merge_lora后调用模型产生AttributeError: can't set attribute错误

[Asakinevergup]

No description provided.

[Asakinevergup]

你好 我在训练好lora，使用merge_lora后尝试调用模型时候产生了下列错误，您能帮我看看哪里出问题了吗？谢谢！
(ChatGLM) @n1:~/ChatGLM-Finetuning-master$ python test.py
Traceback (most recent call last):
File "test.py", line 7, in
tokenizer = ChatGLMTokenizer.from_pretrained(model_dir)
File "/home/.local/lib/python3.8/site-packages/transformers/tokenization_utils_base.py", line 2048, in from_pretrained
return cls._from_pretrained(
File "/home/.local/lib/python3.8/site-packages/transformers/tokenization_utils_base.py", line 2287, in _from_pretrained
tokenizer = cls(*init_inputs, **init_kwargs)
File "/home/ChatGLM-Finetuning-master/glm3/tokenization_chatglm.py", line 108, in init
super().init(padding_side=padding_side, clean_up_tokenization_spaces=clean_up_tokenization_spaces,
File "/home/.local/lib/python3.8/site-packages/transformers/tokenization_utils.py", line 363, in init
super().init(**kwargs)
File "/home/.local/lib/python3.8/site-packages/transformers/tokenization_utils_base.py", line 1603, in init
super().init(**kwargs)
File "/home/.local/lib/python3.8/site-packages/transformers/tokenization_utils_base.py", line 861, in init
setattr(self, key, value)
AttributeError: can't set attribute

//下列是我的测试代码
import torch
from transformers import AutoTokenizer, AutoModel
from glm3.tokenization_chatglm import ChatGLMTokenizer
model_dir='./output-glm3/epoch-2-step-720/'

//使用 ChatGLMTokenizer 从本地路径加载分词器
tokenizer = ChatGLMTokenizer.from_pretrained(model_dir)
model = AutoModel.from_pretrained(model_dir, trust_remote_code=True).to("cuda").eval()

//测试模型
response, history = model.chat(tokenizer, "hello", history=[])
print("Response:", response)