ValueError: The current `device_map` had weights offloaded to the disk. Please provide an `offload_folder` for them. Alternatively, make sure you have `safetensors` installed if the model you are using offers the weights in this format.

[klj123wan]

init model ... Traceback (most recent call last): File "/Volumes/D671087/Baichuan-13B/cli_demo.py", line 87, in main() File "/Volumes/D671087/Baichuan-13B/cli_demo.py", line 48, in main model, tokenizer = init_model() File "/Volumes/D671087/Baichuan-13B/cli_demo.py", line 13, in init_model model = AutoModelForCausalLM.from_pretrained( File "/Users/alexkong/anaconda3/envs/baichuan/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 560, in from_pretrained return model_class.from_pretrained( File "/Users/alexkong/anaconda3/envs/baichuan/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3307, in from_pretrained ) = cls._load_pretrained_model( File "/Users/alexkong/anaconda3/envs/baichuan/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3428, in _load_pretrained_model raise ValueError( ValueError: The current device_map had weights offloaded to the disk. Please provide an offload_folder for them. Alternatively, make sure you have safetensors installed if the model you are using offers the weights in this format.

Mac m1 ，在外接硬盘上面运行，hug 软连到电脑上，真实文件也是在外接硬盘上面