Add files using upload-large-folder tool

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Figures/LAT-Audio.png 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 +1,399 @@
+{
+  "use_ray": false,
+  "ray_exp_name": null,
+  "device_groups": null,
+  "model": "/mnt/data/share-ssd/user/shaomingchen/code/long-audio/time-aware/ft_omni/Qwen3-Omni-30B-A3B-Instruct",
+  "model_type": "qwen3_omni_moe",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_impl": null,
+  "experts_impl": null,
+  "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": "qwen3_omni",
+  "system": "You are a helpful assistant.",
+  "max_length": 32768,
+  "truncation_strategy": "delete",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "use_chat_template": true,
+  "padding_side": "right",
+  "padding_free": true,
+  "loss_scale": "default",
+  "sequence_parallel_size": 1,
+  "template_backend": "swift",
+  "response_prefix": null,
+  "enable_thinking": null,
+  "add_non_thinking_prefix": true,
+  "dataset": [
+    "/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/train.jsonl"
+  ],
+  "val_dataset": [
+    "/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/val.jsonl"
+  ],
+  "cached_dataset": [],
+  "cached_val_dataset": [],
+  "split_dataset_ratio": 0.0,
+  "data_seed": 42,
+  "dataset_num_proc": 64,
+  "load_from_cache_file": false,
+  "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": [
+    "swift-robot"
+  ],
+  "model_author": [
+    "swift"
+  ],
+  "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": 0.9,
+  "top_k": 50,
+  "top_p": 0.9,
+  "repetition_penalty": 1.0,
+  "num_beams": 1,
+  "stream": false,
+  "stop_words": [],
+  "logprobs": false,
+  "top_logprobs": null,
+  "structured_outputs_regex": null,
+  "tuner_backend": "peft",
+  "tuner_type": "full",
+  "train_type": null,
+  "adapters": [],
+  "external_plugins": [],
+  "custom_register_path": [],
+  "seed": 42,
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_length": null,
+  "packing_num_proc": 1,
+  "lazy_tokenize": true,
+  "use_hf": false,
+  "hub_token": null,
+  "ddp_timeout": 18000000,
+  "ddp_backend": "nccl",
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "freeze_llm": false,
+  "freeze_vit": false,
+  "freeze_aligner": false,
+  "freeze_parameters": [
+    "visual.talker",
+    "visual.code2wav"
+  ],
+  "freeze_parameters_regex": null,
+  "freeze_parameters_ratio": 0.0,
+  "trainable_parameters": [
+    "visual.thinker.audio_tower.proj1",
+    "visual.thinker.audio_tower.proj2",
+    "visual.thinker.visual.merger",
+    "visual.thinker.visual.merger_list"
+  ],
+  "trainable_parameters_regex": 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,
+  "loss_type": null,
+  "mcore_ref_model": null,
+  "mcore_ref_adapter": null,
+  "beta": null,
+  "rpo_alpha": null,
+  "reference_free": false,
+  "label_smoothing": 0.0,
+  "f_divergence_type": "reverse_kl",
+  "desirable_weight": 1.0,
+  "undesirable_weight": 1.0,
+  "calculate_KL": null,
+  "center_rewards_coefficient": null,
+  "teacher_model": null,
+  "teacher_model_type": null,
+  "teacher_model_revision": null,
+  "lmbda": 0.5,
+  "seq_kd": false,
+  "offload_teacher_model": false,
+  "sft_alpha": 0.0,
+  "generation_batch_size": null,
+  "steps_per_generation": null,
+  "num_generations": 8,
+  "num_generations_eval": null,
+  "max_completion_length": 512,
+  "importance_sampling_level": "token",
+  "tau_pos": 1.0,
+  "tau_neg": 1.05,
+  "epsilon": 0.2,
+  "epsilon_high": null,
+  "delta": null,
+  "use_vllm": true,
+  "vllm_mode": null,
+  "vllm_enable_prefix_caching": true,
+  "vllm_gpu_memory_utilization": 0.9,
+  "vllm_tensor_parallel_size": 1,
+  "vllm_max_model_len": null,
+  "vllm_enforce_eager": false,
+  "vllm_limit_mm_per_prompt": null,
+  "vllm_disable_cascade_attn": false,
+  "vllm_max_num_seqs": null,
+  "vllm_mm_processor_cache_gb": null,
+  "vllm_engine_kwargs": null,
+  "sleep_level": 0,
+  "offload_optimizer": false,
+  "offload_model": false,
+  "offload_bridge": false,
+  "vllm_server_base_url": null,
+  "vllm_server_host": null,
+  "vllm_server_port": [
+    8000
+  ],
+  "vllm_server_timeout": 240.0,
+  "vllm_server_group_port": null,
+  "reward_funcs": [],
+  "reward_weights": null,
+  "cosine_min_len_value_wrong": -0.5,
+  "cosine_max_len_value_wrong": 0.0,
+  "cosine_min_len_value_correct": 1.0,
+  "cosine_max_len_value_correct": 0.5,
+  "cosine_max_len": null,
+  "repetition_n_grams": 3,
+  "repetition_max_penalty": -1.0,
+  "soft_max_length": null,
+  "soft_cache_length": null,
+  "dynamic_sample": false,
+  "max_resample_times": 3,
+  "overlong_filter": false,
+  "scale_rewards": "group",
+  "advantage_estimator": "grpo",
+  "kl_in_reward": false,
+  "wandb_log_unique_prompts": null,
+  "log_completions": false,
+  "rollout_importance_sampling_mode": null,
+  "rollout_importance_sampling_threshold": 2.0,
+  "log_rollout_offpolicy_metrics": false,
+  "off_policy_sequence_mask_delta": null,
+  "log_entropy": false,
+  "top_entropy_quantile": 1.0,
+  "reward_model": null,
+  "reward_model_plugin": null,
+  "sync_ref_model": false,
+  "ref_model_sync_steps": 512,
+  "ref_model_mixup_alpha": 0.6,
+  "async_generate": false,
+  "move_model_batches": null,
+  "multi_turn_scheduler": null,
+  "max_turns": null,
+  "completion_length_limit_scope": "per_round",
+  "vllm_server_pass_dataset": false,
+  "num_iterations": 1,
+  "micro_batch_size": 1,
+  "global_batch_size": 64,
+  "recompute_granularity": "full",
+  "recompute_method": "uniform",
+  "recompute_num_layers": 1,
+  "recompute_modules": [
+    "core_attn"
+  ],
+  "train_iters": null,
+  "num_train_epochs": 5,
+  "masked_softmax_fusion": true,
+  "bias_dropout_fusion": true,
+  "bias_activation_fusion": true,
+  "apply_rope_fusion": false,
+  "gradient_accumulation_fusion": false,
+  "cross_entropy_loss_fusion": true,
+  "cross_entropy_fusion_impl": "native",
+  "calculate_per_token_loss": true,
+  "attention_backend": "<AttnBackend.flash: 1>",
+  "optimizer": "adam",
+  "optimizer_cpu_offload": false,
+  "optimizer_offload_fraction": 1.0,
+  "use_precision_aware_optimizer": false,
+  "main_grads_dtype": "float32",
+  "main_params_dtype": "float32",
+  "exp_avg_dtype": "float32",
+  "exp_avg_sq_dtype": "float32",
+  "manual_gc": false,
+  "manual_gc_steps": 0,
+  "manual_gc_eval": true,
+  "train_dataloader_shuffle": true,
+  "dataloader_num_workers": 4,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": true,
+  "dataloader_prefetch_factor": 2,
+  "data_sharding": false,
+  "group_by_length": false,
+  "te_rng_tracker": false,
+  "data_parallel_random_init": false,
+  "mlp_padding_free": false,
+  "lr_warmup_init": 0.0,
+  "lr": 0.0001,
+  "lr_decay_style": "cosine",
+  "lr_decay_iters": null,
+  "lr_warmup_iters": 0,
+  "lr_warmup_fraction": 0.1,
+  "min_lr": 1e-06,
+  "lr_wsd_decay_style": "exponential",
+  "lr_wsd_decay_iters": null,
+  "weight_decay": 0.1,
+  "weight_decay_incr_style": "constant",
+  "start_weight_decay": 0.1,
+  "end_weight_decay": 0.1,
+  "clip_grad": 1.0,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_eps": 1e-08,
+  "sgd_momentum": 0.9,
+  "output_dir": "/mnt/data/share-oss/user/shaomingchen/ckpt/long-audio/time-aware/exp12/v1-20260309-155539",
+  "save_steps": 800,
+  "no_save_optim": true,
+  "no_save_rng": true,
+  "mcore_model": null,
+  "mcore_adapter": null,
+  "no_load_optim": false,
+  "no_load_rng": false,
+  "finetune": true,
+  "perform_initialization": false,
+  "use_cpu_initialization": false,
+  "async_save": false,
+  "save_total_limit": null,
+  "metric_for_best_model": "loss",
+  "greater_is_better": false,
+  "use_persistent_ckpt_worker": false,
+  "dist_ckpt_save_pre_mcore_014": false,
+  "dist_ckpt_optim_fully_reshardable": false,
+  "distrib_optim_fully_reshardable_mem_efficient": false,
+  "local_rank": 0,
+  "use_distributed_optimizer": true,
+  "tensor_model_parallel_size": 2,
+  "pipeline_model_parallel_size": 1,
+  "decoder_first_pipeline_num_layers": null,
+  "decoder_last_pipeline_num_layers": null,
+  "account_for_embedding_in_pipeline_split": false,
+  "account_for_loss_in_pipeline_split": false,
+  "overlap_p2p_comm": false,
+  "align_param_gather": false,
+  "sequence_parallel": true,
+  "context_parallel_size": 1,
+  "tp_comm_overlap": false,
+  "overlap_grad_reduce": false,
+  "overlap_param_gather": false,
+  "overlap_param_gather_with_optimizer_step": false,
+  "align_grad_reduce": true,
+  "virtual_pipeline_model_parallel_size": null,
+  "microbatch_group_size_per_vp_stage": null,
+  "pipeline_model_parallel_layout": null,
+  "expert_model_parallel_size": 4,
+  "expert_tensor_parallel_size": 1,
+  "report_to": [
+    "tensorboard"
+  ],
+  "logging_steps": 5,
+  "tensorboard_dir": "/mnt/data/share-oss/user/shaomingchen/ckpt/long-audio/time-aware/exp12/v1-20260309-155539/runs",
+  "tensorboard_queue_size": 50,
+  "wandb_project": "megatron-swift",
+  "wandb_exp_name": null,
+  "swanlab_project": "megatron-swift",
+  "swanlab_exp_name": null,
+  "eval_iters": -1,
+  "eval_steps": 800,
+  "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,
+  "accumulate_allreduce_grads_in_fp32": true,
+  "moe_router_load_balancing_type": null,
+  "moe_router_dtype": "fp32",
+  "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,
+  "mtp_num_layers": null,
+  "mtp_loss_scaling_factor": 0.1,
+  "save_safetensors": true,
+  "ref_model": null,
+  "ref_adapters": [],
+  "merge_lora": true,
+  "max_shard_size": "5GB",
+  "vit_gradient_checkpointing": true,
+  "vit_lr": null,
+  "aligner_lr": null,
+  "gradient_checkpointing_kwargs": null,
+  "check_model": true,
+  "apply_wd_to_qk_layernorm": false,
+  "enable_dft_loss": false,
+  "enable_channel_loss": false,
+  "save_strategy": "steps",
+  "callbacks": [
+    "print",
+    "default_flow",
+    "tensorboard"
+  ],
+  "add_version": true,
+  "create_checkpoint_symlink": false,
+  "swift_version": "4.0.0.dev0",
+  "ckpt_dir": null,
+  "rank": 0,
+  "global_world_size": 64,
+  "local_world_size": 8,
+  "model_suffix": "Qwen3-Omni-30B-A3B-Instruct",
+  "model_info": "ModelInfo(model_type='qwen3_omni_moe', model_dir='/mnt/data/share-ssd/user/shaomingchen/code/long-audio/time-aware/ft_omni/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, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",
+  "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='qwen3_omni', 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=[])",
+  "model_dir": "/mnt/data/share-ssd/user/shaomingchen/code/long-audio/time-aware/ft_omni/Qwen3-Omni-30B-A3B-Instruct",
+  "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='')",
+  "_val_dataset_exists": true,
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "seq_length": 32768,
+  "is_multimodal": true,
+  "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'>)",
+  "fp8": null,
+  "params_dtype": "bfloat16",
+  "world_size": 64,
+  "data_parallel_size": 32,
+  "num_microbatches": 2
+}

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 +1,552 @@
+{
+  "architectures": [
+    "Qwen3OmniMoeForConditionalGeneration"
+  ],
+  "assistant_token_id": 77091,
+  "code2wav_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "codebook_dim": 512,
+    "codebook_size": 2048,
+    "decoder_dim": 1536,
+    "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,
+    "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"
+  ],
+  "model_type": "qwen3_omni_moe",
+  "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": null,
+      "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,
+    "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": null,
+      "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_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": null,
+      "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",
+    "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": null,
+      "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": null,
+      "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": "4.57.6",
+  "tts_bos_token_id": 151672,
+  "tts_eos_token_id": 151673,
+  "tts_pad_token_id": 151671,
+  "user_token_id": 872
+}

iter_0003200/common.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df1d0b8cd550f46d68fbf3414071ed06fd1cd951b626daa70abf35e01766db46
+size 16039

iter_0003200/metadata.json

@@ -0,0 +1 @@
+{"sharded_backend": "torch_dist", "sharded_backend_version": 1, "common_backend": "torch", "common_backend_version": 1}

latest_checkpointed_iteration.txt

@@ -0,0 +1 @@
+3200

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e607798d2c21d58d1d968d5e920de2bc997b7dfe7558a09733dc650ceae11ab
+size 4999746336

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:829fbbf28f51793ede999630d76ef2d60edf8bb1716b587b23bc5d50ef4040b0
+size 4995907928

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5daf9778761134170be4cde1c1ee2e955d980aadc519f42194ad65cab9f00a07
+size 4998681018

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:133ec1d0743675a22f2d437cd368bc1ee886b9f53feb4d5c1924d1c01b8e3520
+size 4997754200

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dad1ea5c68c5cbcc8648b408a8d63749f17257014ab0cd64397964b8649a592d
+size 4997754968

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf66afa0b43f288ed7b050e6b68315a118bd6f56a8c4512e25e4fc79095ba81d
+size 4997755776

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03bf839882c8f278842498168af306cb1aa6e22aa97913fcd81fdb40def15482
+size 4997755776

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3dc7c667fb370bb6f2fe173c5c9c6e845b487bb8fd97b3363a6f53045ef672d
+size 4997755776

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbd06333c354fc81eba29a8bb0eb82b0d23a7bc672b78de887736e1309cecdeb
+size 4991468272

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7af4d7bf56c182ff28ed5524894c472b593d95ad9b1076d3733bd4d5d0793d9e
+size 4985172320

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a45560d21dbc2aace7047adfc30613b4fe2ad9f3d5e3ea4c2c9df4a58e0dd970
+size 4985172320

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee7b239f98d116ff502625a302d5ffd2831aa4e0ace302899cfcca5c83d92ebf
+size 4985172320

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:978858df53731101983fe50e3a680ce5290deb33eb38b293ba3926bf6e033dcd
+size 4985172320

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0809717adfbb454dd09cfc2b2aa42b8aab10346f5cb236bf45a7f79732b4a9af
+size 4985172320

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b188de7181f90642817ecad720866be606f14def3bf4c7051e0d2c162f9d8235
+size 622858440

preprocessor_config.json

@@ -0,0 +1,31 @@
+{
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "chunk_length": 1800,
+  "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 +1,55 @@
+{
+  "chunk_length": 1800,
+  "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"
+}