Hugging Face's logo

Evan-Lin
/
captioner-sft

Safetensors
qwen2_5_omni
Model card Files
xet
 Community
Evan-Lin commited on
Commit
b0f59a7
·
verified ·
1 Parent(s): ec10d99

Upload folder using huggingface_hub

Browse files
Files changed (19) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +24 -0
  3. args.json +366 -0
  4. chat_template.jinja +7 -0
  5. config.json +644 -0
  6. generation_config.json +8 -0
  7. merges.txt +0 -0
  8. model-00001-of-00002.safetensors +3 -0
  9. model-00002-of-00002.safetensors +3 -0
  10. model.safetensors.index.json +0 -0
  11. preprocessor_config.json +31 -0
  12. special_tokens_map.json +38 -0
  13. spk_dict.pt +3 -0
  14. tokenizer.json +3 -0
  15. tokenizer_config.json +222 -0
  16. trainer_state.json +0 -0
  17. training_args.bin +3 -0
  18. video_preprocessor_config.json +55 -0
  19. 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|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
+ }
args.json ADDED
@@ -0,0 +1,366 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/work/yuxiang1234/Audio-Captioner/ckpts/qwen2.5-omni-3b/sft_full/v5-20260510-200923",
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": 16,
10
+ "per_device_eval_batch_size": 8,
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": 2e-05,
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": "/work/yuxiang1234/Audio-Captioner/ckpts/qwen2.5-omni-3b/sft_full/v5-20260510-200923/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": 4,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": true,
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
+ "bf16": true,
51
+ "fp16": false,
52
+ "fp16_opt_level": "O1",
53
+ "half_precision_backend": "auto",
54
+ "bf16_full_eval": false,
55
+ "fp16_full_eval": false,
56
+ "tf32": null,
57
+ "local_rank": 0,
58
+ "ddp_backend": null,
59
+ "tpu_num_cores": null,
60
+ "tpu_metrics_debug": false,
61
+ "debug": null,
62
+ "dataloader_drop_last": false,
63
+ "eval_steps": 1000.0,
64
+ "dataloader_num_workers": 8,
65
+ "dataloader_prefetch_factor": null,
66
+ "past_index": -1,
67
+ "run_name": "/work/yuxiang1234/Audio-Captioner/ckpts/qwen2.5-omni-3b/sft_full/v5-20260510-200923",
68
+ "disable_tqdm": null,
69
+ "remove_unused_columns": true,
70
+ "label_names": null,
71
+ "load_best_model_at_end": false,
72
+ "metric_for_best_model": "loss",
73
+ "greater_is_better": false,
74
+ "ignore_data_skip": false,
75
+ "fsdp": [],
76
+ "fsdp_min_num_params": 0,
77
+ "fsdp_config": null,
78
+ "fsdp_transformer_layer_cls_to_wrap": null,
79
+ "accelerator_config": {
80
+ "dispatch_batches": false
81
+ },
82
+ "parallelism_config": null,
83
+ "deepspeed": null,
84
+ "label_smoothing_factor": 0.0,
85
+ "optim": "adamw_torch_fused",
86
+ "optim_args": null,
87
+ "adafactor": false,
88
+ "group_by_length": false,
89
+ "length_column_name": "length",
90
+ "report_to": [
91
+ "wandb"
92
+ ],
93
+ "project": "huggingface",
94
+ "trackio_space_id": "trackio",
95
+ "ddp_find_unused_parameters": null,
96
+ "ddp_bucket_cap_mb": null,
97
+ "ddp_broadcast_buffers": null,
98
+ "dataloader_pin_memory": true,
99
+ "dataloader_persistent_workers": true,
100
+ "skip_memory_metrics": true,
101
+ "use_legacy_prediction_loop": false,
102
+ "push_to_hub": false,
103
+ "resume_from_checkpoint": null,
104
+ "hub_model_id": null,
105
+ "hub_strategy": "every_save",
106
+ "hub_token": null,
107
+ "hub_private_repo": null,
108
+ "hub_always_push": false,
109
+ "hub_revision": null,
110
+ "gradient_checkpointing": true,
111
+ "gradient_checkpointing_kwargs": null,
112
+ "include_inputs_for_metrics": false,
113
+ "include_for_metrics": [],
114
+ "eval_do_concat_batches": true,
115
+ "fp16_backend": "auto",
116
+ "push_to_hub_model_id": null,
117
+ "push_to_hub_organization": null,
118
+ "push_to_hub_token": null,
119
+ "mp_parameters": "",
120
+ "auto_find_batch_size": false,
121
+ "full_determinism": false,
122
+ "torchdynamo": null,
123
+ "ray_scope": "last",
124
+ "ddp_timeout": 18000000,
125
+ "torch_compile": false,
126
+ "torch_compile_backend": null,
127
+ "torch_compile_mode": null,
128
+ "include_tokens_per_second": false,
129
+ "include_num_input_tokens_seen": false,
130
+ "neftune_noise_alpha": null,
131
+ "optim_target_modules": null,
132
+ "batch_eval_metrics": false,
133
+ "eval_on_start": false,
134
+ "use_liger_kernel": false,
135
+ "liger_kernel_config": null,
136
+ "eval_use_gather_object": false,
137
+ "average_tokens_across_devices": true,
138
+ "sortish_sampler": false,
139
+ "predict_with_generate": false,
140
+ "generation_max_length": null,
141
+ "generation_num_beams": null,
142
+ "generation_config": null,
143
+ "tuner_backend": "peft",
144
+ "vit_gradient_checkpointing": null,
145
+ "router_aux_loss_coef": 0.0,
146
+ "enable_dft_loss": false,
147
+ "enable_channel_loss": false,
148
+ "check_model": false,
149
+ "acc_strategy": "token",
150
+ "train_dataloader_shuffle": true,
151
+ "max_epochs": null,
152
+ "aligner_lr": null,
153
+ "vit_lr": null,
154
+ "use_logits_to_keep": null,
155
+ "ds3_gather_for_generation": true,
156
+ "resume_only_model": false,
157
+ "optimizer": null,
158
+ "loss_type": null,
159
+ "metric": null,
160
+ "eval_use_evalscope": false,
161
+ "eval_dataset": [],
162
+ "eval_dataset_args": null,
163
+ "eval_limit": null,
164
+ "eval_generation_config": null,
165
+ "extra_eval_args": null,
166
+ "use_flash_ckpt": false,
167
+ "use_ray": false,
168
+ "ray_exp_name": null,
169
+ "device_groups": null,
170
+ "model": "Qwen/Qwen2.5-Omni-3B",
171
+ "model_type": "qwen2_5_omni",
172
+ "model_revision": null,
173
+ "task_type": "causal_lm",
174
+ "torch_dtype": "bfloat16",
175
+ "attn_impl": null,
176
+ "new_special_tokens": [],
177
+ "num_labels": null,
178
+ "problem_type": null,
179
+ "rope_scaling": null,
180
+ "device_map": null,
181
+ "max_memory": {},
182
+ "max_model_len": null,
183
+ "local_repo_path": null,
184
+ "init_strategy": null,
185
+ "template": "qwen2_5_omni",
186
+ "system": null,
187
+ "max_length": 4096,
188
+ "truncation_strategy": "delete",
189
+ "max_pixels": null,
190
+ "agent_template": null,
191
+ "norm_bbox": null,
192
+ "use_chat_template": true,
193
+ "padding_side": "right",
194
+ "padding_free": false,
195
+ "loss_scale": "default",
196
+ "sequence_parallel_size": 1,
197
+ "template_backend": "swift",
198
+ "response_prefix": null,
199
+ "enable_thinking": null,
200
+ "add_non_thinking_prefix": true,
201
+ "dataset": [
202
+ "audioset_balanced_captioning",
203
+ "msp_podcast_captioning",
204
+ "expresso_captioning",
205
+ "musicbench_captioning"
206
+ ],
207
+ "val_dataset": [],
208
+ "cached_dataset": [],
209
+ "cached_val_dataset": [],
210
+ "split_dataset_ratio": 0.0,
211
+ "dataset_num_proc": 4,
212
+ "load_from_cache_file": false,
213
+ "dataset_shuffle": true,
214
+ "val_dataset_shuffle": false,
215
+ "streaming": false,
216
+ "interleave_prob": null,
217
+ "stopping_strategy": "first_exhausted",
218
+ "shuffle_buffer_size": 1000,
219
+ "download_mode": "reuse_dataset_if_exists",
220
+ "columns": {},
221
+ "strict": false,
222
+ "model_name": null,
223
+ "model_author": null,
224
+ "custom_dataset_info": [],
225
+ "quant_method": null,
226
+ "quant_bits": null,
227
+ "hqq_axis": null,
228
+ "bnb_4bit_compute_dtype": "bfloat16",
229
+ "bnb_4bit_quant_type": "nf4",
230
+ "bnb_4bit_use_double_quant": true,
231
+ "bnb_4bit_quant_storage": null,
232
+ "max_new_tokens": 64,
233
+ "temperature": 0.0,
234
+ "top_k": null,
235
+ "top_p": null,
236
+ "repetition_penalty": null,
237
+ "num_beams": 1,
238
+ "stream": false,
239
+ "stop_words": [],
240
+ "logprobs": false,
241
+ "top_logprobs": null,
242
+ "structured_outputs_regex": null,
243
+ "ckpt_dir": null,
244
+ "lora_modules": [],
245
+ "train_type": "full",
246
+ "adapters": [],
247
+ "external_plugins": [],
248
+ "model_kwargs": {},
249
+ "load_args": false,
250
+ "load_data_args": false,
251
+ "packing": false,
252
+ "packing_length": null,
253
+ "packing_num_proc": 1,
254
+ "lazy_tokenize": true,
255
+ "custom_register_path": [
256
+ "/work/yuxiang1234/Audio-Captioner/custom_dataset.py",
257
+ "/work/yuxiang1234/Audio-Captioner/custom_metric.py"
258
+ ],
259
+ "use_hf": true,
260
+ "ignore_args_error": false,
261
+ "use_swift_lora": false,
262
+ "freeze_parameters": [
263
+ "thinker.audio_tower",
264
+ "thinker.visual",
265
+ "thinker.audio_tower.proj",
266
+ "thinker.visual.merger",
267
+ "talker",
268
+ "token2wav"
269
+ ],
270
+ "freeze_parameters_regex": null,
271
+ "freeze_parameters_ratio": 0.0,
272
+ "trainable_parameters": [],
273
+ "trainable_parameters_regex": null,
274
+ "freeze_llm": false,
275
+ "freeze_vit": true,
276
+ "freeze_aligner": true,
277
+ "target_modules": [
278
+ "all-linear"
279
+ ],
280
+ "target_regex": null,
281
+ "target_parameters": null,
282
+ "modules_to_save": [],
283
+ "lora_rank": 8,
284
+ "lora_alpha": 32,
285
+ "lora_dropout": 0.05,
286
+ "lora_bias": "none",
287
+ "lora_dtype": null,
288
+ "lorap_lr_ratio": null,
289
+ "use_rslora": false,
290
+ "use_dora": false,
291
+ "lora_ga_batch_size": 2,
292
+ "lora_ga_iters": 2,
293
+ "lora_ga_max_length": 1024,
294
+ "lora_ga_direction": "ArB2r",
295
+ "lora_ga_scale": "stable",
296
+ "lora_ga_stable_gamma": 16,
297
+ "init_weights": true,
298
+ "fourier_n_frequency": 2000,
299
+ "fourier_scaling": 300.0,
300
+ "boft_block_size": 4,
301
+ "boft_block_num": 0,
302
+ "boft_n_butterfly_factor": 1,
303
+ "boft_dropout": 0.0,
304
+ "vera_rank": 256,
305
+ "vera_projection_prng_key": 0,
306
+ "vera_dropout": 0.0,
307
+ "vera_d_initial": 0.1,
308
+ "adapter_act": "gelu",
309
+ "adapter_length": 128,
310
+ "use_galore": false,
311
+ "galore_target_modules": null,
312
+ "galore_rank": 128,
313
+ "galore_update_proj_gap": 50,
314
+ "galore_scale": 1.0,
315
+ "galore_proj_type": "std",
316
+ "galore_optim_per_parameter": false,
317
+ "galore_with_embedding": false,
318
+ "galore_quantization": false,
319
+ "galore_proj_quant": false,
320
+ "galore_proj_bits": 4,
321
+ "galore_proj_group_size": 256,
322
+ "galore_cos_threshold": 0.4,
323
+ "galore_gamma_proj": 2,
324
+ "galore_queue_size": 5,
325
+ "adalora_target_r": 8,
326
+ "adalora_init_r": 12,
327
+ "adalora_tinit": 0,
328
+ "adalora_tfinal": 0,
329
+ "adalora_deltaT": 1,
330
+ "adalora_beta1": 0.85,
331
+ "adalora_beta2": 0.85,
332
+ "adalora_orth_reg_weight": 0.5,
333
+ "llamapro_num_new_blocks": 4,
334
+ "llamapro_num_groups": null,
335
+ "lisa_activated_layers": 0,
336
+ "lisa_step_interval": 20,
337
+ "reft_layer_key": null,
338
+ "reft_layers": null,
339
+ "reft_rank": 4,
340
+ "reft_intervention_type": "LoreftIntervention",
341
+ "reft_args": null,
342
+ "swanlab_token": null,
343
+ "swanlab_project": "ms-swift",
344
+ "swanlab_workspace": null,
345
+ "swanlab_exp_name": null,
346
+ "swanlab_notification_method": null,
347
+ "swanlab_webhook_url": null,
348
+ "swanlab_secret": null,
349
+ "swanlab_mode": "cloud",
350
+ "add_version": true,
351
+ "create_checkpoint_symlink": false,
352
+ "zero_hpz_partition_size": null,
353
+ "deepspeed_autotp_size": null,
354
+ "early_stop_interval": null,
355
+ "rank": 0,
356
+ "global_world_size": 1,
357
+ "local_world_size": 1,
358
+ "model_suffix": "Qwen2.5-Omni-3B",
359
+ "model_info": "ModelInfo(model_type='qwen2_5_omni', model_dir='/work/yuxiang1234/.cache/huggingface/hub/models--Qwen--Qwen2.5-Omni-3B/snapshots/f75b40e3da2003cdd6e1829b1f420ca70797c34e', 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, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
360
+ "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 0x151e33f9c5e0>, 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', 'thinker.lm_head'], 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, is_reranker=False, task_type=None, ignore_patterns=[], requires=['transformers>=4.50', 'soundfile', 'qwen_omni_utils', 'decord'], tags=['vision', 'video', 'audio'])",
361
+ "model_dir": "/work/yuxiang1234/.cache/huggingface/hub/models--Qwen--Qwen2.5-Omni-3B/snapshots/f75b40e3da2003cdd6e1829b1f420ca70797c34e",
362
+ "_val_dataset_exists": [],
363
+ "hub": "<class 'swift.hub.hub.HFHub'>",
364
+ "evaluation_strategy": "steps",
365
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/work/yuxiang1234/Audio-Captioner/ckpts/qwen2.5-omni-3b/sft_full/v5-20260510-200923', 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=16, per_device_eval_batch_size=8, 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=2e-05, 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='/work/yuxiang1234/Audio-Captioner/ckpts/qwen2.5-omni-3b/sft_full/v5-20260510-200923/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=4, save_safetensors=True, save_on_each_node=False, save_only_model=True, 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, 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=8, dataloader_prefetch_factor=2, past_index=-1, run_name='/work/yuxiang1234/Audio-Captioner/ckpts/qwen2.5-omni-3b/sft_full/v5-20260510-200923', 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=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['wandb'], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=True, 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=False, 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, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='full', local_repo_path=None, galore_config=None, task_type='causal_lm', problem_type=None)"
366
+ }
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 %}
config.json ADDED
@@ -0,0 +1,644 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5OmniForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "enable_audio_output": false,
7
+ "enable_talker": true,
8
+ "eos_token_id": 151645,
9
+ "hidden_size": 2048,
10
+ "keys_to_ignore_at_inference": [
11
+ "past_key_values",
12
+ "hidden_states",
13
+ "attention_mask"
14
+ ],
15
+ "model_type": "qwen2_5_omni",
16
+ "pad_token_id": 151643,
17
+ "talker_config": {
18
+ "_attn_implementation_autoset": true,
19
+ "_name_or_path": "Qwen2.5-Omni-3B/talker",
20
+ "architectures": [
21
+ "Qwen2OmniTalkerForConditionalGeneration"
22
+ ],
23
+ "attention_dropout": 0.0,
24
+ "audio_end_token_id": 151648,
25
+ "audio_start_token_id": 151647,
26
+ "audio_token_index": 151646,
27
+ "dtype": "bfloat16",
28
+ "embedding_size": 2048,
29
+ "head_dim": 64,
30
+ "hidden_act": "silu",
31
+ "hidden_size": 896,
32
+ "image_token_index": 151655,
33
+ "init_std": 0.02,
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 4864,
36
+ "layer_types": [
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
+ "full_attention"
61
+ ],
62
+ "max_position_embeddings": 32768,
63
+ "max_window_layers": 28,
64
+ "model_type": "qwen2_5_omni_talker",
65
+ "num_attention_heads": 14,
66
+ "num_hidden_layers": 24,
67
+ "num_key_value_heads": 2,
68
+ "position_id_per_seconds": 25,
69
+ "rms_norm_eps": 1e-06,
70
+ "rope_scaling": {
71
+ "mrope_section": [
72
+ 16,
73
+ 16,
74
+ 0
75
+ ],
76
+ "rope_type": "default",
77
+ "type": "default"
78
+ },
79
+ "rope_theta": 1000000.0,
80
+ "seconds_per_chunk": 2,
81
+ "sliding_window": null,
82
+ "spatial_merge_size": 2,
83
+ "tts_codec_end_token_id": 8294,
84
+ "tts_codec_mask_token_id": 8296,
85
+ "tts_codec_pad_token_id": 8292,
86
+ "tts_codec_start_token_id": 8293,
87
+ "tts_text_end_token_id": 151861,
88
+ "tts_text_pad_token_id": 151859,
89
+ "tts_text_start_token_id": 151860,
90
+ "use_cache": true,
91
+ "use_sliding_window": false,
92
+ "video_token_index": 151656,
93
+ "vision_end_token_id": 151653,
94
+ "vision_start_token_id": 151652,
95
+ "vocab_size": 8448
96
+ },
97
+ "thinker_config": {
98
+ "_attn_implementation_autoset": true,
99
+ "_name_or_path": "Qwen2.5-Omni-3B/thinker",
100
+ "architectures": [
101
+ "Qwen2OmniNaViTThinkerForConditionalGeneration"
102
+ ],
103
+ "audio_config": {
104
+ "_attn_implementation_autoset": true,
105
+ "_name_or_path": "",
106
+ "activation_dropout": 0.0,
107
+ "activation_function": "gelu",
108
+ "add_cross_attention": false,
109
+ "architectures": null,
110
+ "attention_dropout": 0.0,
111
+ "bad_words_ids": null,
112
+ "begin_suppress_tokens": null,
113
+ "bos_token_id": null,
114
+ "chunk_size_feed_forward": 0,
115
+ "cross_attention_hidden_size": null,
116
+ "d_model": 1280,
117
+ "decoder_start_token_id": null,
118
+ "diversity_penalty": 0.0,
119
+ "do_sample": false,
120
+ "dropout": 0.0,
121
+ "dtype": "bfloat16",
122
+ "early_stopping": false,
123
+ "encoder_attention_heads": 20,
124
+ "encoder_ffn_dim": 5120,
125
+ "encoder_layerdrop": 0.0,
126
+ "encoder_layers": 32,
127
+ "encoder_no_repeat_ngram_size": 0,
128
+ "eos_token_id": null,
129
+ "exponential_decay_length_penalty": null,
130
+ "finetuning_task": null,
131
+ "forced_bos_token_id": null,
132
+ "forced_eos_token_id": null,
133
+ "id2label": {
134
+ "0": "LABEL_0",
135
+ "1": "LABEL_1"
136
+ },
137
+ "init_std": 0.02,
138
+ "initializer_range": 0.02,
139
+ "is_decoder": false,
140
+ "is_encoder_decoder": false,
141
+ "label2id": {
142
+ "LABEL_0": 0,
143
+ "LABEL_1": 1
144
+ },
145
+ "length_penalty": 1.0,
146
+ "max_length": 20,
147
+ "max_source_positions": 1500,
148
+ "min_length": 0,
149
+ "model_type": "qwen2_5_omni_audio_encoder",
150
+ "n_window": 100,
151
+ "no_repeat_ngram_size": 0,
152
+ "num_beam_groups": 1,
153
+ "num_beams": 1,
154
+ "num_hidden_layers": 32,
155
+ "num_mel_bins": 128,
156
+ "num_return_sequences": 1,
157
+ "output_attentions": false,
158
+ "output_dim": 2048,
159
+ "output_hidden_states": false,
160
+ "output_scores": false,
161
+ "pad_token_id": 151643,
162
+ "prefix": null,
163
+ "problem_type": null,
164
+ "pruned_heads": {},
165
+ "remove_invalid_values": false,
166
+ "repetition_penalty": 1.0,
167
+ "return_dict": true,
168
+ "return_dict_in_generate": false,
169
+ "scale_embedding": false,
170
+ "sep_token_id": null,
171
+ "suppress_tokens": null,
172
+ "task_specific_params": null,
173
+ "temperature": 1.0,
174
+ "tf_legacy_loss": false,
175
+ "tie_encoder_decoder": false,
176
+ "tie_word_embeddings": true,
177
+ "tokenizer_class": null,
178
+ "top_k": 50,
179
+ "top_p": 1.0,
180
+ "torchscript": false,
181
+ "typical_p": 1.0,
182
+ "use_bfloat16": false
183
+ },
184
+ "audio_end_token_id": 151648,
185
+ "audio_start_token_id": 151647,
186
+ "audio_token_index": 151646,
187
+ "bos_token_id": 151644,
188
+ "dtype": "bfloat16",
189
+ "eos_token_id": 151645,
190
+ "ignore_index": -100,
191
+ "image_token_index": 151655,
192
+ "init_std": 0.02,
193
+ "initializer_range": 0.02,
194
+ "model_type": "qwen2_5_omni_thinker",
195
+ "pad_token_id": 151643,
196
+ "position_id_per_seconds": 25,
197
+ "seconds_per_chunk": 2,
198
+ "text_config": {
199
+ "_name_or_path": "",
200
+ "add_cross_attention": false,
201
+ "architectures": null,
202
+ "attention_dropout": 0.0,
203
+ "bad_words_ids": null,
204
+ "begin_suppress_tokens": null,
205
+ "bos_token_id": null,
206
+ "chunk_size_feed_forward": 0,
207
+ "cross_attention_hidden_size": null,
208
+ "decoder_start_token_id": null,
209
+ "diversity_penalty": 0.0,
210
+ "do_sample": false,
211
+ "dtype": "bfloat16",
212
+ "early_stopping": false,
213
+ "encoder_no_repeat_ngram_size": 0,
214
+ "eos_token_id": null,
215
+ "exponential_decay_length_penalty": null,
216
+ "finetuning_task": null,
217
+ "forced_bos_token_id": null,
218
+ "forced_eos_token_id": null,
219
+ "hidden_act": "silu",
220
+ "hidden_size": 2048,
221
+ "id2label": {
222
+ "0": "LABEL_0",
223
+ "1": "LABEL_1"
224
+ },
225
+ "init_std": 0.02,
226
+ "initializer_range": 0.02,
227
+ "intermediate_size": 11008,
228
+ "is_decoder": false,
229
+ "is_encoder_decoder": false,
230
+ "label2id": {
231
+ "LABEL_0": 0,
232
+ "LABEL_1": 1
233
+ },
234
+ "layer_types": [
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
+ "full_attention"
271
+ ],
272
+ "length_penalty": 1.0,
273
+ "max_length": 20,
274
+ "max_position_embeddings": 32768,
275
+ "max_window_layers": 70,
276
+ "min_length": 0,
277
+ "model_type": "qwen2_5_omni_text",
278
+ "no_repeat_ngram_size": 0,
279
+ "num_attention_heads": 16,
280
+ "num_beam_groups": 1,
281
+ "num_beams": 1,
282
+ "num_hidden_layers": 36,
283
+ "num_key_value_heads": 2,
284
+ "num_return_sequences": 1,
285
+ "output_attentions": false,
286
+ "output_hidden_states": false,
287
+ "output_scores": false,
288
+ "pad_token_id": 151643,
289
+ "prefix": null,
290
+ "problem_type": null,
291
+ "pruned_heads": {},
292
+ "remove_invalid_values": false,
293
+ "repetition_penalty": 1.0,
294
+ "return_dict": true,
295
+ "return_dict_in_generate": false,
296
+ "rms_norm_eps": 1e-06,
297
+ "rope_scaling": {
298
+ "mrope_section": [
299
+ 16,
300
+ 24,
301
+ 24
302
+ ],
303
+ "rope_type": "default",
304
+ "type": "default"
305
+ },
306
+ "rope_theta": 1000000.0,
307
+ "sep_token_id": null,
308
+ "sliding_window": null,
309
+ "suppress_tokens": null,
310
+ "task_specific_params": null,
311
+ "temperature": 1.0,
312
+ "tf_legacy_loss": false,
313
+ "tie_encoder_decoder": false,
314
+ "tie_word_embeddings": false,
315
+ "tokenizer_class": null,
316
+ "top_k": 50,
317
+ "top_p": 1.0,
318
+ "torchscript": false,
319
+ "typical_p": 1.0,
320
+ "use_bfloat16": false,
321
+ "use_cache": false,
322
+ "use_sliding_window": false,
323
+ "vocab_size": 151936
324
+ },
325
+ "user_token_id": 872,
326
+ "video_token_index": 151656,
327
+ "vision_config": {
328
+ "_attn_implementation_autoset": true,
329
+ "_name_or_path": "",
330
+ "add_cross_attention": false,
331
+ "architectures": null,
332
+ "bad_words_ids": null,
333
+ "begin_suppress_tokens": null,
334
+ "bos_token_id": null,
335
+ "chunk_size_feed_forward": 0,
336
+ "cross_attention_hidden_size": null,
337
+ "decoder_start_token_id": null,
338
+ "depth": 32,
339
+ "diversity_penalty": 0.0,
340
+ "do_sample": false,
341
+ "dtype": "bfloat16",
342
+ "early_stopping": false,
343
+ "embed_dim": 1280,
344
+ "encoder_no_repeat_ngram_size": 0,
345
+ "eos_token_id": null,
346
+ "exponential_decay_length_penalty": null,
347
+ "finetuning_task": null,
348
+ "forced_bos_token_id": null,
349
+ "forced_eos_token_id": null,
350
+ "fullatt_block_indexes": [
351
+ 7,
352
+ 15,
353
+ 23,
354
+ 31
355
+ ],
356
+ "hidden_act": "silu",
357
+ "hidden_size": 1280,
358
+ "id2label": {
359
+ "0": "LABEL_0",
360
+ "1": "LABEL_1"
361
+ },
362
+ "in_channels": 3,
363
+ "in_chans": 3,
364
+ "init_std": 0.02,
365
+ "initializer_range": 0.02,
366
+ "intermediate_size": 3420,
367
+ "is_decoder": false,
368
+ "is_encoder_decoder": false,
369
+ "label2id": {
370
+ "LABEL_0": 0,
371
+ "LABEL_1": 1
372
+ },
373
+ "length_penalty": 1.0,
374
+ "max_length": 20,
375
+ "min_length": 0,
376
+ "model_type": "qwen2_5_omni_vision_encoder",
377
+ "no_repeat_ngram_size": 0,
378
+ "num_beam_groups": 1,
379
+ "num_beams": 1,
380
+ "num_heads": 16,
381
+ "num_return_sequences": 1,
382
+ "out_hidden_size": 2048,
383
+ "output_attentions": false,
384
+ "output_hidden_states": false,
385
+ "output_scores": false,
386
+ "pad_token_id": 151643,
387
+ "patch_size": 14,
388
+ "prefix": null,
389
+ "problem_type": null,
390
+ "pruned_heads": {},
391
+ "remove_invalid_values": false,
392
+ "repetition_penalty": 1.0,
393
+ "return_dict": true,
394
+ "return_dict_in_generate": false,
395
+ "sep_token_id": null,
396
+ "spatial_merge_size": 2,
397
+ "spatial_patch_size": 14,
398
+ "suppress_tokens": null,
399
+ "task_specific_params": null,
400
+ "temperature": 1.0,
401
+ "temporal_patch_size": 2,
402
+ "tf_legacy_loss": false,
403
+ "tie_encoder_decoder": false,
404
+ "tie_word_embeddings": true,
405
+ "tokenizer_class": null,
406
+ "tokens_per_second": 25,
407
+ "top_k": 50,
408
+ "top_p": 1.0,
409
+ "torchscript": false,
410
+ "typical_p": 1.0,
411
+ "use_bfloat16": false,
412
+ "window_size": 112
413
+ },
414
+ "vision_end_token_id": 151653,
415
+ "vision_start_token_id": 151652,
416
+ "vision_token_id": 151654
417
+ },
418
+ "token2wav_config": {
419
+ "_attn_implementation_autoset": true,
420
+ "bigvgan_config": {
421
+ "_attn_implementation_autoset": true,
422
+ "_name_or_path": "",
423
+ "add_cross_attention": false,
424
+ "architectures": null,
425
+ "bad_words_ids": null,
426
+ "begin_suppress_tokens": null,
427
+ "bos_token_id": null,
428
+ "chunk_size_feed_forward": 0,
429
+ "cross_attention_hidden_size": null,
430
+ "decoder_start_token_id": null,
431
+ "diversity_penalty": 0.0,
432
+ "do_sample": false,
433
+ "dtype": null,
434
+ "early_stopping": false,
435
+ "encoder_no_repeat_ngram_size": 0,
436
+ "eos_token_id": null,
437
+ "exponential_decay_length_penalty": null,
438
+ "finetuning_task": null,
439
+ "forced_bos_token_id": null,
440
+ "forced_eos_token_id": null,
441
+ "id2label": {
442
+ "0": "LABEL_0",
443
+ "1": "LABEL_1"
444
+ },
445
+ "is_decoder": false,
446
+ "is_encoder_decoder": false,
447
+ "label2id": {
448
+ "LABEL_0": 0,
449
+ "LABEL_1": 1
450
+ },
451
+ "length_penalty": 1.0,
452
+ "max_length": 20,
453
+ "mel_dim": 80,
454
+ "min_length": 0,
455
+ "model_type": "qwen2_5_omni_bigvgan",
456
+ "no_repeat_ngram_size": 0,
457
+ "num_beam_groups": 1,
458
+ "num_beams": 1,
459
+ "num_return_sequences": 1,
460
+ "output_attentions": false,
461
+ "output_hidden_states": false,
462
+ "output_scores": false,
463
+ "pad_token_id": null,
464
+ "prefix": null,
465
+ "problem_type": null,
466
+ "pruned_heads": {},
467
+ "remove_invalid_values": false,
468
+ "repetition_penalty": 1.0,
469
+ "resblock_dilation_sizes": [
470
+ [
471
+ 1,
472
+ 3,
473
+ 5
474
+ ],
475
+ [
476
+ 1,
477
+ 3,
478
+ 5
479
+ ],
480
+ [
481
+ 1,
482
+ 3,
483
+ 5
484
+ ]
485
+ ],
486
+ "resblock_kernel_sizes": [
487
+ 3,
488
+ 7,
489
+ 11
490
+ ],
491
+ "return_dict": true,
492
+ "return_dict_in_generate": false,
493
+ "sep_token_id": null,
494
+ "suppress_tokens": null,
495
+ "task_specific_params": null,
496
+ "temperature": 1.0,
497
+ "tf_legacy_loss": false,
498
+ "tie_encoder_decoder": false,
499
+ "tie_word_embeddings": true,
500
+ "tokenizer_class": null,
501
+ "top_k": 50,
502
+ "top_p": 1.0,
503
+ "torchscript": false,
504
+ "typical_p": 1.0,
505
+ "upsample_initial_channel": 1536,
506
+ "upsample_kernel_sizes": [
507
+ 11,
508
+ 7,
509
+ 4,
510
+ 4,
511
+ 4,
512
+ 4
513
+ ],
514
+ "upsample_rates": [
515
+ 5,
516
+ 3,
517
+ 2,
518
+ 2,
519
+ 2,
520
+ 2
521
+ ],
522
+ "use_bfloat16": false,
523
+ "use_bias_at_final": false
524
+ },
525
+ "dit_config": {
526
+ "_attn_implementation_autoset": true,
527
+ "_name_or_path": "",
528
+ "add_cross_attention": false,
529
+ "architectures": null,
530
+ "bad_words_ids": null,
531
+ "begin_suppress_tokens": null,
532
+ "block_size": 24,
533
+ "bos_token_id": null,
534
+ "chunk_size_feed_forward": 0,
535
+ "cross_attention_hidden_size": null,
536
+ "decoder_start_token_id": null,
537
+ "depth": 22,
538
+ "dim": 1024,
539
+ "diversity_penalty": 0.0,
540
+ "do_sample": false,
541
+ "dropout": 0.1,
542
+ "dtype": "float32",
543
+ "early_stopping": false,
544
+ "emb_dim": 512,
545
+ "enc_attention_channels": 64,
546
+ "enc_channels": [
547
+ 256,
548
+ 256,
549
+ 256,
550
+ 256,
551
+ 768
552
+ ],
553
+ "enc_dilations": [
554
+ 1,
555
+ 2,
556
+ 3,
557
+ 4,
558
+ 1
559
+ ],
560
+ "enc_dim": 128,
561
+ "enc_emb_dim": 192,
562
+ "enc_global_context": true,
563
+ "enc_kernel_sizes": [
564
+ 5,
565
+ 3,
566
+ 3,
567
+ 3,
568
+ 1
569
+ ],
570
+ "enc_lin_neurons": 192,
571
+ "enc_res2net_scale": 2,
572
+ "enc_se_channels": 64,
573
+ "encoder_no_repeat_ngram_size": 0,
574
+ "eos_token_id": null,
575
+ "exponential_decay_length_penalty": null,
576
+ "ff_mult": 2,
577
+ "finetuning_task": null,
578
+ "forced_bos_token_id": null,
579
+ "forced_eos_token_id": null,
580
+ "head_dim": 64,
581
+ "heads": 16,
582
+ "hidden_size": 1024,
583
+ "id2label": {
584
+ "0": "LABEL_0",
585
+ "1": "LABEL_1"
586
+ },
587
+ "is_decoder": false,
588
+ "is_encoder_decoder": false,
589
+ "label2id": {
590
+ "LABEL_0": 0,
591
+ "LABEL_1": 1
592
+ },
593
+ "length_penalty": 1.0,
594
+ "look_ahead_layers": [
595
+ 10
596
+ ],
597
+ "look_backward_layers": [
598
+ 0,
599
+ 20
600
+ ],
601
+ "max_length": 20,
602
+ "max_position_embeddings": 32768,
603
+ "mel_dim": 80,
604
+ "min_length": 0,
605
+ "model_type": "qwen2_5_omni_dit",
606
+ "no_repeat_ngram_size": 0,
607
+ "num_attention_heads": 16,
608
+ "num_beam_groups": 1,
609
+ "num_beams": 1,
610
+ "num_embeds": 8193,
611
+ "num_hidden_layers": 22,
612
+ "num_return_sequences": 1,
613
+ "output_attentions": false,
614
+ "output_hidden_states": false,
615
+ "output_scores": false,
616
+ "pad_token_id": null,
617
+ "prefix": null,
618
+ "problem_type": null,
619
+ "pruned_heads": {},
620
+ "remove_invalid_values": false,
621
+ "repeats": 2,
622
+ "repetition_penalty": 1.0,
623
+ "return_dict": true,
624
+ "return_dict_in_generate": false,
625
+ "rope_theta": 10000.0,
626
+ "sep_token_id": null,
627
+ "suppress_tokens": null,
628
+ "task_specific_params": null,
629
+ "temperature": 1.0,
630
+ "tf_legacy_loss": false,
631
+ "tie_encoder_decoder": false,
632
+ "tie_word_embeddings": true,
633
+ "tokenizer_class": null,
634
+ "top_k": 50,
635
+ "top_p": 1.0,
636
+ "torchscript": false,
637
+ "typical_p": 1.0,
638
+ "use_bfloat16": false
639
+ },
640
+ "dtype": "bfloat16",
641
+ "model_type": "qwen2_5_omni_token2wav"
642
+ },
643
+ "transformers_version": "4.57.6"
644
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "transformers_version": "4.57.6"
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3caacbd0621a9707b8608951504a04c5d59d88aad643d941eab1bd7095f85021
3
+ size 4994850880
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f808a1226fd47191f3691a71bba15c8f772ffd562154d0b4405a0bbeaecdffd1
3
+ size 4412251408
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
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
+ }
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
+ }
spk_dict.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a05609b28f5d42b7b748f0f07592545c8f1f6885b9ae8fff64baf56e86b2a18
3
+ size 259544
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8441917e39ae0244e06d704b95b3124795cec478e297f9afac39ba670d7e9d99
3
+ size 11421870
tokenizer_config.json ADDED
@@ -0,0 +1,222 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b4370669278349908a810dadf650a50a6b77d029c28637c1a86828b458e6da8
3
+ size 7057
video_preprocessor_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 300,
3
+ "crop_size": null,
4
+ "data_format": "channels_first",
5
+ "default_to_square": true,
6
+ "device": null,
7
+ "dither": 0.0,
8
+ "do_center_crop": null,
9
+ "do_convert_rgb": true,
10
+ "do_normalize": true,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "do_sample_frames": false,
14
+ "feature_extractor_type": "WhisperFeatureExtractor",
15
+ "feature_size": 128,
16
+ "fps": null,
17
+ "hop_length": 160,
18
+ "image_mean": [
19
+ 0.48145466,
20
+ 0.4578275,
21
+ 0.40821073
22
+ ],
23
+ "image_std": [
24
+ 0.26862954,
25
+ 0.26130258,
26
+ 0.27577711
27
+ ],
28
+ "input_data_format": null,
29
+ "max_frames": 768,
30
+ "max_pixels": 12845056,
31
+ "merge_size": 2,
32
+ "min_frames": 4,
33
+ "min_pixels": 3136,
34
+ "n_fft": 400,
35
+ "n_samples": 4800000,
36
+ "nb_max_frames": 30000,
37
+ "num_frames": null,
38
+ "pad_size": null,
39
+ "padding_side": "right",
40
+ "padding_value": 0.0,
41
+ "patch_size": 14,
42
+ "processor_class": "Qwen2_5OmniProcessor",
43
+ "resample": 3,
44
+ "rescale_factor": 0.00392156862745098,
45
+ "return_attention_mask": true,
46
+ "return_metadata": false,
47
+ "sampling_rate": 16000,
48
+ "size": {
49
+ "longest_edge": 12845056,
50
+ "shortest_edge": 3136
51
+ },
52
+ "temporal_patch_size": 2,
53
+ "video_metadata": null,
54
+ "video_processor_type": "Qwen2VLVideoProcessor"
55
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff