mcshao commited on
Commit
a54c7ce
·
verified ·
1 Parent(s): c950f11

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* 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
  Figures/LAT-Audio.png 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
  Figures/LAT-Audio.png filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
args.json ADDED
@@ -0,0 +1,400 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "use_ray": false,
3
+ "ray_exp_name": null,
4
+ "device_groups": null,
5
+ "model": "/mnt/data/share-oss/user/shaomingchen/ckpt/long-audio/time-aware/exp14-baseline+all_conv2_v2/v0-20260312-131003/checkpoint-2500",
6
+ "model_type": "qwen3_omni_moe",
7
+ "model_revision": null,
8
+ "task_type": "causal_lm",
9
+ "torch_dtype": "bfloat16",
10
+ "attn_impl": null,
11
+ "experts_impl": null,
12
+ "new_special_tokens": [],
13
+ "num_labels": null,
14
+ "problem_type": null,
15
+ "rope_scaling": null,
16
+ "device_map": null,
17
+ "max_memory": {},
18
+ "max_model_len": null,
19
+ "local_repo_path": null,
20
+ "init_strategy": null,
21
+ "template": "qwen3_omni",
22
+ "system": "You are a helpful assistant.",
23
+ "max_length": 65536,
24
+ "truncation_strategy": "delete",
25
+ "max_pixels": null,
26
+ "agent_template": null,
27
+ "norm_bbox": null,
28
+ "use_chat_template": true,
29
+ "padding_side": "right",
30
+ "padding_free": true,
31
+ "loss_scale": "default",
32
+ "sequence_parallel_size": 1,
33
+ "template_backend": "swift",
34
+ "response_prefix": null,
35
+ "enable_thinking": null,
36
+ "add_non_thinking_prefix": true,
37
+ "dataset": [
38
+ "/mnt/data/share-ssd/user/shaomingchen/code/long-audio/time-aware/ft_omni/ms-swift-2-27-fsdp/examples/train/multimodal/data/train_ACM_MM/agentic_v2/train.jsonl"
39
+ ],
40
+ "val_dataset": [
41
+ "/mnt/data/share-ssd/user/shaomingchen/code/long-audio/time-aware/ft_omni/ms-swift-2-27-fsdp/examples/train/multimodal/data/train_ACM_MM/agentic_v2/val.jsonl"
42
+ ],
43
+ "cached_dataset": [],
44
+ "cached_val_dataset": [],
45
+ "split_dataset_ratio": 0.0,
46
+ "data_seed": 42,
47
+ "dataset_num_proc": 64,
48
+ "load_from_cache_file": false,
49
+ "dataset_shuffle": true,
50
+ "val_dataset_shuffle": false,
51
+ "streaming": false,
52
+ "interleave_prob": null,
53
+ "stopping_strategy": "first_exhausted",
54
+ "shuffle_buffer_size": 1000,
55
+ "download_mode": "reuse_dataset_if_exists",
56
+ "columns": {},
57
+ "strict": false,
58
+ "remove_unused_columns": true,
59
+ "model_name": [
60
+ "swift-robot"
61
+ ],
62
+ "model_author": [
63
+ "swift"
64
+ ],
65
+ "custom_dataset_info": [],
66
+ "quant_method": null,
67
+ "quant_bits": null,
68
+ "hqq_axis": null,
69
+ "bnb_4bit_compute_dtype": "bfloat16",
70
+ "bnb_4bit_quant_type": "nf4",
71
+ "bnb_4bit_use_double_quant": true,
72
+ "bnb_4bit_quant_storage": null,
73
+ "max_new_tokens": null,
74
+ "temperature": 0.9,
75
+ "top_k": 50,
76
+ "top_p": 0.9,
77
+ "repetition_penalty": 1.0,
78
+ "num_beams": 1,
79
+ "stream": false,
80
+ "stop_words": [],
81
+ "logprobs": false,
82
+ "top_logprobs": null,
83
+ "structured_outputs_regex": null,
84
+ "tuner_backend": "peft",
85
+ "tuner_type": "full",
86
+ "train_type": null,
87
+ "adapters": [],
88
+ "external_plugins": [],
89
+ "custom_register_path": [],
90
+ "seed": 42,
91
+ "model_kwargs": {},
92
+ "load_args": false,
93
+ "load_data_args": false,
94
+ "packing": false,
95
+ "packing_length": null,
96
+ "packing_num_proc": 1,
97
+ "lazy_tokenize": true,
98
+ "use_hf": false,
99
+ "hub_token": null,
100
+ "ddp_timeout": 18000000,
101
+ "ddp_backend": "nccl",
102
+ "ignore_args_error": false,
103
+ "use_swift_lora": false,
104
+ "freeze_llm": false,
105
+ "freeze_vit": true,
106
+ "freeze_aligner": true,
107
+ "freeze_parameters": [
108
+ "visual.thinker.audio_tower",
109
+ "visual.thinker.visual",
110
+ "visual.thinker.audio_tower.proj1",
111
+ "visual.thinker.audio_tower.proj2",
112
+ "visual.thinker.visual.merger",
113
+ "visual.thinker.visual.merger_list",
114
+ "visual.talker",
115
+ "visual.code2wav"
116
+ ],
117
+ "freeze_parameters_regex": null,
118
+ "freeze_parameters_ratio": 0.0,
119
+ "trainable_parameters": [],
120
+ "trainable_parameters_regex": null,
121
+ "target_modules": [
122
+ "all-linear"
123
+ ],
124
+ "target_regex": null,
125
+ "modules_to_save": [],
126
+ "lora_rank": 8,
127
+ "lora_alpha": 32,
128
+ "lora_dropout": 0.05,
129
+ "lora_bias": "none",
130
+ "lora_dtype": null,
131
+ "use_rslora": false,
132
+ "rlhf_type": null,
133
+ "loss_type": null,
134
+ "mcore_ref_model": null,
135
+ "mcore_ref_adapter": null,
136
+ "beta": null,
137
+ "rpo_alpha": null,
138
+ "reference_free": false,
139
+ "label_smoothing": 0.0,
140
+ "f_divergence_type": "reverse_kl",
141
+ "desirable_weight": 1.0,
142
+ "undesirable_weight": 1.0,
143
+ "calculate_KL": null,
144
+ "center_rewards_coefficient": null,
145
+ "teacher_model": null,
146
+ "teacher_model_type": null,
147
+ "teacher_model_revision": null,
148
+ "lmbda": 0.5,
149
+ "seq_kd": false,
150
+ "offload_teacher_model": false,
151
+ "sft_alpha": 0.0,
152
+ "generation_batch_size": null,
153
+ "steps_per_generation": null,
154
+ "num_generations": 8,
155
+ "num_generations_eval": null,
156
+ "max_completion_length": 512,
157
+ "importance_sampling_level": "token",
158
+ "tau_pos": 1.0,
159
+ "tau_neg": 1.05,
160
+ "epsilon": 0.2,
161
+ "epsilon_high": null,
162
+ "delta": null,
163
+ "use_vllm": true,
164
+ "vllm_mode": null,
165
+ "vllm_enable_prefix_caching": true,
166
+ "vllm_gpu_memory_utilization": 0.9,
167
+ "vllm_tensor_parallel_size": 1,
168
+ "vllm_max_model_len": null,
169
+ "vllm_enforce_eager": false,
170
+ "vllm_limit_mm_per_prompt": null,
171
+ "vllm_disable_cascade_attn": false,
172
+ "vllm_max_num_seqs": null,
173
+ "vllm_mm_processor_cache_gb": null,
174
+ "vllm_engine_kwargs": null,
175
+ "sleep_level": 0,
176
+ "offload_optimizer": false,
177
+ "offload_model": false,
178
+ "offload_bridge": false,
179
+ "vllm_server_base_url": null,
180
+ "vllm_server_host": null,
181
+ "vllm_server_port": [
182
+ 8000
183
+ ],
184
+ "vllm_server_timeout": 240.0,
185
+ "vllm_server_group_port": null,
186
+ "reward_funcs": [],
187
+ "reward_weights": null,
188
+ "cosine_min_len_value_wrong": -0.5,
189
+ "cosine_max_len_value_wrong": 0.0,
190
+ "cosine_min_len_value_correct": 1.0,
191
+ "cosine_max_len_value_correct": 0.5,
192
+ "cosine_max_len": null,
193
+ "repetition_n_grams": 3,
194
+ "repetition_max_penalty": -1.0,
195
+ "soft_max_length": null,
196
+ "soft_cache_length": null,
197
+ "dynamic_sample": false,
198
+ "max_resample_times": 3,
199
+ "overlong_filter": false,
200
+ "scale_rewards": "group",
201
+ "advantage_estimator": "grpo",
202
+ "kl_in_reward": false,
203
+ "wandb_log_unique_prompts": null,
204
+ "log_completions": false,
205
+ "rollout_importance_sampling_mode": null,
206
+ "rollout_importance_sampling_threshold": 2.0,
207
+ "log_rollout_offpolicy_metrics": false,
208
+ "off_policy_sequence_mask_delta": null,
209
+ "log_entropy": false,
210
+ "top_entropy_quantile": 1.0,
211
+ "reward_model": null,
212
+ "reward_model_plugin": null,
213
+ "sync_ref_model": false,
214
+ "ref_model_sync_steps": 512,
215
+ "ref_model_mixup_alpha": 0.6,
216
+ "async_generate": false,
217
+ "move_model_batches": null,
218
+ "multi_turn_scheduler": null,
219
+ "max_turns": null,
220
+ "completion_length_limit_scope": "per_round",
221
+ "vllm_server_pass_dataset": false,
222
+ "num_iterations": 1,
223
+ "micro_batch_size": 1,
224
+ "global_batch_size": 64,
225
+ "recompute_granularity": "full",
226
+ "recompute_method": "uniform",
227
+ "recompute_num_layers": 1,
228
+ "recompute_modules": [
229
+ "core_attn"
230
+ ],
231
+ "train_iters": null,
232
+ "num_train_epochs": 8,
233
+ "masked_softmax_fusion": true,
234
+ "bias_dropout_fusion": true,
235
+ "bias_activation_fusion": true,
236
+ "apply_rope_fusion": false,
237
+ "gradient_accumulation_fusion": false,
238
+ "cross_entropy_loss_fusion": true,
239
+ "cross_entropy_fusion_impl": "native",
240
+ "calculate_per_token_loss": true,
241
+ "attention_backend": "<AttnBackend.flash: 1>",
242
+ "optimizer": "adam",
243
+ "optimizer_cpu_offload": false,
244
+ "optimizer_offload_fraction": 1.0,
245
+ "use_precision_aware_optimizer": false,
246
+ "main_grads_dtype": "float32",
247
+ "main_params_dtype": "float32",
248
+ "exp_avg_dtype": "float32",
249
+ "exp_avg_sq_dtype": "float32",
250
+ "manual_gc": false,
251
+ "manual_gc_steps": 0,
252
+ "manual_gc_eval": true,
253
+ "train_dataloader_shuffle": true,
254
+ "dataloader_num_workers": 4,
255
+ "dataloader_pin_memory": true,
256
+ "dataloader_persistent_workers": true,
257
+ "dataloader_prefetch_factor": 2,
258
+ "data_sharding": false,
259
+ "group_by_length": false,
260
+ "te_rng_tracker": false,
261
+ "data_parallel_random_init": false,
262
+ "mlp_padding_free": false,
263
+ "lr_warmup_init": 0.0,
264
+ "lr": 8e-06,
265
+ "lr_decay_style": "cosine",
266
+ "lr_decay_iters": null,
267
+ "lr_warmup_iters": 0,
268
+ "lr_warmup_fraction": 0.05,
269
+ "min_lr": 1e-06,
270
+ "lr_wsd_decay_style": "exponential",
271
+ "lr_wsd_decay_iters": null,
272
+ "weight_decay": 0.1,
273
+ "weight_decay_incr_style": "constant",
274
+ "start_weight_decay": 0.1,
275
+ "end_weight_decay": 0.1,
276
+ "clip_grad": 1.0,
277
+ "adam_beta1": 0.9,
278
+ "adam_beta2": 0.95,
279
+ "adam_eps": 1e-08,
280
+ "sgd_momentum": 0.9,
281
+ "output_dir": "/mnt/data/share-oss/user/shaomingchen/ckpt/long-audio/time-aware/exp16-conv2-64K/v0-20260321-010515",
282
+ "save_steps": 100,
283
+ "no_save_optim": true,
284
+ "no_save_rng": true,
285
+ "mcore_model": null,
286
+ "mcore_adapter": null,
287
+ "no_load_optim": false,
288
+ "no_load_rng": false,
289
+ "finetune": true,
290
+ "perform_initialization": false,
291
+ "use_cpu_initialization": false,
292
+ "async_save": false,
293
+ "save_total_limit": null,
294
+ "metric_for_best_model": "loss",
295
+ "greater_is_better": false,
296
+ "use_persistent_ckpt_worker": false,
297
+ "dist_ckpt_save_pre_mcore_014": false,
298
+ "dist_ckpt_optim_fully_reshardable": false,
299
+ "distrib_optim_fully_reshardable_mem_efficient": false,
300
+ "local_rank": 0,
301
+ "use_distributed_optimizer": true,
302
+ "tensor_model_parallel_size": 2,
303
+ "pipeline_model_parallel_size": 1,
304
+ "decoder_first_pipeline_num_layers": null,
305
+ "decoder_last_pipeline_num_layers": null,
306
+ "account_for_embedding_in_pipeline_split": false,
307
+ "account_for_loss_in_pipeline_split": false,
308
+ "overlap_p2p_comm": false,
309
+ "align_param_gather": false,
310
+ "sequence_parallel": true,
311
+ "context_parallel_size": 1,
312
+ "tp_comm_overlap": false,
313
+ "overlap_grad_reduce": false,
314
+ "overlap_param_gather": false,
315
+ "overlap_param_gather_with_optimizer_step": false,
316
+ "align_grad_reduce": true,
317
+ "virtual_pipeline_model_parallel_size": null,
318
+ "microbatch_group_size_per_vp_stage": null,
319
+ "pipeline_model_parallel_layout": null,
320
+ "expert_model_parallel_size": 4,
321
+ "expert_tensor_parallel_size": 1,
322
+ "report_to": [
323
+ "tensorboard"
324
+ ],
325
+ "logging_steps": 5,
326
+ "tensorboard_dir": "/mnt/data/share-oss/user/shaomingchen/ckpt/long-audio/time-aware/exp16-conv2-64K/v0-20260321-010515/runs",
327
+ "tensorboard_queue_size": 50,
328
+ "wandb_project": "megatron-swift",
329
+ "wandb_exp_name": null,
330
+ "swanlab_project": "megatron-swift",
331
+ "swanlab_exp_name": null,
332
+ "eval_iters": -1,
333
+ "eval_steps": 100,
334
+ "fp8_format": null,
335
+ "fp8_recipe": "delayed",
336
+ "fp8_amax_history_len": 1024,
337
+ "fp8_amax_compute_algo": "max",
338
+ "fp8_param_gather": false,
339
+ "fp16": false,
340
+ "bf16": true,
341
+ "apply_query_key_layer_scaling": false,
342
+ "attention_softmax_in_fp32": true,
343
+ "accumulate_allreduce_grads_in_fp32": true,
344
+ "moe_router_load_balancing_type": null,
345
+ "moe_router_dtype": "fp32",
346
+ "moe_token_dispatcher_type": null,
347
+ "moe_enable_deepep": false,
348
+ "moe_grouped_gemm": true,
349
+ "moe_permute_fusion": true,
350
+ "moe_aux_loss_coeff": 0.001,
351
+ "moe_z_loss_coeff": null,
352
+ "moe_shared_expert_overlap": true,
353
+ "moe_layer_recompute": false,
354
+ "moe_expert_capacity_factor": null,
355
+ "moe_pad_expert_input_to_capacity": false,
356
+ "moe_token_drop_policy": null,
357
+ "mtp_num_layers": null,
358
+ "mtp_loss_scaling_factor": 0.1,
359
+ "save_safetensors": true,
360
+ "ref_model": null,
361
+ "ref_adapters": [],
362
+ "merge_lora": true,
363
+ "max_shard_size": "5GB",
364
+ "vit_gradient_checkpointing": false,
365
+ "vit_lr": null,
366
+ "aligner_lr": null,
367
+ "gradient_checkpointing_kwargs": null,
368
+ "check_model": true,
369
+ "apply_wd_to_qk_layernorm": false,
370
+ "enable_dft_loss": false,
371
+ "enable_channel_loss": false,
372
+ "save_strategy": "steps",
373
+ "callbacks": [
374
+ "print",
375
+ "default_flow",
376
+ "tensorboard"
377
+ ],
378
+ "add_version": true,
379
+ "create_checkpoint_symlink": false,
380
+ "swift_version": "4.0.0.dev0",
381
+ "ckpt_dir": "/mnt/data/share-oss/user/shaomingchen/ckpt/long-audio/time-aware/exp14-baseline+all_conv2_v2/v0-20260312-131003/checkpoint-2500",
382
+ "rank": 0,
383
+ "global_world_size": 32,
384
+ "local_world_size": 8,
385
+ "model_suffix": "checkpoint-2500",
386
+ "model_info": "ModelInfo(model_type='qwen3_omni_moe', model_dir='/mnt/data/share-oss/user/shaomingchen/ckpt/long-audio/time-aware/exp14-baseline+all_conv2_v2/v0-20260312-131003/checkpoint-2500', torch_dtype=torch.bfloat16, max_model_len=65536, quant_method=None, quant_bits=None, rope_scaling={'interleaved': True, 'mrope_section': [24, 20, 20], 'rope_type': 'default', 'type': 'default'}, is_moe_model=True, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",
387
+ "model_meta": "ModelMeta(model_type='qwen3_omni_moe', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-Omni-30B-A3B-Instruct', hf_model_id='Qwen/Qwen3-Omni-30B-A3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-Omni-30B-A3B-Thinking', hf_model_id='Qwen/Qwen3-Omni-30B-A3B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-Omni-30B-A3B-Captioner', hf_model_id='Qwen/Qwen3-Omni-30B-A3B-Captioner', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_omni', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.models.qwen.Qwen3OmniLoader'>, template=None, model_arch=MultiModelKeys(arch_name='qwen3_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.proj1', 'thinker.audio_tower.proj2', 'thinker.visual.merger', 'thinker.visual.merger_list'], vision_tower=['thinker.audio_tower', 'thinker.visual'], generator=['talker', 'code2wav']), architectures=['Qwen3OmniMoeForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.57.dev0', 'soundfile', 'decord', 'qwen_omni_utils'], tags=['vision', 'video', 'audio'])",
388
+ "model_dir": "/mnt/data/share-oss/user/shaomingchen/ckpt/long-audio/time-aware/exp14-baseline+all_conv2_v2/v0-20260312-131003/checkpoint-2500",
389
+ "template_meta": "QwenTemplateMeta(template_type='qwen3_omni', prefix=[], prompt=['<|im_start|>user\\n{{QUERY}}<|im_end|>\\n<|im_start|>assistant\\n'], chat_sep=['<|im_end|>\\n'], suffix=['<|im_end|>\\n'], template_cls=<class 'swift.template.templates.qwen.Qwen3OmniTemplate'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system=None, auto_add_bos=False, stop_words=['<|endoftext|>'], agent_template='hermes', is_thinking=False, thinking_prefix='<think>\\n', non_thinking_prefix='', history_thinking_prefix='')",
390
+ "_val_dataset_exists": true,
391
+ "hub": "<class 'swift.hub.hub.MSHub'>",
392
+ "seq_length": 65536,
393
+ "is_multimodal": true,
394
+ "megatron_model_meta": "MegatronModelMeta(megatron_model_type='qwen3_omni', model_types=['qwen3_omni_moe'], bridge_cls=<class 'swift.megatron.model.mm_gpts.qwen3_vl.Qwen3OmniBridge'>, visual_cls=<class 'swift.megatron.model.mm_gpts.qwen3_vl.Qwen3Omni_Vit'>, is_multimodal=True, loader=<class 'swift.megatron.model.mm_gpts.qwen3_vl.Qwen3VLLoader'>)",
395
+ "fp8": null,
396
+ "params_dtype": "bfloat16",
397
+ "world_size": 32,
398
+ "data_parallel_size": 16,
399
+ "num_microbatches": 4
400
+ }
iter_0001600/.metadata ADDED
Binary file (478 Bytes). View file
 
iter_0001600/common.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b5a5f042553a59c1e17156562292a0bedde6c90ef62e1012742d10dadc652e5
3
+ size 16231
iter_0001600/metadata.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"sharded_backend": "torch_dist", "sharded_backend_version": 1, "common_backend": "torch", "common_backend_version": 1}
latest_checkpointed_iteration.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 1600
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00003-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:875301868cb45d776413acb5e391c7c83a40935b3058e446ab878c1d7429339a
3
+ size 4998681018
model-00004-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:206d2398eae9d628cafb43c4978d6bc5f73390b58c2b80743b703717f20004f6
3
+ size 4997754200
model-00005-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0041a8fb6da261ab722c39d50023b0d3eded67cb5764f6bbe062a27db6d5c5c1
3
+ size 4997754968
model-00006-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f49e61e88be3df501ca90fdb600528fa5e30c220b3803d19af9edaa81f0b194d
3
+ size 4997755776
model-00007-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80a2e0f1f7a5db4aeea88cb76f57235fb6fba60bbfd152ea0e3c122d15faf3b2
3
+ size 4997755776
model-00008-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b4d3cda0f6b561cb9ed0026060f2b63467ac84d7f1dbc2348a05f2684838931
3
+ size 4997755776
model-00009-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1f3f713b8f5d47facc4b7834a359600937a0e9ca8444743952262d54e4a59a1
3
+ size 4991468272
model-00010-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ade12e958e2c599c468ab334b704c6878732675b05028c86c22918a0e1db54e
3
+ size 4985172320
model-00011-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df0cd95aa0b35fec1264aebddcf13721fa0ec4caf40598b2aad8e15e25d9ec9c
3
+ size 4985172320
model-00012-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80528b751c9872259f10618072e550c3bc64482d0ac48d8395b5b5852ab64094
3
+ size 4985172320
model-00013-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e4dd85abde484fcb8efa3aaacfe8a985d935e73000969396e772edd1b55ef14
3
+ size 4985172320
model-00014-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a5983d3c5a41ebc4b4e540b81dd329531aebc9c3e686db8264b69bbd529e501
3
+ size 4985172320
model-00015-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f98305c6949839ebb4dc6b9721b059ca20d5a33a04268c7d8cf988997cd5ee0
3
+ size 622858440
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
+ "dither": 0.0,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 128,
5
+ "hop_length": 160,
6
+ "chunk_length": 1800,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
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": 16,
27
+ "processor_class": "Qwen3OmniMoeProcessor",
28
+ "return_attention_mask": true,
29
+ "sampling_rate": 16000,
30
+ "temporal_patch_size": 2
31
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>",
16
+ "<|audio_start|>",
17
+ "<|audio_end|>",
18
+ "<tts_pad>",
19
+ "<tts_text_bos>",
20
+ "<tts_text_bos_single>",
21
+ "<|audio_pad|>"
22
+ ],
23
+ "audio_bos_token": "<|audio_start|>",
24
+ "audio_eos_token": "<|audio_end|>",
25
+ "audio_token": "<|audio_pad|>",
26
+ "eos_token": {
27
+ "content": "<|im_end|>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "image_token": "<|image_pad|>",
34
+ "pad_token": {
35
+ "content": "<|endoftext|>",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "video_token": "<|video_pad|>",
42
+ "vision_bos_token": "<|vision_start|>",
43
+ "vision_eos_token": "<|vision_end|>"
44
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09267689b8362020b9763b65dd5be7e086b31e28d72e02837a9e781de9a91bc7
3
+ size 11423986
tokenizer_config.json ADDED
@@ -0,0 +1,317 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "151669": {
214
+ "content": "<|audio_start|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<|audio_end|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "<tts_pad>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "<tts_text_bos>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "<tts_text_eod>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151674": {
254
+ "content": "<tts_text_bos_single>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "151675": {
262
+ "content": "<|audio_pad|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ }
269
+ },
270
+ "additional_special_tokens": [
271
+ "<|im_start|>",
272
+ "<|im_end|>",
273
+ "<|object_ref_start|>",
274
+ "<|object_ref_end|>",
275
+ "<|box_start|>",
276
+ "<|box_end|>",
277
+ "<|quad_start|>",
278
+ "<|quad_end|>",
279
+ "<|vision_start|>",
280
+ "<|vision_end|>",
281
+ "<|vision_pad|>",
282
+ "<|image_pad|>",
283
+ "<|video_pad|>",
284
+ "<|audio_start|>",
285
+ "<|audio_end|>",
286
+ "<tts_pad>",
287
+ "<tts_text_bos>",
288
+ "<tts_text_bos_single>",
289
+ "<|audio_pad|>"
290
+ ],
291
+ "audio_bos_token": "<|audio_start|>",
292
+ "audio_eos_token": "<|audio_end|>",
293
+ "audio_token": "<|audio_pad|>",
294
+ "bos_token": null,
295
+ "clean_up_tokenization_spaces": false,
296
+ "eos_token": "<|im_end|>",
297
+ "errors": "replace",
298
+ "extra_special_tokens": {
299
+ "audio_bos_token": "<|audio_start|>",
300
+ "audio_eos_token": "<|audio_end|>",
301
+ "audio_token": "<|audio_pad|>",
302
+ "image_token": "<|image_pad|>",
303
+ "video_token": "<|video_pad|>",
304
+ "vision_bos_token": "<|vision_start|>",
305
+ "vision_eos_token": "<|vision_end|>"
306
+ },
307
+ "image_token": "<|image_pad|>",
308
+ "model_max_length": 131072,
309
+ "pad_token": "<|endoftext|>",
310
+ "processor_class": "Qwen3OmniMoeProcessor",
311
+ "split_special_tokens": false,
312
+ "tokenizer_class": "Qwen2Tokenizer",
313
+ "unk_token": null,
314
+ "video_token": "<|video_pad|>",
315
+ "vision_bos_token": "<|vision_start|>",
316
+ "vision_eos_token": "<|vision_end|>"
317
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 1800,
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
+ 0.5,
20
+ 0.5,
21
+ 0.5
22
+ ],
23
+ "image_std": [
24
+ 0.5,
25
+ 0.5,
26
+ 0.5
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": 16,
42
+ "processor_class": "Qwen3OmniMoeProcessor",
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