allyoung / internlm4law Goto Github PK

运行模型库上的示例代码碰到以下异常，不知是不是模型没上传正确？

import torch
import os
from transformers import AutoModelForCausalLM, AutoTokenizer, AutoModel

base_path = './zhangsan_say_law'

os.system('apt install git')
os.system('apt install git-lfs')
os.system(f'git clone https://code.openxlab.org.cn/ljnyyds/zhangsan_say_law.git {base_path}')
os.system(f'cd {base_path} && git lfs pull')

tokenizer = AutoTokenizer.from_pretrained(base_path,trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(base_path,trust_remote_code=True, torch_dtype=torch.float16).cuda()

UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 128: invalid start byte

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/home/zhanqing/projects/law_customer_service/src/pre_train/download_model2.py", line 15, in
model = AutoModelForCausalLM.from_pretrained(base_path,trust_remote_code=True, torch_dtype=torch.float16).cuda()
File "/home/zhanqing/anaconda3/envs/xtuner/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 556, in from_pretrained
return model_class.from_pretrained(
File "/home/zhanqing/anaconda3/envs/xtuner/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3502, in from_pretrained
) = cls._load_pretrained_model(
File "/home/zhanqing/anaconda3/envs/xtuner/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3903, in _load_pretrained_model
state_dict = load_state_dict(shard_file)
File "/home/zhanqing/anaconda3/envs/xtuner/lib/python3.10/site-packages/transformers/modeling_utils.py", line 551, in load_state_dict
raise OSError(
OSError: Unable to load weights from pytorch checkpoint file for '/data/models/zhangsan_say_law/pytorch_model-00001-of-00008.bin' at '/data/models/zhangsan_say_law/pytorch_model-00001-of-00008.bin'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.

如题