抽取视觉模型时发生错误

[Minami-su]

提取的权重已保存到 ./vision/pytorch_model.bin
Traceback (most recent call last):
File "/data/jcxy/haolu/workspace/frameworks/Zero-Qwen-VL/extract_weight.py", line 47, in
vision_model = AutoModel.from_pretrained('./vision', trust_remote_code=True, torch_dtype=torch.bfloat16, device_map="cuda")
File "/work/jcxy/.conda/envs/haolu/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 524, in from_pretrained
config, kwargs = AutoConfig.from_pretrained(
File "/work/jcxy/.conda/envs/haolu/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 976, in from_pretrained
config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)
File "/work/jcxy/.conda/envs/haolu/lib/python3.10/site-packages/transformers/configuration_utils.py", line 632, in get_config_dict
config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
File "/work/jcxy/.conda/envs/haolu/lib/python3.10/site-packages/transformers/configuration_utils.py", line 689, in _get_config_dict
resolved_config_file = cached_file(
File "/work/jcxy/.conda/envs/haolu/lib/python3.10/site-packages/transformers/utils/hub.py", line 373, in cached_file
raise EnvironmentError(
OSError: ./vision does not appear to have a file named config.json. Checkout 'https://huggingface.co/./vision/tree/None' for available files.

顺便想了解下llava_pro目录下的config.json是怎么获取的,是否可以自己手动读取?