
+ "zero_optimization": {
96
+ "stage": 2,
97
+ "offload_optimizer": {
98
+ "device": "none",
99
+ "pin_memory": true
100
+ },
101
+ "allgather_partitions": true,
102
+ "allgather_bucket_size": 200000000.0,
103
+ "overlap_comm": false,
104
+ "reduce_scatter": true,
105
+ "reduce_bucket_size": 200000000.0,
106
+ "contiguous_gradients": true
107
+ },
108
+ "gradient_accumulation_steps": "auto",
109
+ "gradient_clipping": "auto",
110
+ "steps_per_print": 2000,
111
+ "train_batch_size": "auto",
112
+ "train_micro_batch_size_per_gpu": "auto",
113
+ "wall_clock_breakdown": false
114
+ },
115
+ "label_smoothing_factor": 0.0,
116
+ "optim": "adamw_torch",
117
+ "optim_args": null,
118
+ "adafactor": false,
119
+ "group_by_length": false,
120
+ "length_column_name": "length",
121
+ "report_to": [
122
+ "tensorboard"
123
+ ],
124
+ "ddp_find_unused_parameters": null,
125
+ "ddp_bucket_cap_mb": null,
126
+ "ddp_broadcast_buffers": null,
127
+ "dataloader_pin_memory": true,
128
+ "dataloader_persistent_workers": false,
129
+ "skip_memory_metrics": true,
130
+ "use_legacy_prediction_loop": false,
131
+ "push_to_hub": false,
132
+ "resume_from_checkpoint": null,
133
+ "hub_model_id": null,
134
+ "hub_strategy": "every_save",
135
+ "hub_token": null,
136
+ "hub_private_repo": null,
137
+ "hub_always_push": false,
138
+ "gradient_checkpointing": true,
139
+ "gradient_checkpointing_kwargs": null,
140
+ "include_inputs_for_metrics": false,
141
+ "include_for_metrics": [],
142
+ "eval_do_concat_batches": true,
143
+ "fp16_backend": "auto",
144
+ "push_to_hub_model_id": null,
145
+ "push_to_hub_organization": null,
146
+ "push_to_hub_token": null,
147
+ "mp_parameters": "",
148
+ "auto_find_batch_size": false,
149
+ "full_determinism": false,
150
+ "torchdynamo": null,
151
+ "ray_scope": "last",
152
+ "ddp_timeout": 18000000,
153
+ "torch_compile": false,
154
+ "torch_compile_backend": null,
155
+ "torch_compile_mode": null,
156
+ "include_tokens_per_second": false,
157
+ "include_num_input_tokens_seen": false,
158
+ "neftune_noise_alpha": null,
159
+ "optim_target_modules": null,
160
+ "batch_eval_metrics": false,
161
+ "eval_on_start": false,
162
+ "use_liger_kernel": false,
163
+ "eval_use_gather_object": false,
164
+ "average_tokens_across_devices": false,
165
+ "sortish_sampler": false,
166
+ "predict_with_generate": false,
167
+ "generation_max_length": null,
168
+ "generation_num_beams": null,
169
+ "generation_config": null,
170
+ "vit_gradient_checkpointing": null,
171
+ "check_model": true,
172
+ "acc_strategy": "token",
173
+ "train_dataloader_shuffle": true,
174
+ "max_epochs": null,
175
+ "aligner_lr": null,
176
+ "vit_lr": null,
177
+ "optimizer": null,
178
+ "use_logits_to_keep": null,
179
+ "channels": null,
180
+ "ds3_gather_for_generation": true,
181
+ "metric_warmup_step": 0,
182
+ "fsdp_num": 1,
183
+ "acc_steps": 1,
184
+ "eval_use_evalscope": false,
185
+ "eval_dataset": [],
186
+ "eval_dataset_args": null,
187
+ "eval_limit": null,
188
+ "eval_generation_config": null,
189
+ "model": "/home/work_nfs23/sywang/ckpt/Qwen2.5-Omni-3B",
190
+ "model_type": "qwen2_5_omni",
191
+ "model_revision": null,
192
+ "task_type": "causal_lm",
193
+ "torch_dtype": "bfloat16",
194
+ "attn_impl": "flash_attn",
195
+ "num_labels": null,
196
+ "problem_type": null,
197
+ "rope_scaling": null,
198
+ "device_map": null,
199
+ "max_memory": {},
200
+ "local_repo_path": null,
201
+ "init_strategy": null,
202
+ "template": "qwen2_5_omni",
203
+ "system": "You are a speech recognition model.",
204
+ "max_length": 2048,
205
+ "truncation_strategy": "delete",
206
+ "max_pixels": null,
207
+ "agent_template": null,
208
+ "norm_bbox": null,
209
+ "use_chat_template": true,
210
+ "padding_free": false,
211
+ "padding_side": "right",
212
+ "loss_scale": "default",
213
+ "sequence_parallel_size": 1,
214
+ "response_prefix": null,
215
+ "template_backend": "swift",
216
+ "dataset": [
217
+ "data/train_chaun.jsonl"
218
+ ],
219
+ "val_dataset": [],
220
+ "split_dataset_ratio": 0.0,
221
+ "dataset_num_proc": 1,
222
+ "load_from_cache_file": true,
223
+ "dataset_shuffle": true,
224
+ "val_dataset_shuffle": false,
225
+ "streaming": false,
226
+ "interleave_prob": null,
227
+ "stopping_strategy": "first_exhausted",
228
+ "shuffle_buffer_size": 1000,
229
+ "download_mode": "reuse_dataset_if_exists",
230
+ "columns": {},
231
+ "strict": false,
232
+ "model_name": null,
233
+ "model_author": null,
234
+ "custom_dataset_info": [],
235
+ "quant_method": null,
236
+ "quant_bits": null,
237
+ "hqq_axis": null,
238
+ "bnb_4bit_compute_dtype": "bfloat16",
239
+ "bnb_4bit_quant_type": "nf4",
240
+ "bnb_4bit_use_double_quant": true,
241
+ "bnb_4bit_quant_storage": null,
242
+ "max_new_tokens": 64,
243
+ "temperature": 0.0,
244
+ "top_k": null,
245
+ "top_p": null,
246
+ "repetition_penalty": null,
247
+ "num_beams": 1,
248
+ "stream": false,
249
+ "stop_words": [],
250
+ "logprobs": false,
251
+ "top_logprobs": null,
252
+ "ckpt_dir": null,
253
+ "lora_modules": [],
254
+ "tuner_backend": "peft",
255
+ "train_type": "lora",
256
+ "adapters": [],
257
+ "external_plugins": [],
258
+ "model_kwargs": {},
259
+ "load_args": false,
260
+ "load_data_args": false,
261
+ "packing": false,
262
+ "packing_cache": null,
263
+ "custom_register_path": [],
264
+ "use_hf": false,
265
+ "ignore_args_error": false,
266
+ "use_swift_lora": false,
267
+ "freeze_parameters": [
268
+ "thinker.audio_tower",
269
+ "thinker.visual",
270
+ "thinker.audio_tower.proj",
271
+ "thinker.visual.merger",
272
+ "talker",
273
+ "token2wav"
274
+ ],
275
+ "freeze_parameters_regex": null,
276
+ "freeze_parameters_ratio": 0.0,
277
+ "trainable_parameters": [],
278
+ "trainable_parameters_regex": null,
279
+ "freeze_llm": false,
280
+ "freeze_vit": true,
281
+ "freeze_aligner": true,
282
+ "target_modules": [
283
+ "all-linear"
284
+ ],
285
+ "target_regex": null,
286
+ "modules_to_save": [],
287
+ "lora_rank": 8,
288
+ "lora_alpha": 32,
289
+ "lora_dropout": 0.05,
290
+ "lora_bias": "none",
291
+ "lora_dtype": null,
292
+ "lorap_lr_ratio": null,
293
+ "use_rslora": false,
294
+ "use_dora": false,
295
+ "lora_ga_batch_size": 2,
296
+ "lora_ga_iters": 2,
297
+ "lora_ga_max_length": 1024,
298
+ "lora_ga_direction": "ArB2r",
299
+ "lora_ga_scale": "stable",
300
+ "lora_ga_stable_gamma": 16,
301
+ "init_weights": true,
302
+ "fourier_n_frequency": 2000,
303
+ "fourier_scaling": 300.0,
304
+ "boft_block_size": 4,
305
+ "boft_block_num": 0,
306
+ "boft_n_butterfly_factor": 1,
307
+ "boft_dropout": 0.0,
308
+ "vera_rank": 256,
309
+ "vera_projection_prng_key": 0,
310
+ "vera_dropout": 0.0,
311
+ "vera_d_initial": 0.1,
312
+ "adapter_act": "gelu",
313
+ "adapter_length": 128,
314
+ "use_galore": false,
315
+ "galore_target_modules": null,
316
+ "galore_rank": 128,
317
+ "galore_update_proj_gap": 50,
318
+ "galore_scale": 1.0,
319
+ "galore_proj_type": "std",
320
+ "galore_optim_per_parameter": false,
321
+ "galore_with_embedding": false,
322
+ "galore_quantization": false,
323
+ "galore_proj_quant": false,
324
+ "galore_proj_bits": 4,
325
+ "galore_proj_group_size": 256,
326
+ "galore_cos_threshold": 0.4,
327
+ "galore_gamma_proj": 2,
328
+ "galore_queue_size": 5,
329
+ "adalora_target_r": 8,
330
+ "adalora_init_r": 12,
331
+ "adalora_tinit": 0,
332
+ "adalora_tfinal": 0,
333
+ "adalora_deltaT": 1,
334
+ "adalora_beta1": 0.85,
335
+ "adalora_beta2": 0.85,
336
+ "adalora_orth_reg_weight": 0.5,
337
+ "llamapro_num_new_blocks": 4,
338
+ "llamapro_num_groups": null,
339
+ "lisa_activated_layers": 0,
340
+ "lisa_step_interval": 20,
341
+ "reft_layer_key": null,
342
+ "reft_layers": null,
343
+ "reft_rank": 4,
344
+ "reft_intervention_type": "LoreftIntervention",
345
+ "reft_args": null,
346
+ "swanlab_token": null,
347
+ "swanlab_project": null,
348
+ "swanlab_workspace": null,
349
+ "swanlab_exp_name": null,
350
+ "swanlab_lark_webhook_url": null,
351
+ "swanlab_lark_secret": null,
352
+ "swanlab_mode": "cloud",
353
+ "add_version": true,
354
+ "resume_only_model": false,
355
+ "create_checkpoint_symlink": false,
356
+ "lazy_tokenize": true,
357
+ "loss_type": null,
358
+ "metric": null,
359
+ "zero_hpz_partition_size": null,
360
+ "rank": 0,
361
+ "global_world_size": 8,
362
+ "local_world_size": 8,
363
+ "model_suffix": "Qwen2.5-Omni-3B",
364
+ "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'}, config=None, task_type='causal_lm', num_labels=None)",
365
+ "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 0x746e9ed7b060>, model_arch='qwen2_5_omni', 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'])",
366
+ "model_dir": "/home/work_nfs23/sywang/ckpt/Qwen2.5-Omni-3B",
367
+ "hub": "<class 'swift.hub.hub.MSHub'>",
368
+ "evaluation_strategy": "steps",
369
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/home/work_nfs23/sywang/code/asr_rl/sft_chuan/v0-20250729-234858', 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=2, 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=1.0, 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/sft_chuan/v0-20250729-234858/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=1000, 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=1000.0, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/home/work_nfs23/sywang/code/asr_rl/sft_chuan/v0-20250729-234858', 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), 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, 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, 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, vit_gradient_checkpointing=True, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, optimizer=None, use_logits_to_keep=None, channels=None, ds3_gather_for_generation=True, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, sft_alpha=0, train_type='lora', local_repo_path=None, galore_config=None)"
370
+ }
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 +1,573 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5OmniForConditionalGeneration"
4
+ ],
5
+ "enable_audio_output": true,
6
+ "enable_talker": true,
7
+ "hidden_size": 2048,
8
+ "keys_to_ignore_at_inference": [
9
+ "past_key_values",
10
+ "hidden_states",
11
+ "attention_mask"
12
+ ],
13
+ "model_type": "qwen2_5_omni",
14
+ "pad_token_id": 151643,
15
+ "talker_config": {
16
+ "_name_or_path": "Qwen2.5-Omni-3B/talker",
17
+ "architectures": [
18
+ "Qwen2OmniTalkerForConditionalGeneration"
19
+ ],
20
+ "attention_dropout": 0.0,
21
+ "audio_end_token_id": 151648,
22
+ "audio_start_token_id": 151647,
23
+ "audio_token_index": 151646,
24
+ "embedding_size": 2048,
25
+ "head_dim": 64,
26
+ "hidden_act": "silu",
27
+ "hidden_size": 896,
28
+ "image_token_index": 151655,
29
+ "init_std": 0.02,
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 4864,
32
+ "max_position_embeddings": 32768,
33
+ "max_window_layers": 28,
34
+ "model_type": "qwen2_5_omni_talker",
35
+ "num_attention_heads": 14,
36
+ "num_hidden_layers": 24,
37
+ "num_key_value_heads": 2,
38
+ "position_id_per_seconds": 25,
39
+ "rms_norm_eps": 1e-06,
40
+ "rope_scaling": {
41
+ "mrope_section": [
42
+ 16,
43
+ 16,
44
+ 0
45
+ ],
46
+ "rope_type": "default",
47
+ "type": "default"
48
+ },
49
+ "rope_theta": 1000000.0,
50
+ "seconds_per_chunk": 2,
51
+ "sliding_window": 32768,
52
+ "spatial_merge_size": 2,
53
+ "torch_dtype": "bfloat16",
54
+ "tts_codec_end_token_id": 8294,
55
+ "tts_codec_mask_token_id": 8296,
56
+ "tts_codec_pad_token_id": 8292,
57
+ "tts_codec_start_token_id": 8293,
58
+ "tts_text_end_token_id": 151861,
59
+ "tts_text_pad_token_id": 151859,
60
+ "tts_text_start_token_id": 151860,
61
+ "use_cache": true,
62
+ "use_sliding_window": false,
63
+ "video_token_index": 151656,
64
+ "vision_end_token_id": 151653,
65
+ "vision_start_token_id": 151652,
66
+ "vocab_size": 8448
67
+ },
68
+ "thinker_config": {
69
+ "_name_or_path": "Qwen2.5-Omni-3B/thinker",
70
+ "architectures": [
71
+ "Qwen2OmniNaViTThinkerForConditionalGeneration"
72
+ ],
73
+ "audio_config": {
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
+ "initializer_range": 0.02,
107
+ "is_decoder": false,
108
+ "is_encoder_decoder": false,
109
+ "label2id": {
110
+ "LABEL_0": 0,
111
+ "LABEL_1": 1
112
+ },
113
+ "length_penalty": 1.0,
114
+ "max_length": 20,
115
+ "max_source_positions": 1500,
116
+ "min_length": 0,
117
+ "model_type": "qwen2_5_omni_audio_encoder",
118
+ "n_window": 100,
119
+ "no_repeat_ngram_size": 0,
120
+ "num_beam_groups": 1,
121
+ "num_beams": 1,
122
+ "num_hidden_layers": 32,
123
+ "num_mel_bins": 128,
124
+ "num_return_sequences": 1,
125
+ "output_attentions": false,
126
+ "output_dim": 2048,
127
+ "output_hidden_states": false,
128
+ "output_scores": false,
129
+ "pad_token_id": null,
130
+ "prefix": null,
131
+ "problem_type": null,
132
+ "pruned_heads": {},
133
+ "remove_invalid_values": false,
134
+ "repetition_penalty": 1.0,
135
+ "return_dict": true,
136
+ "return_dict_in_generate": false,
137
+ "scale_embedding": false,
138
+ "sep_token_id": null,
139
+ "suppress_tokens": null,
140
+ "task_specific_params": null,
141
+ "temperature": 1.0,
142
+ "tf_legacy_loss": false,
143
+ "tie_encoder_decoder": false,
144
+ "tie_word_embeddings": true,
145
+ "tokenizer_class": null,
146
+ "top_k": 50,
147
+ "top_p": 1.0,
148
+ "torch_dtype": null,
149
+ "torchscript": false,
150
+ "typical_p": 1.0,
151
+ "use_bfloat16": false
152
+ },
153
+ "audio_end_token_id": 151648,
154
+ "audio_start_token_id": 151647,
155
+ "audio_token_index": 151646,
156
+ "bos_token_id": 151644,
157
+ "eos_token_id": 151645,
158
+ "ignore_index": -100,
159
+ "image_token_index": 151655,
160
+ "init_std": 0.02,
161
+ "initializer_range": 0.02,
162
+ "model_type": "qwen2_5_omni_thinker",
163
+ "pad_token_id": 151643,
164
+ "position_id_per_seconds": 25,
165
+ "seconds_per_chunk": 2,
166
+ "text_config": {
167
+ "_name_or_path": "",
168
+ "add_cross_attention": false,
169
+ "architectures": null,
170
+ "attention_dropout": 0.0,
171
+ "bad_words_ids": null,
172
+ "begin_suppress_tokens": null,
173
+ "bos_token_id": null,
174
+ "chunk_size_feed_forward": 0,
175
+ "cross_attention_hidden_size": null,
176
+ "decoder_start_token_id": null,
177
+ "diversity_penalty": 0.0,
178
+ "do_sample": false,
179
+ "early_stopping": false,
180
+ "encoder_no_repeat_ngram_size": 0,
181
+ "eos_token_id": null,
182
+ "exponential_decay_length_penalty": null,
183
+ "finetuning_task": null,
184
+ "forced_bos_token_id": null,
185
+ "forced_eos_token_id": null,
186
+ "hidden_act": "silu",
187
+ "hidden_size": 2048,
188
+ "id2label": {
189
+ "0": "LABEL_0",
190
+ "1": "LABEL_1"
191
+ },
192
+ "init_std": 0.02,
193
+ "initializer_range": 0.02,
194
+ "intermediate_size": 11008,
195
+ "is_decoder": false,
196
+ "is_encoder_decoder": false,
197
+ "label2id": {
198
+ "LABEL_0": 0,
199
+ "LABEL_1": 1
200
+ },
201
+ "length_penalty": 1.0,
202
+ "max_length": 20,
203
+ "max_position_embeddings": 32768,
204
+ "max_window_layers": 70,
205
+ "min_length": 0,
206
+ "model_type": "qwen2_5_omni_text",
207
+ "no_repeat_ngram_size": 0,
208
+ "num_attention_heads": 16,
209
+ "num_beam_groups": 1,
210
+ "num_beams": 1,
211
+ "num_hidden_layers": 36,
212
+ "num_key_value_heads": 2,
213
+ "num_return_sequences": 1,
214
+ "output_attentions": false,
215
+ "output_hidden_states": false,
216
+ "output_scores": false,
217
+ "pad_token_id": null,
218
+ "prefix": null,
219
+ "problem_type": null,
220
+ "pruned_heads": {},
221
+ "remove_invalid_values": false,
222
+ "repetition_penalty": 1.0,
223
+ "return_dict": true,
224
+ "return_dict_in_generate": false,
225
+ "rms_norm_eps": 1e-06,
226
+ "rope_scaling": {
227
+ "mrope_section": [
228
+ 16,
229
+ 24,
230
+ 24
231
+ ],
232
+ "rope_type": "default",
233
+ "type": "default"
234
+ },
235
+ "rope_theta": 1000000.0,
236
+ "sep_token_id": null,
237
+ "sliding_window": 32768,
238
+ "suppress_tokens": null,
239
+ "task_specific_params": null,
240
+ "temperature": 1.0,
241
+ "tf_legacy_loss": false,
242
+ "tie_encoder_decoder": false,
243
+ "tie_word_embeddings": false,
244
+ "tokenizer_class": null,
245
+ "top_k": 50,
246
+ "top_p": 1.0,
247
+ "torch_dtype": null,
248
+ "torchscript": false,
249
+ "typical_p": 1.0,
250
+ "use_bfloat16": false,
251
+ "use_cache": true,
252
+ "use_sliding_window": false,
253
+ "vocab_size": 151936
254
+ },
255
+ "torch_dtype": "bfloat16",
256
+ "user_token_id": 872,
257
+ "video_token_index": 151656,
258
+ "vision_config": {
259
+ "_name_or_path": "",
260
+ "add_cross_attention": false,
261
+ "architectures": null,
262
+ "bad_words_ids": null,
263
+ "begin_suppress_tokens": null,
264
+ "bos_token_id": null,
265
+ "chunk_size_feed_forward": 0,
266
+ "cross_attention_hidden_size": null,
267
+ "decoder_start_token_id": null,
268
+ "depth": 32,
269
+ "diversity_penalty": 0.0,
270
+ "do_sample": false,
271
+ "early_stopping": false,
272
+ "embed_dim": 1280,
273
+ "encoder_no_repeat_ngram_size": 0,
274
+ "eos_token_id": null,
275
+ "exponential_decay_length_penalty": null,
276
+ "finetuning_task": null,
277
+ "forced_bos_token_id": null,
278
+ "forced_eos_token_id": null,
279
+ "fullatt_block_indexes": [
280
+ 7,
281
+ 15,
282
+ 23,
283
+ 31
284
+ ],
285
+ "hidden_act": "silu",
286
+ "hidden_size": 1280,
287
+ "id2label": {
288
+ "0": "LABEL_0",
289
+ "1": "LABEL_1"
290
+ },
291
+ "in_channels": 3,
292
+ "in_chans": 3,
293
+ "init_std": 0.02,
294
+ "initializer_range": 0.02,
295
+ "intermediate_size": 3420,
296
+ "is_decoder": false,
297
+ "is_encoder_decoder": false,
298
+ "label2id": {
299
+ "LABEL_0": 0,
300
+ "LABEL_1": 1
301
+ },
302
+ "length_penalty": 1.0,
303
+ "max_length": 20,
304
+ "min_length": 0,
305
+ "model_type": "qwen2_5_omni_vision_encoder",
306
+ "no_repeat_ngram_size": 0,
307
+ "num_beam_groups": 1,
308
+ "num_beams": 1,
309
+ "num_heads": 16,
310
+ "num_return_sequences": 1,
311
+ "out_hidden_size": 2048,
312
+ "output_attentions": false,
313
+ "output_hidden_states": false,
314
+ "output_scores": false,
315
+ "pad_token_id": null,
316
+ "patch_size": 14,
317
+ "prefix": null,
318
+ "problem_type": null,
319
+ "pruned_heads": {},
320
+ "remove_invalid_values": false,
321
+ "repetition_penalty": 1.0,
322
+ "return_dict": true,
323
+ "return_dict_in_generate": false,
324
+ "sep_token_id": null,
325
+ "spatial_merge_size": 2,
326
+ "spatial_patch_size": 14,
327
+ "suppress_tokens": null,
328
+ "task_specific_params": null,
329
+ "temperature": 1.0,
330
+ "temporal_patch_size": 2,
331
+ "tf_legacy_loss": false,
332
+ "tie_encoder_decoder": false,
333
+ "tie_word_embeddings": true,
334
+ "tokenizer_class": null,
335
+ "tokens_per_second": 25,
336
+ "top_k": 50,
337
+ "top_p": 1.0,
338
+ "torch_dtype": null,
339
+ "torchscript": false,
340
+ "typical_p": 1.0,
341
+ "use_bfloat16": false,
342
+ "window_size": 112
343
+ },
344
+ "vision_end_token_id": 151653,
345
+ "vision_start_token_id": 151652,
346
+ "vision_token_id": 151654
347
+ },
348
+ "token2wav_config": {
349
+ "bigvgan_config": {
350
+ "_name_or_path": "",
351
+ "add_cross_attention": false,
352
+ "architectures": null,
353
+ "bad_words_ids": null,
354
+ "begin_suppress_tokens": null,
355
+ "bos_token_id": null,
356
+ "chunk_size_feed_forward": 0,
357
+ "cross_attention_hidden_size": null,
358
+ "decoder_start_token_id": null,
359
+ "diversity_penalty": 0.0,
360
+ "do_sample": false,
361
+ "early_stopping": false,
362
+ "encoder_no_repeat_ngram_size": 0,
363
+ "eos_token_id": null,
364
+ "exponential_decay_length_penalty": null,
365
+ "finetuning_task": null,
366
+ "forced_bos_token_id": null,
367
+ "forced_eos_token_id": null,
368
+ "id2label": {
369
+ "0": "LABEL_0",
370
+ "1": "LABEL_1"
371
+ },
372
+ "is_decoder": false,
373
+ "is_encoder_decoder": false,
374
+ "label2id": {
375
+ "LABEL_0": 0,
376
+ "LABEL_1": 1
377
+ },
378
+ "length_penalty": 1.0,
379
+ "max_length": 20,
380
+ "mel_dim": 80,
381
+ "min_length": 0,
382
+ "model_type": "qwen2_5_omni_bigvgan",
383
+ "no_repeat_ngram_size": 0,
384
+ "num_beam_groups": 1,
385
+ "num_beams": 1,
386
+ "num_return_sequences": 1,
387
+ "output_attentions": false,
388
+ "output_hidden_states": false,
389
+ "output_scores": false,
390
+ "pad_token_id": null,
391
+ "prefix": null,
392
+ "problem_type": null,
393
+ "pruned_heads": {},
394
+ "remove_invalid_values": false,
395
+ "repetition_penalty": 1.0,
396
+ "resblock_dilation_sizes": [
397
+ [
398
+ 1,
399
+ 3,
400
+ 5
401
+ ],
402
+ [
403
+ 1,
404
+ 3,
405
+ 5
406
+ ],
407
+ [
408
+ 1,
409
+ 3,
410
+ 5
411
+ ]
412
+ ],
413
+ "resblock_kernel_sizes": [
414
+ 3,
415
+ 7,
416
+ 11
417
+ ],
418
+ "return_dict": true,
419
+ "return_dict_in_generate": false,
420
+ "sep_token_id": null,
421
+ "suppress_tokens": null,
422
+ "task_specific_params": null,
423
+ "temperature": 1.0,
424
+ "tf_legacy_loss": false,
425
+ "tie_encoder_decoder": false,
426
+ "tie_word_embeddings": true,
427
+ "tokenizer_class": null,
428
+ "top_k": 50,
429
+ "top_p": 1.0,
430
+ "torch_dtype": null,
431
+ "torchscript": false,
432
+ "typical_p": 1.0,
433
+ "upsample_initial_channel": 1536,
434
+ "upsample_kernel_sizes": [
435
+ 11,
436
+ 7,
437
+ 4,
438
+ 4,
439
+ 4,
440
+ 4
441
+ ],
442
+ "upsample_rates": [
443
+ 5,
444
+ 3,
445
+ 2,
446
+ 2,
447
+ 2,
448
+ 2
449
+ ],
450
+ "use_bfloat16": false,
451
+ "use_bias_at_final": false
452
+ },
453
+ "dit_config": {
454
+ "_name_or_path": "",
455
+ "add_cross_attention": false,
456
+ "architectures": null,
457
+ "bad_words_ids": null,
458
+ "begin_suppress_tokens": null,
459
+ "block_size": 24,
460
+ "bos_token_id": null,
461
+ "chunk_size_feed_forward": 0,
462
+ "cross_attention_hidden_size": null,
463
+ "decoder_start_token_id": null,
464
+ "depth": 22,
465
+ "dim": 1024,
466
+ "diversity_penalty": 0.0,
467
+ "do_sample": false,
468
+ "dropout": 0.1,
469
+ "early_stopping": false,
470
+ "emb_dim": 512,
471
+ "enc_attention_channels": 64,
472
+ "enc_channels": [
473
+ 256,
474
+ 256,
475
+ 256,
476
+ 256,
477
+ 768
478
+ ],
479
+ "enc_dilations": [
480
+ 1,
481
+ 2,
482
+ 3,
483
+ 4,
484
+ 1
485
+ ],
486
+ "enc_dim": 128,
487
+ "enc_emb_dim": 192,
488
+ "enc_global_context": true,
489
+ "enc_kernel_sizes": [
490
+ 5,
491
+ 3,
492
+ 3,
493
+ 3,
494
+ 1
495
+ ],
496
+ "enc_lin_neurons": 192,
497
+ "enc_res2net_scale": 2,
498
+ "enc_se_channels": 64,
499
+ "encoder_no_repeat_ngram_size": 0,
500
+ "eos_token_id": null,
501
+ "exponential_decay_length_penalty": null,
502
+ "ff_mult": 2,
503
+ "finetuning_task": null,
504
+ "forced_bos_token_id": null,
505
+ "forced_eos_token_id": null,
506
+ "head_dim": 64,
507
+ "heads": 16,
508
+ "hidden_size": 1024,
509
+ "id2label": {
510
+ "0": "LABEL_0",
511
+ "1": "LABEL_1"
512
+ },
513
+ "is_decoder": false,
514
+ "is_encoder_decoder": false,
515
+ "label2id": {
516
+ "LABEL_0": 0,
517
+ "LABEL_1": 1
518
+ },
519
+ "length_penalty": 1.0,
520
+ "look_ahead_layers": [
521
+ 10
522
+ ],
523
+ "look_backward_layers": [
524
+ 0,
525
+ 20
526
+ ],
527
+ "max_length": 20,
528
+ "max_position_embeddings": 32768,
529
+ "mel_dim": 80,
530
+ "min_length": 0,
531
+ "model_type": "qwen2_5_omni_dit",
532
+ "no_repeat_ngram_size": 0,
533
+ "num_attention_heads": 16,
534
+ "num_beam_groups": 1,
535
+ "num_beams": 1,
536
+ "num_embeds": 8193,
537
+ "num_hidden_layers": 22,
538
+ "num_return_sequences": 1,
539
+ "output_attentions": false,
540
+ "output_hidden_states": false,
541
+ "output_scores": false,
542
+ "pad_token_id": null,
543
+ "prefix": null,
544
+ "problem_type": null,
545
+ "pruned_heads": {},
546
+ "remove_invalid_values": false,
547
+ "repeats": 2,
548
+ "repetition_penalty": 1.0,
549
+ "return_dict": true,
550
+ "return_dict_in_generate": false,
551
+ "rope_theta": 10000.0,
552
+ "sep_token_id": null,
553
+ "suppress_tokens": null,
554
+ "task_specific_params": null,
555
+ "temperature": 1.0,
556
+ "tf_legacy_loss": false,
557
+ "tie_encoder_decoder": false,
558
+ "tie_word_embeddings": true,
559
+ "tokenizer_class": null,
560
+ "top_k": 50,
561
+ "top_p": 1.0,
562
+ "torch_dtype": "float32",
563
+ "torchscript": false,
564
+ "typical_p": 1.0,
565
+ "use_bfloat16": false
566
+ },
567
+ "model_type": "qwen2_5_omni_token2wav",
568
+ "pad_token_id": 151643,
569
+ "torch_dtype": "bfloat16"
570
+ },
571
+ "torch_dtype": "bfloat16",
572
+ "transformers_version": "4.52.3"
573
+ }
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": "4.52.3"
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 sha256:0bf191da971b473c15401d6e30c74af2d63a6a3d529d12588923fc31b4b357eb
3
+ size 4994850880
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 sha256:5bb9b78fcc9c696802de4924c24186e9a074739675f3b675cb3a4a022eae3cd1
3
+ size 4999787448
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 sha256:8f2138170a87ec604b53232491a96d6dcf19e0724aca37e69aace143e508b170
3
+ size 1978024880
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 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_kwargs_names": [
3
+ "do_convert_rgb",
4
+ "do_resize",
5
+ "size",
6
+ "size_divisor",
7
+ "default_to_square",
8
+ "resample",
9
+ "do_rescale",
10
+ "rescale_factor",
11
+ "do_normalize",
12
+ "image_mean",
13
+ "image_std",
14
+ "do_pad",
15
+ "do_center_crop",
16
+ "crop_size",
17
+ "data_format",
18
+ "input_data_format",
19
+ "device",
20
+ "min_pixels",
21
+ "max_pixels",
22
+ "patch_size",
23
+ "temporal_patch_size",
24
+ "merge_size"
25
+ ],
26
+ "chunk_length": 300,
27
+ "crop_size": null,
28
+ "data_format": "channels_first",
29
+ "default_to_square": true,
30
+ "device": null,
31
+ "dither": 0.0,
32
+ "do_center_crop": null,
33
+ "do_convert_rgb": true,
34
+ "do_normalize": true,
35
+ "do_pad": null,
36
+ "do_rescale": true,
37
+ "do_resize": true,
38
+ "feature_extractor_type": "WhisperFeatureExtractor",
39
+ "feature_size": 128,
40
+ "hop_length": 160,
41
+ "image_mean": [
42
+ 0.48145466,
43
+ 0.4578275,
44
+ 0.40821073
45
+ ],
46
+ "image_processor_type": "Qwen2VLImageProcessor",
47
+ "image_std": [
48
+ 0.26862954,
49
+ 0.26130258,
50
+ 0.27577711
51
+ ],
52
+ "input_data_format": null,
53
+ "max_pixels": 12845056,
54
+ "merge_size": 2,
55
+ "min_pixels": 3136,
56
+ "model_valid_processing_keys": [
57
+ "do_convert_rgb",
58
+ "do_resize",
59
+ "size",
60
+ "size_divisor",
61
+ "default_to_square",
62
+ "resample",
63
+ "do_rescale",
64
+ "rescale_factor",
65
+ "do_normalize",
66
+ "image_mean",
67
+ "image_std",
68
+ "do_pad",
69
+ "do_center_crop",
70
+ "crop_size",
71
+ "data_format",
72
+ "input_data_format",
73
+ "device",
74
+ "min_pixels",
75
+ "max_pixels",
76
+ "patch_size",
77
+ "temporal_patch_size",
78
+ "merge_size"
79
+ ],
80
+ "n_fft": 400,
81
+ "n_samples": 4800000,
82
+ "nb_max_frames": 30000,
83
+ "padding_side": "right",
84
+ "padding_value": 0.0,
85
+ "patch_size": 14,
86
+ "processor_class": "Qwen2_5OmniProcessor",
87
+ "resample": 3,
88
+ "rescale_factor": 0.00392156862745098,
89
+ "return_attention_mask": true,
90
+ "sampling_rate": 16000,
91
+ "size": {
92
+ "longest_edge": 12845056,
93
+ "shortest_edge": 3136
94
+ },
95
+ "size_divisor": null,
96
+ "temporal_patch_size": 2,
97
+ "video_processor_type": "Qwen2VLVideoProcessor"
98
+ }
Qwen2.5-Omni-3B-Chuan/vocab.json ADDED
The diff for this file is too large to render. See raw diff