## 问题：
load LLaMA 7b的weights的时候报错：
ValueError: Tokenizer class LLaMATokenizer does not exist or is not currently imported.
## 出现原因：
新版transformers里面llama的tokenizer命名为LlamaTokenizer
但是旧的模型里面的tokenizer叫LLaMATokenizer
## 解决方案：
改动transformers源码中三个位置：
utils/dummy_sentencepiece_objects.py
models/auto/tokenization_aotu.py
__init__.py
在这三个文件中找到LlamaTokenizer, 改为LLaMATokenizier
参考：github.com/mbehm/transformers/tree/main/src/transformers
注：找到当前环境库源码，用 print(transformers.__file__)
- LLaMATokenizer ValueError Tokenizer currently notllamatokenizer valueerror tokenizer currently llamatokenizer tokenizer embedding tokenizer nlp tokenizer笔记llm tokenizer_from_json component tokenizer graph 1.2 texts preprocessing fit_on_texts tokenizer tokenizer_from_json 39 from preprocessing valueerror