{ "use_ray": false, "ray_exp_name": null, "device_groups": null, "model": "/comp_robot/jiangqing/projects/2023/research/R1/QwenSFTOfficial/open_source/IDEA-Research/Rex-Omni", "model_type": "qwen2_5_vl", "model_revision": null, "task_type": "causal_lm", "torch_dtype": "float16", "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": "qwen2_5_vl", "system": null, "max_length": 4096, "truncation_strategy": "delete", "max_pixels": null, "agent_template": null, "norm_bbox": null, "use_chat_template": true, "padding_free": false, "padding_side": "right", "loss_scale": "default", "sequence_parallel_size": 1, "response_prefix": null, "template_backend": "swift", "dataset": [ "work_dirs/quatilize.json" ], "val_dataset": [], "split_dataset_ratio": 0.0, "data_seed": 42, "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, "remove_unused_columns": true, "model_name": null, "model_author": null, "custom_dataset_info": [], "quant_method": "awq", "quant_bits": 4, "hqq_axis": null, "bnb_4bit_compute_dtype": "float32", "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, "lora_modules": [], "tuner_backend": "peft", "train_type": "lora", "adapters": [], "external_plugins": [], "seed": 42, "model_kwargs": {}, "load_args": true, "load_data_args": false, "packing": false, "packing_length": null, "lazy_tokenize": true, "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, "merge_lora": false, "safe_serialization": true, "max_shard_size": "5GB", "output_dir": "/comp_robot/jiangqing/projects/2023/research/R1/QwenSFTOfficial/open_source/IDEA-Research/Rex-Omni-AWQ", "quant_n_samples": 256, "quant_batch_size": null, "group_size": 128, "to_cached_dataset": false, "to_ollama": false, "to_mcore": false, "to_hf": false, "mcore_model": null, "mcore_adapters": [], "thread_count": null, "test_convert_precision": false, "test_convert_dtype": "float32", "push_to_hub": false, "hub_model_id": null, "hub_private_repo": false, "commit_message": "update files", "to_peft_format": false, "exist_ok": false, "rank": -1, "local_rank": -1, "global_world_size": 1, "local_world_size": 1, "model_suffix": "Rex-Omni", "model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/comp_robot/jiangqing/projects/2023/research/R1/QwenSFTOfficial/open_source/IDEA-Research/Rex-Omni', torch_dtype=torch.float16, max_model_len=128000, quant_method=None, quant_bits=None, rope_scaling={'mrope_section': [16, 24, 24], 'rope_type': 'default', 'type': 'default'}, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)", "model_meta": "ModelMeta(model_type='qwen2_5_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_vl', get_function=, model_arch=MultiModelKeys(arch_name='qwen2_vl', 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=['model'], aligner=['visual.merger'], vision_tower=['visual'], generator=[]), architectures=['Qwen2_5_VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.49', 'qwen_vl_utils>=0.0.6', 'decord'], tags=['vision', 'video'])", "model_dir": "/comp_robot/jiangqing/projects/2023/research/R1/QwenSFTOfficial/open_source/IDEA-Research/Rex-Omni", "hub": "" }