Upload folder using huggingface_hub

args.json

@@ -0,0 +1,370 @@
+{
+  "output_dir": "/data/leizikun/msp/script/occupy/output/minicpm5-1b-fullft-neko",
+  "per_device_train_batch_size": 4,
+  "num_train_epochs": 5.0,
+  "max_steps": -1,
+  "learning_rate": 2e-05,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": null,
+  "warmup_steps": 0,
+  "optim": "adamw_torch_fused",
+  "optim_args": null,
+  "weight_decay": 0.01,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "optim_target_modules": null,
+  "gradient_accumulation_steps": 4,
+  "average_tokens_across_devices": true,
+  "max_grad_norm": 1.0,
+  "label_smoothing_factor": 0.0,
+  "bf16": true,
+  "fp16": false,
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": null,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "use_liger_kernel": false,
+  "liger_kernel_config": null,
+  "use_cache": false,
+  "neftune_noise_alpha": null,
+  "torch_empty_cache_steps": null,
+  "auto_find_batch_size": false,
+  "logging_strategy": "steps",
+  "logging_steps": 10,
+  "logging_first_step": true,
+  "log_on_each_node": true,
+  "logging_nan_inf_filter": true,
+  "include_num_input_tokens_seen": false,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "disable_tqdm": null,
+  "report_to": [
+    "wandb"
+  ],
+  "run_name": "minicpm5-1b-fullft-2a800-z2-bs4-ga4-4096",
+  "project": "huggingface",
+  "trackio_space_id": null,
+  "trackio_bucket_id": null,
+  "trackio_static_space_id": null,
+  "eval_strategy": "no",
+  "eval_steps": null,
+  "eval_delay": 0,
+  "per_device_eval_batch_size": 4,
+  "prediction_loss_only": false,
+  "eval_on_start": false,
+  "eval_do_concat_batches": true,
+  "eval_use_gather_object": false,
+  "eval_accumulation_steps": null,
+  "include_for_metrics": [],
+  "batch_eval_metrics": false,
+  "save_only_model": true,
+  "save_strategy": "epoch",
+  "save_steps": 500,
+  "save_on_each_node": false,
+  "save_total_limit": 3,
+  "enable_jit_checkpoint": false,
+  "push_to_hub": false,
+  "hub_token": null,
+  "hub_private_repo": null,
+  "hub_model_id": null,
+  "hub_strategy": "every_save",
+  "hub_always_push": false,
+  "hub_revision": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": "loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "restore_callback_states_from_checkpoint": false,
+  "full_determinism": false,
+  "seed": 42,
+  "data_seed": 42,
+  "use_cpu": false,
+  "accelerator_config": {
+    "dispatch_batches": false
+  },
+  "parallelism_config": null,
+  "dataloader_drop_last": false,
+  "dataloader_num_workers": 4,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": false,
+  "dataloader_prefetch_factor": null,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "train_sampling_strategy": "random",
+  "length_column_name": "length",
+  "ddp_find_unused_parameters": false,
+  "ddp_bucket_cap_mb": null,
+  "ddp_broadcast_buffers": null,
+  "ddp_static_graph": null,
+  "ddp_backend": "nccl",
+  "ddp_timeout": 18000000,
+  "fsdp": [],
+  "fsdp_config": null,
+  "deepspeed": {
+    "bf16": {
+      "enabled": "auto"
+    },
+    "zero_optimization": {
+      "stage": 2,
+      "offload_optimizer": {
+        "device": "none",
+        "pin_memory": true
+      },
+      "allgather_partitions": true,
+      "allgather_bucket_size": 500000000.0,
+      "overlap_comm": true,
+      "reduce_scatter": true,
+      "reduce_bucket_size": 500000000.0,
+      "contiguous_gradients": true
+    },
+    "gradient_accumulation_steps": "auto",
+    "gradient_clipping": "auto",
+    "train_batch_size": "auto",
+    "train_micro_batch_size_per_gpu": "auto",
+    "wall_clock_breakdown": false
+  },
+  "debug": null,
+  "skip_memory_metrics": true,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "resume_from_checkpoint": null,
+  "warmup_ratio": 0.03,
+  "logging_dir": "/data/leizikun/msp/script/occupy/output/minicpm5-1b-fullft-neko/runs",
+  "local_rank": 0,
+  "sortish_sampler": false,
+  "predict_with_generate": false,
+  "generation_max_length": null,
+  "generation_num_beams": null,
+  "generation_config": null,
+  "tuner_backend": "peft",
+  "vit_gradient_checkpointing": false,
+  "router_aux_loss_coef": 0.0,
+  "enable_dft_loss": false,
+  "enable_channel_loss": false,
+  "safe_serialization": true,
+  "max_shard_size": "5GB",
+  "check_model": true,
+  "acc_strategy": "token",
+  "train_dataloader_shuffle": true,
+  "group_by_length": false,
+  "max_epochs": null,
+  "aligner_lr": null,
+  "vit_lr": null,
+  "use_logits_to_keep": null,
+  "ds3_gather_for_generation": true,
+  "resume_only_model": false,
+  "optimizer": null,
+  "loss_type": null,
+  "eval_metric": null,
+  "callbacks": [],
+  "early_stop_interval": null,
+  "eval_use_evalscope": false,
+  "eval_dataset": [],
+  "eval_dataset_args": null,
+  "eval_limit": null,
+  "eval_generation_config": null,
+  "extra_eval_args": null,
+  "tuner_type": "full",
+  "use_galore": false,
+  "galore_target_modules": null,
+  "galore_rank": 128,
+  "galore_update_proj_gap": 50,
+  "galore_scale": 1.0,
+  "galore_proj_type": "std",
+  "galore_optim_per_parameter": false,
+  "galore_with_embedding": false,
+  "galore_quantization": false,
+  "galore_proj_quant": false,
+  "galore_proj_bits": 4,
+  "galore_proj_group_size": 256,
+  "galore_cos_threshold": 0.4,
+  "galore_gamma_proj": 2,
+  "galore_queue_size": 5,
+  "lisa_activated_layers": 0,
+  "lisa_step_interval": 20,
+  "use_flash_ckpt": false,
+  "use_ray": false,
+  "ray_exp_name": null,
+  "device_groups": null,
+  "model": "/data/leizikun/msp/model/MiniCPM5-1B",
+  "model_type": "llama",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_impl": "sdpa",
+  "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": "minicpm5",
+  "system": null,
+  "max_length": 4096,
+  "truncation_strategy": "delete",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "use_chat_template": true,
+  "padding_side": "right",
+  "padding_free": false,
+  "loss_scale": "default",
+  "sequence_parallel_size": 1,
+  "is_binary_loss_scale": null,
+  "template_backend": "swift",
+  "response_prefix": null,
+  "enable_thinking": null,
+  "preserve_thinking": null,
+  "add_non_thinking_prefix": true,
+  "dataset": [
+    "/data/leizikun/msp/script/occupy/data/train_neko.jsonl"
+  ],
+  "val_dataset": [],
+  "cached_dataset": [],
+  "cached_val_dataset": [],
+  "split_dataset_ratio": 0.0,
+  "dataset_num_proc": 1,
+  "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,
+  "disable_auto_column_mapping": false,
+  "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": 64,
+  "temperature": 0.0,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
+  "num_beams": 1,
+  "stream": false,
+  "stop_words": [],
+  "logprobs": false,
+  "top_logprobs": null,
+  "structured_outputs_regex": null,
+  "adapters": [],
+  "external_plugins": [],
+  "custom_register_path": [],
+  "model_kwargs": {},
+  "enable_npu_model_patch": true,
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_length": null,
+  "packing_num_proc": 1,
+  "lazy_tokenize": false,
+  "use_hf": false,
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "freeze_parameters": [],
+  "freeze_parameters_regex": null,
+  "freeze_parameters_ratio": 0.0,
+  "trainable_parameters": [],
+  "trainable_parameters_regex": null,
+  "freeze_llm": false,
+  "freeze_vit": true,
+  "freeze_aligner": true,
+  "target_modules": [
+    "all-linear"
+  ],
+  "target_regex": null,
+  "target_parameters": null,
+  "modules_to_save": [],
+  "lora_rank": 8,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "lora_bias": "none",
+  "lora_dtype": null,
+  "lorap_lr_ratio": null,
+  "use_rslora": false,
+  "use_dora": false,
+  "lora_ga_batch_size": 2,
+  "lora_ga_iters": 2,
+  "lora_ga_max_length": 1024,
+  "lora_ga_direction": "ArB2r",
+  "lora_ga_scale": "stable",
+  "lora_ga_stable_gamma": 16,
+  "init_weights": true,
+  "fourier_n_frequency": 2000,
+  "fourier_scaling": 300.0,
+  "boft_block_size": 4,
+  "boft_block_num": 0,
+  "boft_n_butterfly_factor": 1,
+  "boft_dropout": 0.0,
+  "vera_rank": 256,
+  "vera_projection_prng_key": 0,
+  "vera_dropout": 0.0,
+  "vera_d_initial": 0.1,
+  "adapter_act": "gelu",
+  "adapter_length": 128,
+  "adalora_target_r": 8,
+  "adalora_init_r": 12,
+  "adalora_tinit": 0,
+  "adalora_tfinal": 0,
+  "adalora_deltaT": 1,
+  "adalora_beta1": 0.85,
+  "adalora_beta2": 0.85,
+  "adalora_orth_reg_weight": 0.5,
+  "llamapro_num_new_blocks": 4,
+  "llamapro_num_groups": null,
+  "reft_layer_key": null,
+  "reft_layers": null,
+  "reft_rank": 4,
+  "reft_intervention_type": "LoreftIntervention",
+  "reft_args": null,
+  "swanlab_token": null,
+  "swanlab_project": "ms-swift",
+  "swanlab_workspace": null,
+  "swanlab_exp_name": null,
+  "swanlab_notification_method": null,
+  "swanlab_webhook_url": null,
+  "swanlab_secret": null,
+  "swanlab_sender_email": null,
+  "swanlab_receiver_email": null,
+  "swanlab_smtp_server": null,
+  "swanlab_smtp_port": null,
+  "swanlab_email_language": "zh",
+  "swanlab_mode": "cloud",
+  "add_version": false,
+  "create_checkpoint_symlink": false,
+  "zero_hpz_partition_size": null,
+  "deepspeed_autotp_size": null,
+  "swift_version": "4.3.0",
+  "ckpt_dir": null,
+  "rank": 0,
+  "global_world_size": 2,
+  "local_world_size": 2,
+  "model_suffix": "MiniCPM5-1B",
+  "model_info": "ModelInfo(model_type='llama', model_dir='/data/leizikun/msp/model/MiniCPM5-1B', torch_dtype=torch.bfloat16, max_model_len=131072, quant_method=None, quant_bits=None, rope_scaling={'rope_theta': 5000000, 'rope_type': 'default'}, is_moe_model=False, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='llama', model_groups=[ModelGroup(models=[Model(ms_model_id='modelscope/Llama-2-7b-ms', hf_model_id='meta-llama/Llama-2-7b-hf', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='modelscope/Llama-2-13b-ms', hf_model_id='meta-llama/Llama-2-13b-hf', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='modelscope/Llama-2-70b-ms', hf_model_id='meta-llama/Llama-2-70b-hf', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='modelscope/Llama-2-7b-chat-ms', hf_model_id='meta-llama/Llama-2-7b-chat-hf', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='modelscope/Llama-2-13b-chat-ms', hf_model_id='meta-llama/Llama-2-13b-chat-hf', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='modelscope/Llama-2-70b-chat-ms', hf_model_id='meta-llama/Llama-2-70b-chat-hf', model_path=None, ms_revision=None, hf_revision=None)], template='llama', ignore_patterns=['.+\\\\.bin$'], requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='AI-ModelScope/chinese-llama-2-1.3b', hf_model_id='hfl/chinese-llama-2-1.3b', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/chinese-llama-2-7b', hf_model_id='hfl/chinese-llama-2-7b', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/chinese-llama-2-7b-16k', hf_model_id='hfl/chinese-llama-2-7b-16k', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/chinese-llama-2-7b-64k', hf_model_id='hfl/chinese-llama-2-7b-64k', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/chinese-llama-2-13b', hf_model_id='hfl/chinese-llama-2-13b', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/chinese-llama-2-13b-16k', hf_model_id='hfl/chinese-llama-2-13b-16k', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/chinese-alpaca-2-1.3b', hf_model_id='hfl/chinese-alpaca-2-1.3b', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/chinese-alpaca-2-7b', hf_model_id='hfl/chinese-alpaca-2-7b', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/chinese-alpaca-2-7b-16k', hf_model_id='hfl/chinese-alpaca-2-7b-16k', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/chinese-alpaca-2-7b-64k', hf_model_id='hfl/chinese-alpaca-2-7b-64k', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/chinese-alpaca-2-13b', hf_model_id='hfl/chinese-alpaca-2-13b', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='AI-ModelScope/chinese-alpaca-2-13b-16k', hf_model_id='hfl/chinese-alpaca-2-13b-16k', model_path=None, ms_revision=None, hf_revision=None)], template='llama', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='AI-ModelScope/Llama-2-7b-AQLM-2Bit-1x16-hf', hf_model_id='ISTA-DASLab/Llama-2-7b-AQLM-2Bit-1x16-hf', model_path=None, ms_revision=None, hf_revision=None)], template='llama', ignore_patterns=None, requires=['transformers>=4.38', 'aqlm', 'torch>=2.2.0'], tags=[]), ModelGroup(models=[Model(ms_model_id='FlagAlpha/Atom-7B', hf_model_id='FlagAlpha/Atom-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='FlagAlpha/Atom-7B-Chat', hf_model_id='FlagAlpha/Atom-7B-Chat', model_path=None, ms_revision=None, hf_revision=None)], template='atom', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='langboat/Mengzi3-13B-Base', hf_model_id='Langboat/Mengzi3-13B-Base', model_path=None, ms_revision=None, hf_revision=None)], template='mengzi', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='AI-ModelScope/NuminaMath-7B-TIR', hf_model_id='AI-MO/NuminaMath-7B-TIR', model_path=None, ms_revision=None, hf_revision=None)], template='numina', ignore_patterns=None, requires=None, tags=['math']), ModelGroup(models=[Model(ms_model_id='Fengshenbang/Ziya2-13B-Base', hf_model_id='IDEA-CCNL/Ziya2-13B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Fengshenbang/Ziya2-13B-Chat', hf_model_id='IDEA-CCNL/Ziya2-13B-Chat', model_path=None, ms_revision=None, hf_revision=None)], template='ziya', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='InfiniAI/Megrez-3b-Instruct', hf_model_id='Infinigence/Megrez-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], template='megrez', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='deepseek-ai/deepseek-llm-7b-base', hf_model_id='deepseek-ai/deepseek-llm-7b-base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/deepseek-llm-7b-chat', hf_model_id='deepseek-ai/deepseek-llm-7b-chat', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/deepseek-llm-67b-base', hf_model_id='deepseek-ai/deepseek-llm-67b-base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/deepseek-llm-67b-chat', hf_model_id='deepseek-ai/deepseek-llm-67b-chat', model_path=None, ms_revision=None, hf_revision=None)], template='deepseek', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='deepseek-ai/deepseek-math-7b-base', hf_model_id='deepseek-ai/deepseek-math-7b-base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/deepseek-math-7b-instruct', hf_model_id='deepseek-ai/deepseek-math-7b-instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/deepseek-math-7b-rl', hf_model_id='deepseek-ai/deepseek-math-7b-rl', model_path=None, ms_revision=None, hf_revision=None)], template='deepseek', ignore_patterns=None, requires=None, tags=['math']), ModelGroup(models=[Model(ms_model_id='deepseek-ai/deepseek-coder-1.3b-base', hf_model_id='deepseek-ai/deepseek-coder-1.3b-base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/deepseek-coder-1.3b-instruct', hf_model_id='deepseek-ai/deepseek-coder-1.3b-instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/deepseek-coder-6.7b-base', hf_model_id='deepseek-ai/deepseek-coder-6.7b-base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/deepseek-coder-6.7b-instruct', hf_model_id='deepseek-ai/deepseek-coder-6.7b-instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/deepseek-coder-33b-base', hf_model_id='deepseek-ai/deepseek-coder-33b-base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/deepseek-coder-33b-instruct', hf_model_id='deepseek-ai/deepseek-coder-33b-instruct', model_path=None, ms_revision=None, hf_revision=None)], template='deepseek', ignore_patterns=None, requires=None, tags=['coding']), ModelGroup(models=[Model(ms_model_id='gongjy/MiniMind2', hf_model_id='jingyaogong/MiniMind2', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id=None, hf_model_id='jingyaogong/MiniMind2-Small', model_path=None, ms_revision=None, hf_revision=None)], template='minimind', ignore_patterns=None, requires=['transformers>=4.57.1'], tags=[]), ModelGroup(models=[Model(ms_model_id='LLM-Research/Meta-Llama-3-8B-Instruct', hf_model_id='meta-llama/Meta-Llama-3-8B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Meta-Llama-3-70B-Instruct', hf_model_id='meta-llama/Meta-Llama-3-70B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Meta-Llama-3-8B', hf_model_id='meta-llama/Meta-Llama-3-8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Meta-Llama-3-70B', hf_model_id='meta-llama/Meta-Llama-3-70B', model_path=None, ms_revision=None, hf_revision=None)], template='llama3', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='swift/Meta-Llama-3-8B-Instruct-GPTQ-Int4', hf_model_id='study-hjt/Meta-Llama-3-8B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Meta-Llama-3-8B-Instruct-GPTQ-Int8', hf_model_id='study-hjt/Meta-Llama-3-8B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Meta-Llama-3-8B-Instruct-AWQ', hf_model_id='study-hjt/Meta-Llama-3-8B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Meta-Llama-3-70B-Instruct-GPTQ-Int4', hf_model_id='study-hjt/Meta-Llama-3-70B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Meta-Llama-3-70B-Instruct-GPTQ-Int8', hf_model_id='study-hjt/Meta-Llama-3-70B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Meta-Llama-3-70B-Instruct-AWQ', hf_model_id='study-hjt/Meta-Llama-3-70B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], template='llama3', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='ChineseAlpacaGroup/llama-3-chinese-8b-instruct', hf_model_id='hfl/llama-3-chinese-8b-instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ChineseAlpacaGroup/llama-3-chinese-8b', hf_model_id='hfl/llama-3-chinese-8b', model_path=None, ms_revision=None, hf_revision=None)], template='llama3', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='LLM-Research/Meta-Llama-3.1-8B-Instruct', hf_model_id='meta-llama/Meta-Llama-3.1-8B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Meta-Llama-3.1-70B-Instruct', hf_model_id='meta-llama/Meta-Llama-3.1-70B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Meta-Llama-3.1-405B-Instruct', hf_model_id='meta-llama/Meta-Llama-3.1-405B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Meta-Llama-3.1-8B', hf_model_id='meta-llama/Meta-Llama-3.1-8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Meta-Llama-3.1-70B', hf_model_id='meta-llama/Meta-Llama-3.1-70B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Meta-Llama-3.1-405B', hf_model_id='meta-llama/Meta-Llama-3.1-405B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Meta-Llama-3.1-70B-Instruct-FP8', hf_model_id='meta-llama/Meta-Llama-3.1-70B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Meta-Llama-3.1-405B-Instruct-FP8', hf_model_id='meta-llama/Meta-Llama-3.1-405B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='llama3_2', ignore_patterns=None, requires=['transformers>=4.43'], tags=[]), ModelGroup(models=[Model(ms_model_id='LLM-Research/Meta-Llama-3.1-8B-Instruct-BNB-NF4', hf_model_id='hugging-quants/Meta-Llama-3.1-8B-Instruct-BNB-NF4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Meta-Llama-3.1-70B-Instruct-bnb-4bit', hf_model_id='unsloth/Meta-Llama-3.1-70B-Instruct-bnb-4bit', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Meta-Llama-3.1-405B-Instruct-BNB-NF4', hf_model_id='hugging-quants/Meta-Llama-3.1-405B-Instruct-BNB-NF4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Meta-Llama-3.1-8B-Instruct-GPTQ-INT4', hf_model_id='hugging-quants/Meta-Llama-3.1-8B-Instruct-GPTQ-INT4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Meta-Llama-3.1-70B-Instruct-GPTQ-INT4', hf_model_id='hugging-quants/Meta-Llama-3.1-70B-Instruct-GPTQ-INT4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Meta-Llama-3.1-405B-Instruct-GPTQ-INT4', hf_model_id='hugging-quants/Meta-Llama-3.1-405B-Instruct-GPTQ-INT4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Meta-Llama-3.1-8B-Instruct-AWQ-INT4', hf_model_id='hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Meta-Llama-3.1-70B-Instruct-AWQ-INT4', hf_model_id='hugging-quants/Meta-Llama-3.1-70B-Instruct-AWQ-INT4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Meta-Llama-3.1-405B-Instruct-AWQ-INT4', hf_model_id='hugging-quants/Meta-Llama-3.1-405B-Instruct-AWQ-INT4', model_path=None, ms_revision=None, hf_revision=None)], template='llama3_2', ignore_patterns=None, requires=['transformers>=4.43'], tags=[]), ModelGroup(models=[Model(ms_model_id='AI-ModelScope/Llama-3.1-Nemotron-70B-Instruct-HF', hf_model_id='nvidia/Llama-3.1-Nemotron-70B-Instruct-HF', model_path=None, ms_revision=None, hf_revision=None)], template='llama3_2', ignore_patterns=None, requires=['transformers>=4.43'], tags=[]), ModelGroup(models=[Model(ms_model_id='AI-ModelScope/Skywork-o1-Open-Llama-3.1-8B', hf_model_id='Skywork/Skywork-o1-Open-Llama-3.1-8B', model_path=None, ms_revision=None, hf_revision=None)], template='skywork_o1', ignore_patterns=None, requires=['transformers>=4.43'], tags=[]), ModelGroup(models=[Model(ms_model_id='LLM-Research/Llama-3.2-1B', hf_model_id='meta-llama/Llama-3.2-1B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Llama-3.2-3B', hf_model_id='meta-llama/Llama-3.2-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Llama-3.2-1B-Instruct', hf_model_id='meta-llama/Llama-3.2-1B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/Llama-3.2-3B-Instruct', hf_model_id='meta-llama/Llama-3.2-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], template='llama3_2', ignore_patterns=None, requires=['transformers>=4.43'], tags=[]), ModelGroup(models=[Model(ms_model_id='LLM-Research/Llama-3.3-70B-Instruct', hf_model_id='meta-llama/Llama-3.3-70B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='unsloth/Llama-3.3-70B-Instruct-bnb-4bit', hf_model_id='unsloth/Llama-3.3-70B-Instruct-bnb-4bit', model_path=None, ms_revision=None, hf_revision=None)], template='llama3_2', ignore_patterns=None, requires=['transformers>=4.43'], tags=[]), ModelGroup(models=[Model(ms_model_id='ZhipuAI/LongWriter-llama3.1-8b', hf_model_id='zai-org/LongWriter-llama3.1-8b', model_path=None, ms_revision=None, hf_revision=None)], template='longwriter_llama', ignore_patterns=None, requires=['transformers>=4.43'], tags=[]), ModelGroup(models=[Model(ms_model_id='deepseek-ai/DeepSeek-R1-Distill-Llama-8B', hf_model_id='deepseek-ai/DeepSeek-R1-Distill-Llama-8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/DeepSeek-R1-Distill-Llama-70B', hf_model_id='deepseek-ai/DeepSeek-R1-Distill-Llama-70B', model_path=None, ms_revision=None, hf_revision=None)], template='deepseek_r1', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='OpenBMB/MiniCPM5-1B', hf_model_id='openbmb/MiniCPM5-1B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='OpenBMB/MiniCPM5-1B-Base', hf_model_id='openbmb/MiniCPM5-1B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='OpenBMB/MiniCPM5-1B-SFT', hf_model_id='openbmb/MiniCPM5-1B-SFT', model_path=None, ms_revision=None, hf_revision=None)], template='minicpm5', ignore_patterns=None, requires=['transformers>=5.6'], tags=[]), ModelGroup(models=[Model(ms_model_id='LLM-Research/Reflection-Llama-3.1-70B', hf_model_id='mattshumer/Reflection-Llama-3.1-70B', model_path=None, ms_revision=None, hf_revision=None)], template='reflection', ignore_patterns=None, requires=['transformers>=4.43'], tags=[])], loader=<class 'swift.model.models.llama.LlamaLoader'>, template='minicpm5', model_arch=ModelKeys(arch_name='llama', embedding='model.embed_tokens', module_list='model.layers', lm_head='lm_head', q_proj='model.layers.{}.self_attn.q_proj', k_proj='model.layers.{}.self_attn.k_proj', v_proj='model.layers.{}.self_attn.v_proj', o_proj='model.layers.{}.self_attn.o_proj', attention='model.layers.{}.self_attn', mlp='model.layers.{}.mlp', down_proj='model.layers.{}.mlp.down_proj', qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None), mcore_model_type=None, architectures=['LlamaForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=5.6'], tags=[])",
+  "model_dir": "/data/leizikun/msp/model/MiniCPM5-1B",
+  "template_meta": "ChatmlTemplateMeta(template_type='minicpm5', 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.base.Template'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system=None, auto_add_bos=True, stop_words=[], agent_template='minicpm5', is_thinking=True, thinking_prefix='<think>\\n', non_thinking_prefix='<think>\\n\\n</think>\\n\\n', history_thinking_prefix='')",
+  "_val_dataset_exists": false,
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "epoch",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/data/leizikun/msp/script/occupy/output/minicpm5-1b-fullft-neko', per_device_train_batch_size=4, num_train_epochs=5.0, max_steps=-1, learning_rate=2e-05, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_steps=0.03, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, weight_decay=0.01, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, optim_target_modules=None, gradient_accumulation_steps=4, average_tokens_across_devices=None, max_grad_norm=1.0, label_smoothing_factor=0.0, bf16=True, fp16=False, bf16_full_eval=False, fp16_full_eval=False, tf32=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, use_liger_kernel=False, liger_kernel_config=None, use_cache=False, neftune_noise_alpha=None, torch_empty_cache_steps=None, auto_find_batch_size=False, logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_steps=10, logging_first_step=True, log_on_each_node=True, logging_nan_inf_filter=True, include_num_input_tokens_seen=None, log_level='passive', log_level_replica='warning', disable_tqdm=False, report_to=['wandb'], run_name='minicpm5-1b-fullft-2a800-z2-bs4-ga4-4096', project='huggingface', trackio_space_id=None, trackio_bucket_id=None, trackio_static_space_id=None, eval_strategy=<IntervalStrategy.NO: 'no'>, eval_steps=None, eval_delay=0, per_device_eval_batch_size=4, prediction_loss_only=False, eval_on_start=False, eval_do_concat_batches=True, eval_use_gather_object=False, eval_accumulation_steps=None, include_for_metrics=[], batch_eval_metrics=False, save_only_model=True, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=500, save_on_each_node=False, save_total_limit=3, enable_jit_checkpoint=False, push_to_hub=False, hub_token=None, hub_private_repo=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_always_push=False, hub_revision=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, restore_callback_states_from_checkpoint=False, full_determinism=False, seed=42, data_seed=42, use_cpu=False, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, dataloader_drop_last=False, dataloader_num_workers=4, dataloader_pin_memory=True, dataloader_persistent_workers=False, dataloader_prefetch_factor=2, remove_unused_columns=False, label_names=None, train_sampling_strategy='random', length_column_name='length', ddp_find_unused_parameters=False, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, ddp_static_graph=None, ddp_backend='nccl', ddp_timeout=18000000, fsdp=[], fsdp_config=None, deepspeed={'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 2, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 500000000.0, 'overlap_comm': True, 'reduce_scatter': True, 'reduce_bucket_size': 500000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, debug=[], skip_memory_metrics=True, do_train=False, do_eval=False, do_predict=False, resume_from_checkpoint=None, warmup_ratio=0.03, logging_dir='/data/leizikun/msp/script/occupy/output/minicpm5-1b-fullft-neko/runs', local_rank=0, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=False, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, safe_serialization=True, max_shard_size='5GB', check_model=True, acc_strategy='token', train_dataloader_shuffle=True, group_by_length=False, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, eval_metric=None, callbacks=[], early_stop_interval=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, tuner_type='full', use_galore=False, galore_target_modules=None, galore_rank=128, galore_update_proj_gap=50, galore_scale=1.0, galore_proj_type='std', galore_optim_per_parameter=False, galore_with_embedding=False, galore_quantization=False, galore_proj_quant=False, galore_proj_bits=4, galore_proj_group_size=256, galore_cos_threshold=0.4, galore_gamma_proj=2, galore_queue_size=5, lisa_activated_layers=0, lisa_step_interval=20, use_flash_ckpt=False)"
+}

chat_template.jinja

@@ -0,0 +1,179 @@
+{{- bos_token }}{%- if tools %}
+    {%- set tool_definitions %}
+        {{- "# Tools\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+        {%- for tool in tools %}
+            {{- "\n" }}
+            {{- tool | tojson(ensure_ascii=False) }}
+        {%- endfor %}
+        {{- '\n</tools>\n\nTool usage guidelines:\n- You may call zero or more functions. If no function calls are needed, just answer normally and do not include any <function ... </function>.\n- When calling a function, return an XML object within <function ... </function> using:\n<function name="function-name"><param name="param-name">param-value</param></function>\n- param-value may be multi-line. If it contains <, & or newline characters, wrap it in a CDATA block: <param name="param-name"><![CDATA[...multi-line value...]]></param>' }}
+    {%- endset %}
+    
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if '<tool_def_sep>' in messages[0].content %}
+            {{- messages[0].content.replace('<tool_def_sep>', tool_definitions) }}
+        {%- else %}
+            {{- messages[0].content + '\n\n' + tool_definitions }}
+        {%- endif %}
+    {%- else %}
+        {{- tool_definitions.lstrip() }}
+    {%- endif %}
+    {{- '<|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 message.tool_calls %}
+            {%- set content_parts = content.split('<tool_sep>') %}
+            {%- set processed_content = content_parts[0] %}
+            {%- set tool_calls_count = message.tool_calls|length %}
+            {%- set tool_sep_count = content_parts|length - 1 %}
+            {%- set min_count = [tool_calls_count, tool_sep_count]|min %}
+            
+            {%- for i in range(1, content_parts|length) %}
+                {%- set tool_index = i - 1 %}
+                {%- if tool_index < tool_calls_count %}
+                    {%- set tool_call = message.tool_calls[tool_index] %}
+                    {%- if tool_call.function %}
+                        {%- set tool_call = tool_call.function %}
+                    {%- endif %}
+                    {%- set single_tool_xml %}
+                        {{- '<function name="' ~ tool_call.name ~ '">' }}
+                        {%- if tool_call.arguments %}
+                            {%- set args_dict = tool_call.arguments %}
+                            {%- for param_name, param_value in args_dict.items() %}
+                                {{- '<param name="' ~ param_name ~ '">' }}
+                                {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
+                                    {{- '<![CDATA[' + param_value + ']]>' }}
+                                {%- else %}
+                                    {{- param_value }}
+                                {%- endif %}
+                                {{- '</param>' }}
+                            {%- endfor %}
+                        {%- endif %}
+                        {{- '</function>' }}
+                    {%- endset %}
+                    {%- set processed_content = processed_content + single_tool_xml + content_parts[i] %}
+                {%- else %}
+                    {%- set processed_content = processed_content + content_parts[i] %}
+                {%- endif %}
+            {%- endfor %}
+            
+            {%- if tool_calls_count > tool_sep_count %}
+                {%- for remaining_index in range(tool_sep_count, tool_calls_count) %}
+                    {%- set tool_call = message.tool_calls[remaining_index] %}
+                    {%- if tool_call.function %}
+                        {%- set tool_call = tool_call.function %}
+                    {%- endif %}
+                    {%- set remaining_tool_xml %}
+                        {{- '<function name="' ~ tool_call.name ~ '">' }}
+                        {%- if tool_call.arguments %}
+                            {%- set args_dict = tool_call.arguments %}
+                            {%- for param_name, param_value in args_dict.items() %}
+                                {{- '<param name="' ~ param_name ~ '">' }}
+                                {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
+                                    {{- '<![CDATA[' + param_value + ']]>' }}
+                                {%- else %}
+                                    {{- param_value }}
+                                {%- endif %}
+                                {{- '</param>' }}
+                            {%- endfor %}
+                        {%- endif %}
+                        {{- '</function>' }}
+                    {%- endset %}
+                    {%- set processed_content = processed_content + remaining_tool_xml %}
+                {%- endfor %}
+            {%- endif %}
+            
+            {%- set content = processed_content %}
+        {%- endif %}
+        
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if 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 and not has_tool_sep %}
+            {%- 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 %}
+                {{- '<function name="' ~ tool_call.name ~ '">' }}
+                {%- if tool_call.arguments %}
+                    {%- set args_dict = tool_call.arguments %}
+                    {%- for param_name, param_value in args_dict.items() %}
+                        {{- '<param name="' ~ param_name ~ '">' }}
+                        {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
+                            {{- '<![CDATA[' + param_value + ']]>' }}
+                        {%- else %}
+                            {{- param_value }}
+                        {%- endif %}
+                        {{- '</param>' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>' }}
+            {%- 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' }}
+        {%- if message.content is string %}
+            {{- content }}
+        {%- else %}
+            {{- message.content | tojson(ensure_ascii=False) }}
+        {%- endif %}
+        {{- '\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 %}
+        {%- if enable_thinking is false %}
+            {{- '<think>\n\n</think>\n\n' }}
+        {%- elif enable_thinking is true %}
+            {{- '<think>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 4608,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 5000000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.10.2",
+  "use_cache": false,
+  "vocab_size": 130560
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    130073
+  ],
+  "pad_token_id": 1,
+  "temperature": 0.9,
+  "top_p": 0.95,
+  "transformers_version": "5.10.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56e5c04e2ade5b2fc32fdce0ea907703b81c49154b9c97dc71dee0800203c018
+size 2161290944

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": true,
+  "legacy": true,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0e4273416626fb87df306612ea41f4481d5c94232c2771f7b1a1fcee32338a6
+size 8593