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 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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 +1,461 @@
+{
+  "model": "/jizhicfs/ygc/hf_cache/models--Qwen--Qwen3-30B-A3B-Thinking-2507/snapshots/144afc2f379b542fdd4e85a1fcd5e1f79112d95d",
+  "model_type": "qwen3_moe_thinking",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_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_thinking",
+  "system": null,
+  "max_length": 131072,
+  "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": 2,
+  "response_prefix": null,
+  "template_backend": "swift",
+  "dataset": [
+    "/jizhicfs/ygc/agentmerge/megatron_multinode/shared/jialongwu/model_merge/web_doc_rag_13500.jsonl"
+  ],
+  "val_dataset": [],
+  "split_dataset_ratio": 0.0,
+  "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": "/jizhicfs/ygc/mcore/Qwen3-30B-A3B-Think-mcore",
+  "lora_modules": [],
+  "tuner_backend": "peft",
+  "train_type": "full",
+  "adapters": [],
+  "external_plugins": [],
+  "seed": 42,
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": true,
+  "packing_length": 131072,
+  "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": 151936,
+  "initialize_embedding": false,
+  "mlp_padding_free": false,
+  "dataloader_persistent_workers": true,
+  "dataloader_prefetch_factor": 10,
+  "architectures": "Qwen3MoeForCausalLM",
+  "llm_architectures": null,
+  "max_epochs": 10,
+  "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": true,
+  "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": false,
+  "micro_batch_size": 1,
+  "global_batch_size": 16,
+  "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": 5,
+  "tensorboard_dir": "/jizhicfs/ygc/agentmerge/megatron_multinode/output/Qwen3-30B-A3B-Think/web_doc_rag_13500/v0-20260108-201506/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": true,
+  "optimizer_offload_fraction": 1.0,
+  "use_precision_aware_optimizer": true,
+  "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": 1e-05,
+  "lr_decay_style": "cosine",
+  "lr_decay_iters": null,
+  "lr_warmup_iters": 0,
+  "lr_warmup_fraction": 0.05,
+  "min_lr": 1e-06,
+  "weight_decay": 0.1,
+  "clip_grad": 1.0,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_eps": 1e-08,
+  "sgd_momentum": 0.9,
+  "save": "/jizhicfs/ygc/agentmerge/megatron_multinode/output/Qwen3-30B-A3B-Think/web_doc_rag_13500/v0-20260108-201506",
+  "save_interval": 168,
+  "save_retain_interval": null,
+  "no_save_optim": true,
+  "no_save_rng": true,
+  "load": "/jizhicfs/ygc/mcore/Qwen3-30B-A3B-Think-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,
+  "async_save": false,
+  "use_persistent_ckpt_worker": false,
+  "ckpt_fully_parallel_load": false,
+  "ckpt_assume_constant_structure": false,
+  "distributed_backend": "nccl",
+  "local_rank": 0,
+  "use_distributed_optimizer": true,
+  "tensor_model_parallel_size": 4,
+  "pipeline_model_parallel_size": 5,
+  "decoder_first_pipeline_num_layers": 8,
+  "decoder_last_pipeline_num_layers": null,
+  "sequence_parallel": true,
+  "context_parallel_size": 2,
+  "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": 262144,
+  "position_embedding_type": "rope",
+  "mrope_section": null,
+  "rotary_base": 10000000,
+  "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": 8,
+  "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": null,
+  "wandb_exp_name": null,
+  "wandb_save_dir": null,
+  "eval_iters": -1,
+  "eval_interval": 168,
+  "seq_length": 131072,
+  "num_workers": 8,
+  "extra_megatron_kwargs": {},
+  "add_version": true,
+  "rank": 0,
+  "global_world_size": 40,
+  "local_world_size": 8,
+  "model_suffix": "Qwen3-30B-A3B-Thinking-2507",
+  "model_info": "ModelInfo(model_type='qwen3_moe_thinking', model_dir='/jizhicfs/ygc/hf_cache/models--Qwen--Qwen3-30B-A3B-Thinking-2507/snapshots/144afc2f379b542fdd4e85a1fcd5e1f79112d95d', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=True, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='qwen3_moe_thinking', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-30B-A3B-Thinking-2507', hf_model_id='Qwen/Qwen3-30B-A3B-Thinking-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-30B-A3B-Thinking-2507-FP8', hf_model_id='Qwen/Qwen3-30B-A3B-Thinking-2507-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Thinking-2507', hf_model_id='Qwen/Qwen3-235B-A22B-Thinking-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Thinking-2507-FP8', hf_model_id='Qwen/Qwen3-235B-A22B-Thinking-2507-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Qwen3-235B-A22B-Thinking-2507-AWQ', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_thinking', get_function=<function get_model_tokenizer_with_flash_attn at 0x7f3b07c9f490>, model_arch=None, architectures=['Qwen3MoeForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.51'], tags=[])",
+  "model_dir": "/jizhicfs/ygc/hf_cache/models--Qwen--Qwen3-30B-A3B-Thinking-2507/snapshots/144afc2f379b542fdd4e85a1fcd5e1f79112d95d",
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "megatron_model_meta": "MegatronModelMeta(megatron_model_type='gpt', model_types=['qwen2', 'qwen2_5', 'qwq', 'qwq_preview', 'qwen2_5_math', 'llama', 'llama3', 'llama3_1', 'llama3_2', 'longwriter_llama3_1', 'codefuse_codellama', 'marco_o1', 'deepseek', 'deepseek_r1_distill', 'yi', 'yi_coder', 'sus', 'skywork_o1', 'openbuddy_llama', 'openbuddy_llama3', 'megrez', 'reflection', 'numina', 'ziya', 'mengzi3', 'qwen3', 'qwen3_thinking', 'qwen3_nothinking', 'qwen2_moe', 'qwen3_moe', 'qwen3_moe_thinking', 'qwen3_coder', 'internlm3', 'mimo', 'mimo_rl', 'moonlight', 'deepseek_moe', 'deepseek_v2', 'deepseek_v2_5', 'deepseek_r1', 'dots1', 'ernie', 'glm4_5', 'deepseek_v3_1', 'ernie_thinking'], convert_mcore2hf=<function convert_mcore2hf at 0x7f3a741fc9d0>, convert_hf2mcore=<function convert_hf2mcore at 0x7f3a741fc550>, model_cls=<class 'swift.megatron.model.gpt_model.GPTModel'>, convert_hf_config=<function convert_gpt_hf_config at 0x7f3a741e4790>, get_transformer_layer_spec=None, model_provider=<function model_provider at 0x7f3a741b7490>, visual_cls=None, extra_args_provider=None)",
+  "extra_args": {
+    "model": "/jizhicfs/ygc/hf_cache/models--Qwen--Qwen3-30B-A3B-Thinking-2507/snapshots/144afc2f379b542fdd4e85a1fcd5e1f79112d95d",
+    "model_type": "qwen3_moe_thinking",
+    "model_revision": null,
+    "task_type": "causal_lm",
+    "torch_dtype": "bfloat16",
+    "attn_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_thinking",
+    "system": null,
+    "max_length": 131072,
+    "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": 2,
+    "response_prefix": null,
+    "template_backend": "swift",
+    "dataset": [
+      "/jizhicfs/ygc/agentmerge/megatron_multinode/shared/jialongwu/model_merge/web_doc_rag_13500.jsonl"
+    ],
+    "val_dataset": [],
+    "split_dataset_ratio": 0.0,
+    "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": "/jizhicfs/ygc/mcore/Qwen3-30B-A3B-Think-mcore",
+    "lora_modules": [],
+    "tuner_backend": "peft",
+    "train_type": "full",
+    "adapters": [],
+    "external_plugins": [],
+    "model_kwargs": {},
+    "load_args": false,
+    "load_data_args": false,
+    "packing": true,
+    "packing_length": 131072,
+    "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": 151936,
+    "initialize_embedding": false,
+    "mlp_padding_free": false,
+    "dataloader_persistent_workers": true,
+    "dataloader_prefetch_factor": 10,
+    "architectures": "Qwen3MoeForCausalLM",
+    "llm_architectures": null,
+    "max_epochs": 10,
+    "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": true,
+    "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": false,
+    "add_version": true,
+    "model_info": "ModelInfo(model_type='qwen3_moe_thinking', model_dir='/jizhicfs/ygc/hf_cache/models--Qwen--Qwen3-30B-A3B-Thinking-2507/snapshots/144afc2f379b542fdd4e85a1fcd5e1f79112d95d', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=True, config=None, task_type='causal_lm', num_labels=None)",
+    "model_meta": "ModelMeta(model_type='qwen3_moe_thinking', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-30B-A3B-Thinking-2507', hf_model_id='Qwen/Qwen3-30B-A3B-Thinking-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-30B-A3B-Thinking-2507-FP8', hf_model_id='Qwen/Qwen3-30B-A3B-Thinking-2507-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Thinking-2507', hf_model_id='Qwen/Qwen3-235B-A22B-Thinking-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Thinking-2507-FP8', hf_model_id='Qwen/Qwen3-235B-A22B-Thinking-2507-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Qwen3-235B-A22B-Thinking-2507-AWQ', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_thinking', get_function=<function get_model_tokenizer_with_flash_attn at 0x7f3b07c9f490>, model_arch=None, architectures=['Qwen3MoeForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.51'], tags=[])",
+    "megatron_model_meta": "MegatronModelMeta(megatron_model_type='gpt', model_types=['qwen2', 'qwen2_5', 'qwq', 'qwq_preview', 'qwen2_5_math', 'llama', 'llama3', 'llama3_1', 'llama3_2', 'longwriter_llama3_1', 'codefuse_codellama', 'marco_o1', 'deepseek', 'deepseek_r1_distill', 'yi', 'yi_coder', 'sus', 'skywork_o1', 'openbuddy_llama', 'openbuddy_llama3', 'megrez', 'reflection', 'numina', 'ziya', 'mengzi3', 'qwen3', 'qwen3_thinking', 'qwen3_nothinking', 'qwen2_moe', 'qwen3_moe', 'qwen3_moe_thinking', 'qwen3_coder', 'internlm3', 'mimo', 'mimo_rl', 'moonlight', 'deepseek_moe', 'deepseek_v2', 'deepseek_v2_5', 'deepseek_r1', 'dots1', 'ernie', 'glm4_5', 'deepseek_v3_1', 'ernie_thinking'], convert_mcore2hf=<function convert_mcore2hf at 0x7f3a741fc9d0>, convert_hf2mcore=<function convert_hf2mcore at 0x7f3a741fc550>, model_cls=<class 'swift.megatron.model.gpt_model.GPTModel'>, convert_hf_config=<function convert_gpt_hf_config at 0x7f3a741e4790>, get_transformer_layer_spec=None, model_provider=<function model_provider at 0x7f3a741b7490>, visual_cls=None, extra_args_provider=None)"
+  }
+}

chat_template.jinja

@@ -0,0 +1,86 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- 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 = '' %}
+    {%- 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<think>\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 262144,
+  "max_window_layers": 48,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000000,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d840e267d393656c0c1eaa2c2a0f31536cf4f78b85fcaa067204328a57e330d3
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ff2655b398b382bb69f6223ebf8281fec0c6d383e82ad8a1f8f928475a6004
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf4fa81bcbb14a295e1ec76fc3ee13ae5c1dd4745f12bfced784d02896dfb651
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc84fe591b93d36f1665b34c3e7249d1ba2fb3ef0f1a3fa5b69bbb95d66497a
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7aa6a00842406991b4548c52c493ba277dcc14237951d9cefd741be8ef6ba1d
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dab1ca818cba164bc68d09199201c8954f29fcc2f5e57b26661ae4113355f2c6
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed774080f1c4cf3125240670bf6871a46f9d20b1387cd9b28f4bc8fd949c3052
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3df1723978955aa469b28f45400413b5795364eb02d2028f77a85253c7b00d49
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dce46fb632f0a918ef24ce084c44e41fef13227dce0b221ee513b48222074dc1
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c7e9347da15e6611b6550212ba7402f0a7e329ae35ee5d7e14e04a906b3845c
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c3b3d648058e38058e2da5b19a973bd738d2f0afea722c98913a9949ff22fb4
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e24701516f4740a4eeecd83e837c937e502d24e561ebf4cd075f18a52054138
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cea82b3076d40175308856ac378958ecdbef36d344e75a0872519f08f444d148
+size 1094220288

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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
+    }
+  },
+  "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|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1010000,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}