【大模型】return _sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg) TypeError: not a string

错误信息

运行大模型 Qwen1.5-14B-Chat 出现如下错误：

Traceback (most recent call last):
  File "/abc/llm/./transformers_low_bit_pipeline.py", line 44, in <module>
    tokenizer = LlamaTokenizer.from_pretrained(model_path, trust_remote_code=True)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/abc/.conda/envs/llm/lib/python3.11/site-packages/transformers/tokenization_utils_base.py", line 2048, in from_pretrained
    return cls._from_pretrained(
           ^^^^^^^^^^^^^^^^^^^^^
  File "/abc/.conda/envs/llm/lib/python3.11/site-packages/transformers/tokenization_utils_base.py", line 2287, in _from_pretrained
    tokenizer = cls(*init_inputs, **init_kwargs)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/abc/.conda/envs/llm/lib/python3.11/site-packages/transformers/models/llama/tokenization_llama.py", line 182, in __init__
    self.sp_model = self.get_spm_processor(kwargs.pop("from_slow", False))
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/abc/.conda/envs/llm/lib/python3.11/site-packages/transformers/models/llama/tokenization_llama.py", line 209, in get_spm_processor
    tokenizer.Load(self.vocab_file)
  File "/abc/.conda/envs/llm/lib/python3.11/site-packages/sentencepiece/__init__.py", line 961, in Load
    return self.LoadFromFile(model_file)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/abc/.conda/envs/llm/lib/python3.11/site-packages/sentencepiece/__init__.py", line 316, in LoadFromFile
    return _sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: not a string

重点信息

这行代码：

    tokenizer = LlamaTokenizer.from_pretrained(model_path, trust_remote_code=True)

报错：

  File "/abc/.conda/envs/llm/lib/python3.11/site-packages/sentencepiece/__init__.py", line 316, in LoadFromFile
    return _sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: not a string

解决方法

代码：

    from transformers import LlamaTokenizer, TextGenerationPipeline

    ...
    
    tokenizer = LlamaTokenizer.from_pretrained(model_path, trust_remote_code=True)
    

修改为：

    from transformers import LlamaTokenizer, TextGenerationPipeline, AutoTokenizer

    ...
    
    tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

验证

再次运行模型，正常！！