Upload folder using huggingface_hub

Qwen2.5-Omni-3B-Chuan/args.json

@@ -1,5 +1,5 @@
 {
-  "output_dir": "/home/work_nfs23/sywang/code/asr_rl/exp/sft_chuan2/v0-20250909-174359",
+  "output_dir": "/home/work_nfs23/sywang/code/asr_rl/sft_chuan/v0-20250729-234858",
   "overwrite_output_dir": false,
   "do_train": false,
   "do_eval": false,
@@ -10,7 +10,7 @@
   "per_device_eval_batch_size": 2,
   "per_gpu_train_batch_size": null,
   "per_gpu_eval_batch_size": null,
-  "gradient_accumulation_steps": 4,
+  "gradient_accumulation_steps": 2,
   "eval_accumulation_steps": null,
   "eval_delay": 0,
   "torch_empty_cache_steps": null,
@@ -20,7 +20,7 @@
   "adam_beta2": 0.95,
   "adam_epsilon": 1e-08,
   "max_grad_norm": 1.0,
-  "num_train_epochs": 5.0,
+  "num_train_epochs": 1.0,
   "max_steps": -1,
   "lr_scheduler_type": "cosine",
   "lr_scheduler_kwargs": null,
@@ -29,13 +29,13 @@
   "log_level": "passive",
   "log_level_replica": "warning",
   "log_on_each_node": true,
-  "logging_dir": "/home/work_nfs23/sywang/code/asr_rl/exp/sft_chuan2/v0-20250909-174359/runs",
+  "logging_dir": "/home/work_nfs23/sywang/code/asr_rl/sft_chuan/v0-20250729-234858/runs",
   "logging_strategy": "steps",
   "logging_first_step": true,
   "logging_steps": 5,
   "logging_nan_inf_filter": true,
   "save_strategy": "steps",
-  "save_steps": 2000.0,
+  "save_steps": 1000.0,
   "save_total_limit": null,
   "save_safetensors": true,
   "save_on_each_node": false,
@@ -61,11 +61,11 @@
   "tpu_metrics_debug": false,
   "debug": null,
   "dataloader_drop_last": false,
-  "eval_steps": 2000.0,
+  "eval_steps": 1000.0,
   "dataloader_num_workers": 4,
   "dataloader_prefetch_factor": null,
   "past_index": -1,
-  "run_name": "/home/work_nfs23/sywang/code/asr_rl/exp/sft_chuan2/v0-20250909-174359",
+  "run_name": "/home/work_nfs23/sywang/code/asr_rl/sft_chuan/v0-20250729-234858",
   "disable_tqdm": null,
   "remove_unused_columns": true,
   "label_names": null,
@@ -80,7 +80,6 @@
   "accelerator_config": {
     "dispatch_batches": false
   },
-  "parallelism_config": null,
   "deepspeed": {
     "fp16": {
       "enabled": "auto",
@@ -136,7 +135,6 @@
   "hub_token": null,
   "hub_private_repo": null,
   "hub_always_push": false,
-  "hub_revision": null,
   "gradient_checkpointing": true,
   "gradient_checkpointing_kwargs": null,
   "include_inputs_for_metrics": false,
@@ -162,51 +160,43 @@
   "batch_eval_metrics": false,
   "eval_on_start": false,
   "use_liger_kernel": false,
-  "liger_kernel_config": null,
   "eval_use_gather_object": false,
-  "average_tokens_across_devices": true,
+  "average_tokens_across_devices": false,
   "sortish_sampler": false,
   "predict_with_generate": false,
   "generation_max_length": null,
   "generation_num_beams": null,
   "generation_config": null,
-  "tuner_backend": "peft",
   "vit_gradient_checkpointing": null,
-  "router_aux_loss_coef": 0.0,
-  "enable_dft_loss": false,
-  "enable_channel_loss": false,
   "check_model": true,
   "acc_strategy": "token",
   "train_dataloader_shuffle": true,
   "max_epochs": null,
   "aligner_lr": null,
   "vit_lr": null,
+  "optimizer": null,
   "use_logits_to_keep": null,
+  "channels": null,
   "ds3_gather_for_generation": true,
-  "resume_only_model": false,
-  "optimizer": null,
-  "loss_type": null,
-  "metric": null,
+  "metric_warmup_step": 0,
+  "fsdp_num": 1,
+  "acc_steps": 1,
   "eval_use_evalscope": false,
   "eval_dataset": [],
   "eval_dataset_args": null,
   "eval_limit": null,
   "eval_generation_config": null,
-  "extra_eval_args": null,
-  "use_flash_ckpt": false,
   "model": "/home/work_nfs23/sywang/ckpt/Qwen2.5-Omni-3B",
   "model_type": "qwen2_5_omni",
   "model_revision": null,
   "task_type": "causal_lm",
   "torch_dtype": "bfloat16",
   "attn_impl": "flash_attn",
-  "new_special_tokens": [],
   "num_labels": null,
   "problem_type": null,
   "rope_scaling": null,
   "device_map": null,
   "max_memory": {},
-  "max_model_len": null,
   "local_repo_path": null,
   "init_strategy": null,
   "template": "qwen2_5_omni",
@@ -224,7 +214,7 @@
   "response_prefix": null,
   "template_backend": "swift",
   "dataset": [
-    "data/train/train_chuan2.jsonl"
+    "data/train_chaun.jsonl"
   ],
   "val_dataset": [],
   "split_dataset_ratio": 0.0,
@@ -261,6 +251,7 @@
   "top_logprobs": null,
   "ckpt_dir": null,
   "lora_modules": [],
+  "tuner_backend": "peft",
   "train_type": "lora",
   "adapters": [],
   "external_plugins": [],
@@ -268,14 +259,19 @@
   "load_args": false,
   "load_data_args": false,
   "packing": false,
-  "packing_length": null,
-  "lazy_tokenize": true,
-  "cached_dataset": [],
+  "packing_cache": null,
   "custom_register_path": [],
   "use_hf": false,
   "ignore_args_error": false,
   "use_swift_lora": false,
-  "freeze_parameters": [],
+  "freeze_parameters": [
+    "thinker.audio_tower",
+    "thinker.visual",
+    "thinker.audio_tower.proj",
+    "thinker.visual.merger",
+    "talker",
+    "token2wav"
+  ],
   "freeze_parameters_regex": null,
   "freeze_parameters_ratio": 0.0,
   "trainable_parameters": [],
@@ -287,7 +283,6 @@
     "all-linear"
   ],
   "target_regex": null,
-  "target_parameters": null,
   "modules_to_save": [],
   "lora_rank": 8,
   "lora_alpha": 32,
@@ -356,18 +351,20 @@
   "swanlab_lark_secret": null,
   "swanlab_mode": "cloud",
   "add_version": true,
+  "resume_only_model": false,
   "create_checkpoint_symlink": false,
+  "lazy_tokenize": true,
+  "loss_type": null,
+  "metric": null,
   "zero_hpz_partition_size": null,
-  "deepspeed_autotp_size": null,
-  "early_stop_interval": null,
   "rank": 0,
-  "global_world_size": 4,
-  "local_world_size": 4,
+  "global_world_size": 8,
+  "local_world_size": 8,
   "model_suffix": "Qwen2.5-Omni-3B",
-  "model_info": "ModelInfo(model_type='qwen2_5_omni', model_dir='/home/work_nfs23/sywang/ckpt/Qwen2.5-Omni-3B', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling={'mrope_section': [16, 24, 24], 'rope_type': 'default', 'type': 'default'}, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)",
-  "model_meta": "ModelMeta(model_type='qwen2_5_omni', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-Omni-3B', hf_model_id='Qwen/Qwen2.5-Omni-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Omni-7B', hf_model_id='Qwen/Qwen2.5-Omni-7B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_omni', get_function=<function get_model_tokenizer_qwen2_5_omni at 0x7fe20f5868e0>, model_arch=MultiModelKeys(arch_name='qwen2_5_omni', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['thinker.model'], aligner=['thinker.audio_tower.proj', 'thinker.visual.merger'], vision_tower=['thinker.audio_tower', 'thinker.visual'], generator=['talker', 'token2wav']), architectures=['Qwen2_5OmniModel', 'Qwen2_5OmniForConditionalGeneration'], additional_saved_files=['spk_dict.pt'], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=[], requires=['transformers>=4.50', 'soundfile', 'qwen_omni_utils', 'decord'], tags=['vision', 'video', 'audio'])",
+  "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)",
+  "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'])",
   "model_dir": "/home/work_nfs23/sywang/ckpt/Qwen2.5-Omni-3B",
   "hub": "<class 'swift.hub.hub.MSHub'>",
   "evaluation_strategy": "steps",
-  "training_args": "Seq2SeqTrainingArguments(output_dir='/home/work_nfs23/sywang/code/asr_rl/exp/sft_chuan2/v0-20250909-174359', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=2, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=5.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/work_nfs23/sywang/code/asr_rl/exp/sft_chuan2/v0-20250909-174359/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=2000, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=2000.0, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/home/work_nfs23/sywang/code/asr_rl/exp/sft_chuan2/v0-20250909-174359', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 2, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, train_type='lora', local_repo_path=None, galore_config=None)"
+  "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)"
 }

Qwen2.5-Omni-3B-Chuan/config.json

@@ -2,7 +2,6 @@
   "architectures": [
     "Qwen2_5OmniForConditionalGeneration"
   ],
-  "dtype": "bfloat16",
   "enable_audio_output": true,
   "enable_talker": true,
   "hidden_size": 2048,
@@ -14,7 +13,6 @@
   "model_type": "qwen2_5_omni",
   "pad_token_id": 151643,
   "talker_config": {
-    "_attn_implementation_autoset": true,
     "_name_or_path": "Qwen2.5-Omni-3B/talker",
     "architectures": [
       "Qwen2OmniTalkerForConditionalGeneration"
@@ -23,7 +21,6 @@
     "audio_end_token_id": 151648,
     "audio_start_token_id": 151647,
     "audio_token_index": 151646,
-    "dtype": "bfloat16",
     "embedding_size": 2048,
     "head_dim": 64,
     "hidden_act": "silu",
@@ -32,32 +29,6 @@
     "init_std": 0.02,
     "initializer_range": 0.02,
     "intermediate_size": 4864,
-    "layer_types": [
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention"
-    ],
     "max_position_embeddings": 32768,
     "max_window_layers": 28,
     "model_type": "qwen2_5_omni_talker",
@@ -77,8 +48,9 @@
     },
     "rope_theta": 1000000.0,
     "seconds_per_chunk": 2,
-    "sliding_window": null,
+    "sliding_window": 32768,
     "spatial_merge_size": 2,
+    "torch_dtype": "bfloat16",
     "tts_codec_end_token_id": 8294,
     "tts_codec_mask_token_id": 8296,
     "tts_codec_pad_token_id": 8292,
@@ -94,13 +66,11 @@
     "vocab_size": 8448
   },
   "thinker_config": {
-    "_attn_implementation_autoset": true,
     "_name_or_path": "Qwen2.5-Omni-3B/thinker",
     "architectures": [
       "Qwen2OmniNaViTThinkerForConditionalGeneration"
     ],
     "audio_config": {
-      "_attn_implementation_autoset": true,
       "_name_or_path": "",
       "activation_dropout": 0.0,
       "activation_function": "gelu",
@@ -117,7 +87,6 @@
       "diversity_penalty": 0.0,
       "do_sample": false,
       "dropout": 0.0,
-      "dtype": "bfloat16",
       "early_stopping": false,
       "encoder_attention_heads": 20,
       "encoder_ffn_dim": 5120,
@@ -157,7 +126,7 @@
       "output_dim": 2048,
       "output_hidden_states": false,
       "output_scores": false,
-      "pad_token_id": 151643,
+      "pad_token_id": null,
       "prefix": null,
       "problem_type": null,
       "pruned_heads": {},
@@ -176,6 +145,7 @@
       "tokenizer_class": null,
       "top_k": 50,
       "top_p": 1.0,
+      "torch_dtype": null,
       "torchscript": false,
       "typical_p": 1.0,
       "use_bfloat16": false
@@ -184,7 +154,6 @@
     "audio_start_token_id": 151647,
     "audio_token_index": 151646,
     "bos_token_id": 151644,
-    "dtype": "bfloat16",
     "eos_token_id": 151645,
     "ignore_index": -100,
     "image_token_index": 151655,
@@ -207,7 +176,6 @@
       "decoder_start_token_id": null,
       "diversity_penalty": 0.0,
       "do_sample": false,
-      "dtype": "bfloat16",
       "early_stopping": false,
       "encoder_no_repeat_ngram_size": 0,
       "eos_token_id": null,
@@ -230,44 +198,6 @@
         "LABEL_0": 0,
         "LABEL_1": 1
       },
-      "layer_types": [
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention",
-        "full_attention"
-      ],
       "length_penalty": 1.0,
       "max_length": 20,
       "max_position_embeddings": 32768,
@@ -284,7 +214,7 @@
       "output_attentions": false,
       "output_hidden_states": false,
       "output_scores": false,
-      "pad_token_id": 151643,
+      "pad_token_id": null,
       "prefix": null,
       "problem_type": null,
       "pruned_heads": {},
@@ -304,7 +234,7 @@
       },
       "rope_theta": 1000000.0,
       "sep_token_id": null,
-      "sliding_window": null,
+      "sliding_window": 32768,
       "suppress_tokens": null,
       "task_specific_params": null,
       "temperature": 1.0,
@@ -314,6 +244,7 @@
       "tokenizer_class": null,
       "top_k": 50,
       "top_p": 1.0,
+      "torch_dtype": null,
       "torchscript": false,
       "typical_p": 1.0,
       "use_bfloat16": false,
@@ -321,10 +252,10 @@
       "use_sliding_window": false,
       "vocab_size": 151936
     },
+    "torch_dtype": "bfloat16",
     "user_token_id": 872,
     "video_token_index": 151656,
     "vision_config": {
-      "_attn_implementation_autoset": true,
       "_name_or_path": "",
       "add_cross_attention": false,
       "architectures": null,
@@ -337,7 +268,6 @@
       "depth": 32,
       "diversity_penalty": 0.0,
       "do_sample": false,
-      "dtype": "bfloat16",
       "early_stopping": false,
       "embed_dim": 1280,
       "encoder_no_repeat_ngram_size": 0,
@@ -382,7 +312,7 @@
       "output_attentions": false,
       "output_hidden_states": false,
       "output_scores": false,
-      "pad_token_id": 151643,
+      "pad_token_id": null,
       "patch_size": 14,
       "prefix": null,
       "problem_type": null,
@@ -405,6 +335,7 @@
       "tokens_per_second": 25,
       "top_k": 50,
       "top_p": 1.0,
+      "torch_dtype": null,
       "torchscript": false,
       "typical_p": 1.0,
       "use_bfloat16": false,
@@ -415,9 +346,7 @@
     "vision_token_id": 151654
   },
   "token2wav_config": {
-    "_attn_implementation_autoset": true,
     "bigvgan_config": {
-      "_attn_implementation_autoset": true,
       "_name_or_path": "",
       "add_cross_attention": false,
       "architectures": null,
@@ -429,7 +358,6 @@
       "decoder_start_token_id": null,
       "diversity_penalty": 0.0,
       "do_sample": false,
-      "dtype": null,
       "early_stopping": false,
       "encoder_no_repeat_ngram_size": 0,
       "eos_token_id": null,
@@ -459,7 +387,7 @@
       "output_attentions": false,
       "output_hidden_states": false,
       "output_scores": false,
-      "pad_token_id": 151643,
+      "pad_token_id": null,
       "prefix": null,
       "problem_type": null,
       "pruned_heads": {},
@@ -499,6 +427,7 @@
       "tokenizer_class": null,
       "top_k": 50,
       "top_p": 1.0,
+      "torch_dtype": null,
       "torchscript": false,
       "typical_p": 1.0,
       "upsample_initial_channel": 1536,
@@ -522,7 +451,6 @@
       "use_bias_at_final": false
     },
     "dit_config": {
-      "_attn_implementation_autoset": true,
       "_name_or_path": "",
       "add_cross_attention": false,
       "architectures": null,
@@ -538,7 +466,6 @@
       "diversity_penalty": 0.0,
       "do_sample": false,
       "dropout": 0.1,
-      "dtype": "float32",
       "early_stopping": false,
       "emb_dim": 512,
       "enc_attention_channels": 64,
@@ -612,7 +539,7 @@
       "output_attentions": false,
       "output_hidden_states": false,
       "output_scores": false,
-      "pad_token_id": 151643,
+      "pad_token_id": null,
       "prefix": null,
       "problem_type": null,
       "pruned_heads": {},
@@ -632,13 +559,15 @@
       "tokenizer_class": null,
       "top_k": 50,
       "top_p": 1.0,
+      "torch_dtype": "float32",
       "torchscript": false,
       "typical_p": 1.0,
       "use_bfloat16": false
     },
-    "dtype": "bfloat16",
     "model_type": "qwen2_5_omni_token2wav",
-    "pad_token_id": 151643
+    "pad_token_id": 151643,
+    "torch_dtype": "bfloat16"
   },
-  "transformers_version": "4.56.0"
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.3"
 }

Qwen2.5-Omni-3B-Chuan/generation_config.json

@@ -4,5 +4,5 @@
     151643,
     151645
   ],
-  "transformers_version": "4.56.0"
+  "transformers_version": "4.52.3"
 }

Qwen2.5-Omni-3B-Chuan/model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee5ce647e0d4852a38d4a76408898e54374f9397c2dcefa7314537a55c1e6b21
-size 1570766848
+oid sha256:0bf191da971b473c15401d6e30c74af2d63a6a3d529d12588923fc31b4b357eb
+size 4994850880

Qwen2.5-Omni-3B-Chuan/model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:694f5ce71776f6caf0a94ace088cd7eeafd3c1a30e029c6e1c7a70f8221df4ba
-size 1573912576
+oid sha256:5bb9b78fcc9c696802de4924c24186e9a074739675f3b675cb3a4a022eae3cd1
+size 4999787448

Qwen2.5-Omni-3B-Chuan/model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aedb25618881ce9466eefb9872e19e81f30d281dd2b139b8c8111ae7a9025e7b
-size 1582039040
+oid sha256:8f2138170a87ec604b53232491a96d6dcf19e0724aca37e69aace143e508b170
+size 1978024880

Qwen2.5-Omni-3B-Chuan/model.safetensors.index.json

@@ -1,6 +1,5 @@
 {
   "metadata": {
-    "total_parameters": 5537120640,
     "total_size": 11972343936
   },
   "weight_map": {

Qwen2.5-Omni-3B-Chuan/video_preprocessor_config.json

@@ -1,4 +1,28 @@
 {
+  "_valid_kwargs_names": [
+    "do_convert_rgb",
+    "do_resize",
+    "size",
+    "size_divisor",
+    "default_to_square",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "do_center_crop",
+    "crop_size",
+    "data_format",
+    "input_data_format",
+    "device",
+    "min_pixels",
+    "max_pixels",
+    "patch_size",
+    "temporal_patch_size",
+    "merge_size"
+  ],
   "chunk_length": 300,
   "crop_size": null,
   "data_format": "channels_first",
@@ -11,31 +35,51 @@
   "do_pad": null,
   "do_rescale": true,
   "do_resize": true,
-  "do_sample_frames": false,
   "feature_extractor_type": "WhisperFeatureExtractor",
   "feature_size": 128,
-  "fps": null,
   "hop_length": 160,
   "image_mean": [
     0.48145466,
     0.4578275,
     0.40821073
   ],
+  "image_processor_type": "Qwen2VLImageProcessor",
   "image_std": [
     0.26862954,
     0.26130258,
     0.27577711
   ],
   "input_data_format": null,
-  "max_frames": 768,
   "max_pixels": 12845056,
   "merge_size": 2,
-  "min_frames": 4,
   "min_pixels": 3136,
+  "model_valid_processing_keys": [
+    "do_convert_rgb",
+    "do_resize",
+    "size",
+    "size_divisor",
+    "default_to_square",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "do_center_crop",
+    "crop_size",
+    "data_format",
+    "input_data_format",
+    "device",
+    "min_pixels",
+    "max_pixels",
+    "patch_size",
+    "temporal_patch_size",
+    "merge_size"
+  ],
   "n_fft": 400,
   "n_samples": 4800000,
   "nb_max_frames": 30000,
-  "num_frames": null,
   "padding_side": "right",
   "padding_value": 0.0,
   "patch_size": 14,
@@ -43,7 +87,6 @@
   "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "return_attention_mask": true,
-  "return_metadata": false,
   "sampling_rate": 16000,
   "size": {
     "longest_edge": 12845056,
@@ -51,6 +94,5 @@
   },
   "size_divisor": null,
   "temporal_patch_size": 2,
-  "video_metadata": null,
   "video_processor_type": "Qwen2VLVideoProcessor"
 }