Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<tts_pad>": 151671,
+  "<tts_text_bos>": 151672,
+  "<tts_text_bos_single>": 151674,
+  "<tts_text_eod>": 151673,
+  "<|audio_end|>": 151670,
+  "<|audio_pad|>": 151675,
+  "<|audio_start|>": 151669,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

args.json

@@ -0,0 +1,480 @@
+{
+  "model": "/data/user_data/siqiouya/ckpts/pretrained/llm/Qwen3-Omni-30B-A3B-Instruct/",
+  "model_type": "qwen3_omni",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_impl": null,
+  "new_special_tokens": [],
+  "num_labels": null,
+  "problem_type": null,
+  "rope_scaling": {
+    "interleaved": true,
+    "mrope_interleaved": true,
+    "mrope_section": [
+      24,
+      20,
+      20
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "device_map": null,
+  "max_memory": {},
+  "max_model_len": null,
+  "local_repo_path": null,
+  "init_strategy": null,
+  "template": "qwen3_omni",
+  "system": null,
+  "max_length": 2048,
+  "truncation_strategy": "delete",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "use_chat_template": true,
+  "padding_free": true,
+  "padding_side": "right",
+  "loss_scale": "default",
+  "sequence_parallel_size": 1,
+  "response_prefix": null,
+  "template_backend": "swift",
+  "dataset": [
+    "/data/group_data/li_lab/siqiouya/datasets/gigaspeech/manifests/train_s_de_v4_ner_baseline_aligned_rate1.0_k20_final.jsonl"
+  ],
+  "val_dataset": [],
+  "split_dataset_ratio": 0.01,
+  "data_seed": 42,
+  "dataset_num_proc": 8,
+  "load_from_cache_file": true,
+  "dataset_shuffle": true,
+  "val_dataset_shuffle": false,
+  "streaming": false,
+  "interleave_prob": null,
+  "stopping_strategy": "first_exhausted",
+  "shuffle_buffer_size": 1000,
+  "download_mode": "reuse_dataset_if_exists",
+  "columns": {},
+  "strict": false,
+  "remove_unused_columns": true,
+  "model_name": null,
+  "model_author": null,
+  "custom_dataset_info": [],
+  "quant_method": null,
+  "quant_bits": null,
+  "hqq_axis": null,
+  "bnb_4bit_compute_dtype": "bfloat16",
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_storage": null,
+  "max_new_tokens": null,
+  "temperature": null,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
+  "num_beams": 1,
+  "stream": false,
+  "stop_words": [],
+  "logprobs": false,
+  "top_logprobs": null,
+  "ckpt_dir": "/data/user_data/siqiouya/ckpts/pretrained/llm/Qwen3-Omni-30B-A3B-Instruct-mcore",
+  "lora_modules": [],
+  "tuner_backend": "peft",
+  "train_type": "lora",
+  "adapters": [],
+  "external_plugins": [],
+  "seed": 42,
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": true,
+  "packing_length": 2048,
+  "lazy_tokenize": false,
+  "cached_dataset": [],
+  "custom_register_path": [],
+  "use_hf": false,
+  "hub_token": null,
+  "ddp_timeout": 18000000,
+  "ddp_backend": null,
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "freeze_llm": false,
+  "freeze_vit": true,
+  "freeze_aligner": true,
+  "freeze_parameters": [],
+  "freeze_parameters_regex": null,
+  "freeze_parameters_ratio": 0.0,
+  "trainable_parameters": [],
+  "trainable_parameters_regex": null,
+  "adapter_load": null,
+  "target_modules": [
+    "all-linear"
+  ],
+  "target_regex": null,
+  "modules_to_save": [],
+  "lora_rank": 8,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "lora_bias": "none",
+  "lora_dtype": null,
+  "use_rslora": false,
+  "rlhf_type": null,
+  "ref_load": null,
+  "ref_adapter_load": null,
+  "beta": 0.1,
+  "rpo_alpha": null,
+  "reference_free": false,
+  "label_smoothing": 0.0,
+  "f_divergence_type": "reverse_kl",
+  "loss_type": null,
+  "desirable_weight": 1.0,
+  "undesirable_weight": 1.0,
+  "calculate_KL": null,
+  "center_rewards_coefficient": null,
+  "padded_vocab_size": 152064,
+  "initialize_embedding": false,
+  "mlp_padding_free": false,
+  "dataloader_persistent_workers": true,
+  "dataloader_prefetch_factor": 10,
+  "architectures": "Qwen3OmniMoeForConditionalGeneration",
+  "llm_architectures": null,
+  "max_epochs": 1,
+  "enable_dft_loss": false,
+  "enable_channel_loss": false,
+  "original_max_position_embeddings": null,
+  "partial_rotary_factor": null,
+  "use_shared_expert_gate": false,
+  "vit_gradient_checkpointing": false,
+  "gradient_checkpointing_kwargs": null,
+  "linear_num_value_heads": null,
+  "linear_num_key_heads": null,
+  "linear_key_head_dim": null,
+  "linear_value_head_dim": null,
+  "linear_conv_kernel_dim": null,
+  "layer_types": null,
+  "mrope_interleaved": true,
+  "micro_batch_size": 1,
+  "global_batch_size": 4,
+  "recompute_granularity": "full",
+  "recompute_method": "uniform",
+  "recompute_num_layers": 1,
+  "recompute_modules": [
+    "core_attn"
+  ],
+  "use_cpu_initialization": false,
+  "deterministic_mode": false,
+  "train_iters": null,
+  "log_interval": 10,
+  "tensorboard_dir": "/data/user_data/siqiouya/ckpts/infinisst-omni/gigaspeech-de-s_v4_ner_baseline_aligned_rate1.0_k20_final/v0-20260106-025939/runs",
+  "no_masked_softmax_fusion": false,
+  "no_bias_dropout_fusion": false,
+  "no_bias_swiglu_fusion": false,
+  "no_rope_fusion": false,
+  "no_gradient_accumulation_fusion": false,
+  "cross_entropy_loss_fusion": true,
+  "cross_entropy_fusion_impl": "native",
+  "calculate_per_token_loss": true,
+  "use_flash_attn": false,
+  "attention_backend": "flash",
+  "optimizer": "adam",
+  "optimizer_cpu_offload": false,
+  "optimizer_offload_fraction": 1.0,
+  "use_precision_aware_optimizer": false,
+  "main_grads_dtype": "fp32",
+  "main_params_dtype": "fp32",
+  "exp_avg_dtype": "fp32",
+  "exp_avg_sq_dtype": "fp32",
+  "dataloader_type": "cyclic",
+  "manual_gc": false,
+  "manual_gc_interval": 0,
+  "lr": 0.0001,
+  "lr_decay_style": "cosine",
+  "lr_decay_iters": null,
+  "lr_warmup_iters": 0,
+  "lr_warmup_fraction": 0.05,
+  "min_lr": 1e-05,
+  "weight_decay": 0.01,
+  "clip_grad": 1.0,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_eps": 1e-08,
+  "sgd_momentum": 0.9,
+  "save": "/data/user_data/siqiouya/ckpts/infinisst-omni/gigaspeech-de-s_v4_ner_baseline_aligned_rate1.0_k20_final/v0-20260106-025939",
+  "save_interval": 200,
+  "no_save_optim": true,
+  "no_save_rng": true,
+  "load": "/data/user_data/siqiouya/ckpts/pretrained/llm/Qwen3-Omni-30B-A3B-Instruct-mcore",
+  "no_load_optim": false,
+  "no_load_rng": false,
+  "finetune": true,
+  "ckpt_format": "torch_dist",
+  "no_initialization": true,
+  "auto_detect_ckpt_format": true,
+  "exit_on_missing_checkpoint": true,
+  "distributed_backend": "nccl",
+  "local_rank": 0,
+  "use_distributed_optimizer": true,
+  "tensor_model_parallel_size": 1,
+  "pipeline_model_parallel_size": 1,
+  "decoder_first_pipeline_num_layers": null,
+  "decoder_last_pipeline_num_layers": null,
+  "sequence_parallel": false,
+  "context_parallel_size": 1,
+  "tp_comm_overlap": false,
+  "overlap_grad_reduce": false,
+  "overlap_param_gather": false,
+  "distributed_timeout_minutes": 300000,
+  "num_layers_per_virtual_pipeline_stage": null,
+  "num_virtual_stages_per_pipeline_rank": null,
+  "microbatch_group_size_per_virtual_pipeline_stage": null,
+  "pipeline_model_parallel_layout": null,
+  "num_layers": 48,
+  "hidden_size": 2048,
+  "ffn_hidden_size": null,
+  "num_attention_heads": 32,
+  "group_query_attention": true,
+  "num_query_groups": 4,
+  "max_position_embeddings": 65536,
+  "position_embedding_type": "mrope",
+  "mrope_section": [
+    24,
+    20,
+    20
+  ],
+  "rotary_base": 1000000,
+  "rotary_percent": 1.0,
+  "rotary_interleaved": false,
+  "normalization": "RMSNorm",
+  "norm_epsilon": 1e-06,
+  "swiglu": true,
+  "untie_embeddings_and_output_weights": true,
+  "disable_bias_linear": true,
+  "add_qkv_bias": false,
+  "attention_dropout": 0.0,
+  "hidden_dropout": 0.0,
+  "kv_channels": 128,
+  "qk_layernorm": true,
+  "transformer_impl": "transformer_engine",
+  "num_experts": 128,
+  "moe_layer_freq": "1",
+  "moe_ffn_hidden_size": 768,
+  "moe_shared_expert_intermediate_size": null,
+  "moe_router_topk": 8,
+  "moe_router_pre_softmax": false,
+  "moe_router_dtype": "fp32",
+  "moe_router_score_function": "softmax",
+  "moe_router_bias_update_rate": 0.001,
+  "moe_router_enable_expert_bias": false,
+  "moe_router_topk_scaling_factor": null,
+  "moe_router_load_balancing_type": "aux_loss",
+  "expert_model_parallel_size": 2,
+  "expert_tensor_parallel_size": 1,
+  "moe_token_dispatcher_type": null,
+  "moe_enable_deepep": false,
+  "moe_grouped_gemm": true,
+  "moe_permute_fusion": true,
+  "moe_aux_loss_coeff": 0.001,
+  "moe_z_loss_coeff": null,
+  "moe_shared_expert_overlap": true,
+  "moe_layer_recompute": false,
+  "moe_expert_capacity_factor": null,
+  "moe_pad_expert_input_to_capacity": false,
+  "moe_token_drop_policy": null,
+  "multi_latent_attention": false,
+  "q_lora_rank": null,
+  "kv_lora_rank": 32,
+  "qk_head_dim": 128,
+  "qk_pos_emb_head_dim": 64,
+  "fp8_format": null,
+  "fp8_recipe": "delayed",
+  "fp8_amax_history_len": 1024,
+  "fp8_amax_compute_algo": "max",
+  "fp8_param_gather": false,
+  "fp16": false,
+  "bf16": true,
+  "apply_query_key_layer_scaling": false,
+  "attention_softmax_in_fp32": true,
+  "log_params_norm": false,
+  "log_throughput": false,
+  "tensorboard_log_interval": 1,
+  "tensorboard_queue_size": 50,
+  "log_timers_to_tensorboard": true,
+  "no_log_learning_rate_to_tensorboard": false,
+  "log_validation_ppl_to_tensorboard": true,
+  "log_memory_to_tensorboard": true,
+  "logging_level": null,
+  "wandb_project": "gigaspeech_de",
+  "wandb_exp_name": "omni-gigaspeech-de-s_v4_ner_baseline_aligned_rate1.0_k20_final",
+  "wandb_save_dir": null,
+  "eval_iters": -1,
+  "eval_interval": 200,
+  "seq_length": 2048,
+  "num_workers": 8,
+  "extra_megatron_kwargs": {},
+  "add_version": true,
+  "rank": 0,
+  "global_world_size": 2,
+  "local_world_size": 2,
+  "model_suffix": "Qwen3-Omni-30B-A3B-Instruct",
+  "model_info": "ModelInfo(model_type='qwen3_omni', model_dir='/data/user_data/siqiouya/ckpts/pretrained/llm/Qwen3-Omni-30B-A3B-Instruct', 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, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='qwen3_omni', 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)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_omni', get_function=<function get_model_tokenizer_qwen3_omni at 0x150f8b44ea20>, 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'], 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', 'token2wav']), 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'])",
+  "model_dir": "/data/user_data/siqiouya/ckpts/pretrained/llm/Qwen3-Omni-30B-A3B-Instruct",
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "megatron_model_meta": "MMGPTMegatronModelMeta(megatron_model_type='qwen3_omni', model_types=['qwen3_omni'], convert_mcore2hf=<function convert_mcore2hf_qwen3_omni at 0x150ef4ae1300>, convert_hf2mcore=<function convert_hf2mcore_qwen3_omni at 0x150ef4ae1260>, model_cls=<class 'swift.megatron.model.mm_gpt.qwen3_vl.Qwen3VLGPTModel'>, convert_hf_config=<function convert_gpt_hf_config at 0x150ef4a899e0>, get_transformer_layer_spec=None, model_provider=<function model_provider at 0x150ef4a887c0>, visual_cls=<class 'swift.megatron.model.mm_gpt.qwen3_vl.Qwen3Omni_Vit'>, extra_args_provider=None)",
+  "extra_args": {
+    "model": "/data/user_data/siqiouya/ckpts/pretrained/llm/Qwen3-Omni-30B-A3B-Instruct/",
+    "model_type": "qwen3_omni",
+    "model_revision": null,
+    "task_type": "causal_lm",
+    "torch_dtype": "bfloat16",
+    "attn_impl": null,
+    "new_special_tokens": [],
+    "num_labels": null,
+    "problem_type": null,
+    "rope_scaling": {
+      "interleaved": true,
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "device_map": null,
+    "max_memory": {},
+    "max_model_len": null,
+    "local_repo_path": null,
+    "init_strategy": null,
+    "template": "qwen3_omni",
+    "system": null,
+    "max_length": 2048,
+    "truncation_strategy": "delete",
+    "max_pixels": null,
+    "agent_template": null,
+    "norm_bbox": null,
+    "use_chat_template": true,
+    "padding_free": true,
+    "padding_side": "right",
+    "sequence_parallel_size": 1,
+    "response_prefix": null,
+    "template_backend": "swift",
+    "dataset": [
+      "/data/group_data/li_lab/siqiouya/datasets/gigaspeech/manifests/train_s_de_v4_ner_baseline_aligned_rate1.0_k20_final.jsonl"
+    ],
+    "val_dataset": [],
+    "split_dataset_ratio": 0.01,
+    "data_seed": 42,
+    "dataset_num_proc": 8,
+    "load_from_cache_file": true,
+    "dataset_shuffle": true,
+    "val_dataset_shuffle": false,
+    "streaming": false,
+    "interleave_prob": null,
+    "stopping_strategy": "first_exhausted",
+    "shuffle_buffer_size": 1000,
+    "download_mode": "reuse_dataset_if_exists",
+    "columns": {},
+    "strict": false,
+    "remove_unused_columns": true,
+    "model_name": null,
+    "model_author": null,
+    "custom_dataset_info": [],
+    "quant_method": null,
+    "quant_bits": null,
+    "hqq_axis": null,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "bnb_4bit_quant_storage": null,
+    "max_new_tokens": null,
+    "temperature": null,
+    "top_k": null,
+    "top_p": null,
+    "repetition_penalty": null,
+    "num_beams": 1,
+    "stream": false,
+    "stop_words": [],
+    "logprobs": false,
+    "top_logprobs": null,
+    "ckpt_dir": "/data/user_data/siqiouya/ckpts/pretrained/llm/Qwen3-Omni-30B-A3B-Instruct-mcore",
+    "lora_modules": [],
+    "tuner_backend": "peft",
+    "train_type": "lora",
+    "adapters": [],
+    "external_plugins": [],
+    "model_kwargs": {},
+    "load_args": false,
+    "load_data_args": false,
+    "packing": true,
+    "packing_length": 2048,
+    "lazy_tokenize": false,
+    "cached_dataset": [],
+    "custom_register_path": [],
+    "use_hf": false,
+    "hub_token": null,
+    "ddp_timeout": 18000000,
+    "ddp_backend": null,
+    "ignore_args_error": false,
+    "use_swift_lora": false,
+    "freeze_llm": false,
+    "freeze_vit": true,
+    "freeze_aligner": true,
+    "freeze_parameters": [],
+    "freeze_parameters_regex": null,
+    "freeze_parameters_ratio": 0.0,
+    "trainable_parameters": [],
+    "trainable_parameters_regex": null,
+    "adapter_load": null,
+    "target_modules": [
+      "all-linear"
+    ],
+    "target_regex": null,
+    "modules_to_save": [],
+    "lora_rank": 8,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "lora_bias": "none",
+    "lora_dtype": null,
+    "use_rslora": false,
+    "rlhf_type": null,
+    "ref_load": null,
+    "ref_adapter_load": null,
+    "beta": 0.1,
+    "rpo_alpha": null,
+    "reference_free": false,
+    "label_smoothing": 0.0,
+    "f_divergence_type": "reverse_kl",
+    "loss_type": null,
+    "desirable_weight": 1.0,
+    "undesirable_weight": 1.0,
+    "calculate_KL": null,
+    "center_rewards_coefficient": null,
+    "padded_vocab_size": 152064,
+    "initialize_embedding": false,
+    "mlp_padding_free": false,
+    "dataloader_persistent_workers": true,
+    "dataloader_prefetch_factor": 10,
+    "architectures": "Qwen3OmniMoeForConditionalGeneration",
+    "llm_architectures": null,
+    "max_epochs": 1,
+    "enable_dft_loss": false,
+    "enable_channel_loss": false,
+    "original_max_position_embeddings": null,
+    "partial_rotary_factor": null,
+    "use_shared_expert_gate": false,
+    "vit_gradient_checkpointing": false,
+    "gradient_checkpointing_kwargs": null,
+    "linear_num_value_heads": null,
+    "linear_num_key_heads": null,
+    "linear_key_head_dim": null,
+    "linear_value_head_dim": null,
+    "linear_conv_kernel_dim": null,
+    "layer_types": null,
+    "mrope_interleaved": true,
+    "add_version": true,
+    "model_info": "ModelInfo(model_type='qwen3_omni', model_dir='/data/user_data/siqiouya/ckpts/pretrained/llm/Qwen3-Omni-30B-A3B-Instruct', 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, config=None, task_type='causal_lm', num_labels=None)",
+    "model_meta": "ModelMeta(model_type='qwen3_omni', 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)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_omni', get_function=<function get_model_tokenizer_qwen3_omni at 0x150f8b44ea20>, 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'], 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', 'token2wav']), 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'])",
+    "megatron_model_meta": "MMGPTMegatronModelMeta(megatron_model_type='qwen3_omni', model_types=['qwen3_omni'], convert_mcore2hf=<function convert_mcore2hf_qwen3_omni at 0x150ef4ae1300>, convert_hf2mcore=<function convert_hf2mcore_qwen3_omni at 0x150ef4ae1260>, model_cls=<class 'swift.megatron.model.mm_gpt.qwen3_vl.Qwen3VLGPTModel'>, convert_hf_config=<function convert_gpt_hf_config at 0x150ef4a899e0>, get_transformer_layer_spec=None, model_provider=<function model_provider at 0x150ef4a887c0>, visual_cls=<class 'swift.megatron.model.mm_gpt.qwen3_vl.Qwen3Omni_Vit'>, extra_args_provider=None)"
+  }
+}

chat_template.jinja

@@ -0,0 +1,122 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {{- "<|vision_start|><|image_pad|><|vision_end|>" }}
+                {%- elif content.type == 'audio' or 'audio' in content or 'audio_url' in content %}
+                    {{- "<|audio_start|><|audio_pad|><|audio_end|>" }}
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {{- "<|vision_start|><|video_pad|><|vision_end|>" }}
+                {%- elif content.type == 'text' %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+    {%- endif %}
+    {{- '\n\n' }}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {{- '<|im_start|>system\n' +"<|vision_start|><|image_pad|><|vision_end|>"+ '<|im_end|>\n' }}
+                {%- elif content.type == 'audio' or 'audio' in content or 'audio_url' in content %}
+                    {{- '<|im_start|>system\n' +"<|audio_start|><|audio_pad|><|audio_end|>"+ '<|im_end|>\n' }}
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {{- '<|im_start|>system\n' +"<|vision_start|><|video_pad|><|vision_end|>"+ '<|im_end|>\n' }}
+                {%- elif content.type == 'text' %}
+                    {{- '<|im_start|>system\n' +content.text+ '<|im_end|>\n' }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = namespace(text="") %}
+        {%- for mcontent in message.content %}
+            {%- if mcontent.type == 'image' or 'image' in mcontent or 'image_url' in mcontent %}
+                {%- set content.text = content.text~"<|vision_start|><|image_pad|><|vision_end|>" %}
+            {%- elif mcontent.type == 'audio' or 'audio' in mcontent or 'audio_url' in mcontent %}
+                {%- set content.text = content.text~"<|audio_start|><|audio_pad|><|audio_end|>" %}
+            {%- elif mcontent.type == 'video' or 'video' in mcontent %}
+                {%- set content.text = content.text~"<|vision_start|><|video_pad|><|vision_end|>" %}
+            {%- elif mcontent.type == 'text' %}
+                {%- set content.text = content.text~mcontent.text %}
+            {%- endif %}
+        {%- endfor %}
+        {%- set content = content.text %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = "" %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+            {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+        {%- endif %}
+    {%- endif %}
+    {%- if loop.index0 > ns.last_query_index %}
+        {%- if loop.last or (not loop.last and reasoning_content) %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip("\n") + '\n</think>\n\n' + content.lstrip('\n') }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '\n' + content }}
+    {%- endif %}
+    {%- if message.tool_calls %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if (loop.first and content) or (not loop.first) %}{{- '\n' }}{%- endif %}
+            {%- if tool_call.function %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {%- if tool_call.arguments is string %}
+                {{- tool_call.arguments }}
+            {%- else %}
+                {{- tool_call.arguments | tojson }}
+            {%- endif %}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}{{- '<|im_start|>user' }}{%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}{{- '<|im_end|>\n' }}{%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}{{- '<think>\n\n</think>\n\n' }}{%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,560 @@
+{
+  "architectures": [
+    "Qwen3OmniMoeForConditionalGeneration"
+  ],
+  "assistant_token_id": 77091,
+  "code2wav_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "codebook_dim": 512,
+    "codebook_size": 2048,
+    "decoder_dim": 1536,
+    "dtype": "bfloat16",
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "intermediate_size": 3072,
+    "layer_scale_initial_scale": 0.01,
+    "max_position_embeddings": 8000,
+    "model_type": "",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 8,
+    "num_key_value_heads": 16,
+    "num_quantizers": 16,
+    "num_semantic_quantizers": 1,
+    "pad_token_id": 151643,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 10000,
+    "semantic_codebook_size": 4096,
+    "sliding_window": 72,
+    "upsample_rates": [
+      8,
+      5,
+      4,
+      3
+    ],
+    "upsampling_ratios": [
+      2,
+      2
+    ],
+    "vector_quantization_hidden_dimension": 512
+  },
+  "dtype": "bfloat16",
+  "enable_audio_output": true,
+  "hidden_size": 1024,
+  "im_end_token_id": 151645,
+  "im_start_token_id": 151644,
+  "keys_to_ignore_at_inference": [
+    "past_key_values",
+    "hidden_states",
+    "attention_mask"
+  ],
+  "model_type": "qwen3_omni_moe",
+  "pad_token_id": 151643,
+  "system_token_id": 8948,
+  "talker_config": {
+    "accept_hidden_layer": 24,
+    "audio_end_token_id": 151670,
+    "audio_start_token_id": 151669,
+    "audio_token_id": 151675,
+    "code_predictor_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_bias": false,
+      "attention_dropout": 0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "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,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "head_dim": 128,
+      "hidden_act": "silu",
+      "hidden_size": 1024,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 3072,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_types": [
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention"
+      ],
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "max_position_embeddings": 32768,
+      "max_window_layers": 28,
+      "min_length": 0,
+      "model_type": "qwen3_omni_moe_talker_code_predictor",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 16,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_code_groups": 16,
+      "num_hidden_layers": 5,
+      "num_key_value_heads": 8,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": 151643,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "rms_norm_eps": 1e-06,
+      "rope_scaling": null,
+      "rope_theta": 1000000,
+      "sep_token_id": null,
+      "sliding_window": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": false,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "use_cache": true,
+      "use_sliding_window": false,
+      "vocab_size": 2048
+    },
+    "codec_bos_id": 2149,
+    "codec_eos_token_id": 2150,
+    "codec_nothink_id": 2155,
+    "codec_pad_id": 2148,
+    "codec_think_bos_id": 2156,
+    "codec_think_eos_id": 2157,
+    "dtype": "bfloat16",
+    "image_token_id": 151655,
+    "model_type": "",
+    "num_code_groups": 16,
+    "output_router_logits": false,
+    "position_id_per_seconds": 13,
+    "seconds_per_chunk": 2,
+    "spatial_merge_size": 2,
+    "speaker_id": {
+      "aiden": 2303,
+      "chelsie": 2301,
+      "ethan": 2302
+    },
+    "text_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_bias": false,
+      "attention_dropout": 0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_sparse_step": 1,
+      "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,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "head_dim": 128,
+      "hidden_act": "silu",
+      "hidden_size": 1024,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 2048,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "max_position_embeddings": 65536,
+      "min_length": 0,
+      "mlp_only_layers": [],
+      "model_type": "qwen3_omni_moe_talker_text",
+      "moe_intermediate_size": 384,
+      "no_repeat_ngram_size": 0,
+      "norm_topk_prob": true,
+      "num_attention_heads": 16,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_experts": 128,
+      "num_experts_per_tok": 6,
+      "num_hidden_layers": 20,
+      "num_key_value_heads": 2,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_router_logits": false,
+      "output_scores": false,
+      "pad_token_id": 151643,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "rms_norm_eps": 1e-06,
+      "rope_scaling": {
+        "interleaved": true,
+        "mrope_interleaved": true,
+        "mrope_section": [
+          24,
+          20,
+          20
+        ],
+        "rope_type": "default",
+        "type": "default"
+      },
+      "rope_theta": 1000000,
+      "router_aux_loss_coef": 0.001,
+      "sep_token_id": null,
+      "shared_expert_intermediate_size": 768,
+      "sliding_window": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": false,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "use_cache": true,
+      "use_sliding_window": false,
+      "vocab_size": 3072
+    },
+    "thinker_hidden_size": 2048,
+    "video_token_id": 151656,
+    "vision_start_token_id": 151652
+  },
+  "thinker_config": {
+    "audio_config": {
+      "_name_or_path": "",
+      "activation_dropout": 0,
+      "activation_function": "gelu",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "conv_chunksize": 500,
+      "cross_attention_hidden_size": null,
+      "d_model": 1280,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "downsample_hidden_size": 480,
+      "dropout": 0,
+      "dtype": "bfloat16",
+      "early_stopping": false,
+      "encoder_attention_heads": 20,
+      "encoder_ffn_dim": 5120,
+      "encoder_layers": 32,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "max_source_positions": 1500,
+      "min_length": 0,
+      "model_type": "qwen3_omni_moe_audio_encoder",
+      "n_window": 50,
+      "n_window_infer": 800,
+      "no_repeat_ngram_size": 0,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_hidden_layers": 32,
+      "num_mel_bins": 128,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_dim": 2048,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": 151643,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "scale_embedding": false,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
+    "audio_end_token_id": 151670,
+    "audio_start_token_id": 151669,
+    "audio_token_id": 151675,
+    "dtype": "bfloat16",
+    "image_token_id": 151655,
+    "initializer_range": 0.02,
+    "model_type": "qwen3_omni_moe_thinker",
+    "pad_token_id": 151643,
+    "position_id_per_seconds": 13,
+    "seconds_per_chunk": 2,
+    "text_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_bias": false,
+      "attention_dropout": 0.0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_sparse_step": 1,
+      "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,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "head_dim": 128,
+      "hidden_act": "silu",
+      "hidden_size": 2048,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 768,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "max_position_embeddings": 65536,
+      "min_length": 0,
+      "mlp_only_layers": [],
+      "model_type": "qwen3_omni_moe_text",
+      "moe_intermediate_size": 768,
+      "no_repeat_ngram_size": 0,
+      "norm_topk_prob": true,
+      "num_attention_heads": 32,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_experts": 128,
+      "num_experts_per_tok": 8,
+      "num_hidden_layers": 48,
+      "num_key_value_heads": 4,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_router_logits": false,
+      "output_scores": false,
+      "pad_token_id": 151643,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "rms_norm_eps": 1e-06,
+      "rope_scaling": {
+        "interleaved": true,
+        "mrope_interleaved": true,
+        "mrope_section": [
+          24,
+          20,
+          20
+        ],
+        "rope_type": "default",
+        "type": "default"
+      },
+      "rope_theta": 1000000,
+      "router_aux_loss_coef": 0.001,
+      "sep_token_id": null,
+      "shared_expert_intermediate_size": 0,
+      "sliding_window": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": false,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "use_cache": true,
+      "use_qk_norm": true,
+      "use_sliding_window": false,
+      "vocab_size": 152064
+    },
+    "user_token_id": 872,
+    "video_token_id": 151656,
+    "vision_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "apply_vit_abs_pos_embed": true,
+      "architectures": null,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "deepstack_visual_indexes": [
+        8,
+        16,
+        24
+      ],
+      "depth": 27,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "dtype": "bfloat16",
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "hidden_act": "gelu_pytorch_tanh",
+      "hidden_size": 1152,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_size": 768,
+      "in_channels": 3,
+      "in_chans": 3,
+      "initializer_range": 0.02,
+      "intermediate_size": 4304,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "model_type": "qwen3_omni_moe_vision_encoder",
+      "no_repeat_ngram_size": 0,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_heads": 16,
+      "num_position_embeddings": 2304,
+      "num_return_sequences": 1,
+      "out_hidden_size": 2048,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": 151643,
+      "patch_size": 16,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "spatial_merge_size": 2,
+      "spatial_patch_size": 16,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "temporal_patch_size": 2,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "tokens_per_second": 2,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652
+  },
+  "transformers_version": "4.57.1",
+  "tts_bos_token_id": 151672,
+  "tts_eos_token_id": 151673,
+  "tts_pad_token_id": 151671,
+  "user_token_id": 872
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "eos_token_id": [
+    151643,
+    151645
+  ],
+  "talker_max_new_tokens": 4096,
+  "talker_repetition_penalty": 1.05,
+  "talker_temperature": 0.9,
+  "talker_top_k": 50,
+  "talker_top_p": 1.0,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f44e70f971d30228d7f55ed4166603380ef6ede4fb259bd9520a01312a26fd6
+size 4997899632

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:987f9fdfabb3f90b00b4751a16aa50f50cff8e5d35637a487f68f06aa43546e9
+size 4997754216

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb026a05ef13968265647c1051b79d1352f52c781f2f7c43887d5d1ab35e7ba2
+size 4997754216

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2375cdb34b2c036819a6f50608167e7b09ded9547d841afb34e9698e84a2e2f9
+size 4997755648

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8225a98fa5afa91b322081d67b8d18a35bda2357cf6cac929f766f4d4be64ac9
+size 4997755792

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ecb4af6f0edada5aad83d92fe1174a70c1f2e3ae26351579c637d0003962f63
+size 4997755792

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c7b27c42418def7118949b4b4296d3c734fb00c8dc11350d9fcfa4122ae4f8c
+size 4997755792

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85b62d261ea78ee843ede5bee156c6fd3b50e62e691e76cf48b711af02148271
+size 4997755792

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c942ec86a356cc597ba20f4627c1a8178b15ae6839d929bbb8933cfaa7b55765
+size 4997755792

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54c053b3b9b99612ee8ced0929be1a49eda2733576d86a83eff4b3e5786dab6b
+size 4997755792

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24c3f98b65acb5fe29671537ad47136c1c8c7e2dd2414dee06cf07d33833b784
+size 4997755792

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5181cef513eb59e15a4916f1c99fd94f72928d5b29d97e8b906a9470e24ca5e9
+size 4997755792

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e002c98479bdbefed0d4e1d66cdd1897969c842753555573ae43eceb89519095
+size 4999771808

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73f09f187ff7b469a8937b39b8ac772e539e0d61311526c345558c5e6a6eb09a
+size 4996618552

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68880d566a50643807a4e73f5227c4f468bb31532925ed5fae78a51bdd39492a
+size 553698794

preprocessor_config.json

@@ -0,0 +1,30 @@
+{
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "n_fft": 400,
+  "n_samples": 4800000,
+  "nb_max_frames": 30000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "patch_size": 16,
+  "processor_class": "Qwen3OmniMoeProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "temporal_patch_size": 2
+}

special_tokens_map.json

@@ -0,0 +1,44 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<|audio_start|>",
+    "<|audio_end|>",
+    "<tts_pad>",
+    "<tts_text_bos>",
+    "<tts_text_bos_single>",
+    "<|audio_pad|>"
+  ],
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<|image_pad|>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09267689b8362020b9763b65dd5be7e086b31e28d72e02837a9e781de9a91bc7
+size 11423986

tokenizer_config.json

@@ -0,0 +1,317 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151669": {
+      "content": "<|audio_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<|audio_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<tts_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<tts_text_bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "<tts_text_eod>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151674": {
+      "content": "<tts_text_bos_single>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151675": {
+      "content": "<|audio_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<|audio_start|>",
+    "<|audio_end|>",
+    "<tts_pad>",
+    "<tts_text_bos>",
+    "<tts_text_bos_single>",
+    "<|audio_pad|>"
+  ],
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "image_token": "<|image_pad|>",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen3OmniMoeProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

video_preprocessor_config.json

@@ -0,0 +1,54 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "dither": 0.0,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "fps": null,
+  "hop_length": 160,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_frames": 4,
+  "min_pixels": 3136,
+  "n_fft": 400,
+  "n_samples": 4800000,
+  "nb_max_frames": 30000,
+  "num_frames": null,
+  "pad_size": null,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "patch_size": 16,
+  "processor_class": "Qwen3OmniMoeProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_attention_mask": true,
+  "return_metadata": false,
+  "sampling_rate": 16000,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}