| { | |
| "model": "Qwen/Qwen3-30B-A3B", | |
| "model_type": "qwen3_moe", | |
| "model_revision": null, | |
| "task_type": "causal_lm", | |
| "torch_dtype": "bfloat16", | |
| "attn_impl": null, | |
| "num_labels": null, | |
| "problem_type": null, | |
| "rope_scaling": null, | |
| "device_map": null, | |
| "max_memory": {}, | |
| "local_repo_path": null, | |
| "template": "qwen3", | |
| "system": null, | |
| "max_length": 2048, | |
| "truncation_strategy": "delete", | |
| "max_pixels": null, | |
| "agent_template": null, | |
| "norm_bbox": null, | |
| "response_prefix": null, | |
| "padding_side": "right", | |
| "loss_scale": "default", | |
| "sequence_parallel_size": 1, | |
| "use_chat_template": true, | |
| "template_backend": "swift", | |
| "dataset": [], | |
| "val_dataset": [], | |
| "split_dataset_ratio": 0.01, | |
| "data_seed": 42, | |
| "dataset_num_proc": 1, | |
| "dataset_shuffle": true, | |
| "val_dataset_shuffle": false, | |
| "streaming": false, | |
| "interleave_prob": null, | |
| "stopping_strategy": "first_exhausted", | |
| "shuffle_buffer_size": 1000, | |
| "enable_cache": false, | |
| "download_mode": "reuse_dataset_if_exists", | |
| "columns": {}, | |
| "strict": false, | |
| "remove_unused_columns": true, | |
| "model_name": [ | |
| null, | |
| null | |
| ], | |
| "model_author": [ | |
| null, | |
| 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": null, | |
| "load_dataset_config": null, | |
| "lora_modules": [], | |
| "tuner_backend": "peft", | |
| "train_type": "lora", | |
| "adapters": [], | |
| "external_plugins": [], | |
| "seed": 42, | |
| "model_kwargs": {}, | |
| "load_args": true, | |
| "load_data_args": false, | |
| "use_hf": true, | |
| "hub_token": null, | |
| "custom_register_path": [], | |
| "ignore_args_error": false, | |
| "use_swift_lora": false, | |
| "merge_lora": false, | |
| "safe_serialization": true, | |
| "max_shard_size": "5GB", | |
| "output_dir": "/fsx/s3/cantina-text-datastore/megatron_output/Qwen3-30B-A3B-mcore/training_data_sft_v1_hf_20250512_ms_swift_json_outputs_lr2e-6/v0-20250605-204723_iter2000_hf", | |
| "quant_n_samples": 256, | |
| "quant_batch_size": 1, | |
| "group_size": 128, | |
| "to_ollama": false, | |
| "to_mcore": false, | |
| "to_hf": true, | |
| "mcore_model": "/fsx/s3/cantina-text-datastore/megatron_output/Qwen3-30B-A3B-mcore/training_data_sft_v1_hf_20250512_ms_swift_json_outputs_lr2e-6/v0-20250605-204723", | |
| "thread_count": 7, | |
| "test_convert_precision": false, | |
| "push_to_hub": false, | |
| "hub_model_id": null, | |
| "hub_private_repo": false, | |
| "commit_message": "update files", | |
| "to_peft_format": false, | |
| "exist_ok": false, | |
| "rank": 0, | |
| "local_rank": 0, | |
| "global_world_size": 1, | |
| "local_world_size": 1, | |
| "model_suffix": "Qwen3-30B-A3B", | |
| "model_info": "ModelInfo(model_type='qwen3_moe', model_dir='/root/.cache/huggingface/hub/models--Qwen--Qwen3-30B-A3B/snapshots/ae659febe817e4b3ebd7355f47792725801204c9', torch_dtype=torch.bfloat16, max_model_len=40960, quant_method=None, quant_bits=None, rope_scaling=None, config=None, task_type='causal_lm', num_labels=None)", | |
| "model_meta": "ModelMeta(model_type='qwen3_moe', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-30B-A3B-Base', hf_model_id='Qwen/Qwen3-30B-A3B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Base', hf_model_id='Qwen/Qwen3-235B-A22B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-30B-A3B', hf_model_id='Qwen/Qwen3-30B-A3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B', hf_model_id='Qwen/Qwen3-235B-A22B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3', get_function=<function get_model_tokenizer_with_flash_attn at 0x7fb186d6ae80>, 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": "/root/.cache/huggingface/hub/models--Qwen--Qwen3-30B-A3B/snapshots/ae659febe817e4b3ebd7355f47792725801204c9", | |
| "hub": "<class 'swift.hub.hub.HFHub'>" | |
| } |