P-Turning微调之后保存的模型会产生推断错误

[CmyLjj]

tokenizer = AutoTokenizer.from_pretrained(
tokenizer_dir, trust_remote_code=True
)
这段代码会报以下错误
File "/data1/caomy/chatglm3-demo/finetune_demo/inference_hf.py", line 59, in
model, tokenizer = load_model_and_tokenizer(model_dir)
File "/data1/caomy/chatglm3-demo/finetune_demo/inference_hf.py", line 40, in load_model_and_tokenizer
tokenizer = AutoTokenizer.from_pretrained(
File "/data2/caomy/envs/chatglm3/lib/python3.9/site-packages/transformers/models/auto/tokenization_auto.py", line 801, in from_pretrained
return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
File "/data2/caomy/envs/chatglm3/lib/python3.9/site-packages/transformers/tokenization_utils_base.py", line 2029, in from_pretrained
return cls._from_pretrained(
File "/data2/caomy/envs/chatglm3/lib/python3.9/site-packages/transformers/tokenization_utils_base.py", line 2261, in _from_pretrained
tokenizer = cls(*init_inputs, **init_kwargs)
File "/home/caomy/.cache/huggingface/modules/transformers_modules/checkpoint-500/tokenization_chatglm.py", line 108, in init
super().init(padding_side=padding_side, clean_up_tokenization_spaces=clean_up_tokenization_spaces,
File "/data2/caomy/envs/chatglm3/lib/python3.9/site-packages/transformers/tokenization_utils.py", line 363, in init
super().init(**kwargs)
File "/data2/caomy/envs/chatglm3/lib/python3.9/site-packages/transformers/tokenization_utils_base.py", line 1603, in init
super().init(**kwargs)
File "/data2/caomy/envs/chatglm3/lib/python3.9/site-packages/transformers/tokenization_utils_base.py", line 861, in init
setattr(self, key, value)
AttributeError: can't set attribute

[Angelicaduti]

您好，请问这个问题解决了吗，我也遇到相同问题了