AttributeError: ‘ChatGLMTokenizer‘ object has no attribute ‘sp_tokenizer‘

报错信息：

Traceback (most recent call last):
  File "D:/workspace/PyCharmProjects/nlp_project/llm/zero_shot/finance_clssify.py", line 64, in <module>
    tokenizer = AutoTokenizer.from_pretrained("D:/workspace/PyCharmProjects/nlp_project/ChatGLM-6B/THUDM/chatglm-6b-int4", trust_remote_code=True)
  File "D:\MyPython\anaconda3\lib\site-packages\transformers\models\auto\tokenization_auto.py", line 881, in from_pretrained
    return tokenizer_class.from_pretrained(
  File "D:\MyPython\anaconda3\lib\site-packages\transformers\tokenization_utils_base.py", line 2291, in from_pretrained
    return cls._from_pretrained(
  File "D:\MyPython\anaconda3\lib\site-packages\transformers\tokenization_utils_base.py", line 2525, in _from_pretrained
    tokenizer = cls(*init_inputs, **init_kwargs)
  File "C:\Users\cts618\.cache\huggingface\modules\transformers_modules\chatglm-6b-int4\tokenization_chatglm.py", line 196, in __init__
    super().__init__(
  File "D:\MyPython\anaconda3\lib\site-packages\transformers\tokenization_utils.py", line 436, in __init__
    self._add_tokens(
  File "D:\MyPython\anaconda3\lib\site-packages\transformers\tokenization_utils.py", line 536, in _add_tokens
    current_vocab = self.get_vocab().copy()
  File "C:\Users\cts618\.cache\huggingface\modules\transformers_modules\chatglm-6b-int4\tokenization_chatglm.py", line 248, in get_vocab
    vocab = {self._convert_id_to_token(i): i for i in range(self.vocab_size)}
  File "C:\Users\cts618\.cache\huggingface\modules\transformers_modules\chatglm-6b-int4\tokenization_chatglm.py", line 244, in vocab_size
    return self.sp_tokenizer.num_tokens
AttributeError: 'ChatGLMTokenizer' object has no attribute 'sp_tokenizer'

解决方案：
注意：版本不兼容，pip安装库最好指定版本安装，不指定版本号默认最新版