当前位置:   article > 正文

The new behaviour of LlamaTokenizer (with self.legacy = False) requires the protobuf library but it_the new behaviour of llamatokenizer (with `self.le

the new behaviour of llamatokenizer (with `self.legacy = false`) requires th

报错:The new behaviour of LlamaTokenizer (with self.legacy = False) requires the protobuf library but it was not found in your environment. 

解决方法:

pip install protobuf
pip install transformers_stream_generator

来源:

[Feature] requerment is not enough during Qwen and Llama2 model quantization · Issue #755 · InternLM/lmdeploy · GitHub

声明:本文内容由网友自发贡献,不代表【wpsshop博客】立场,版权归原作者所有,本站不承担相应法律责任。如您发现有侵权的内容,请联系我们。转载请注明出处:https://www.wpsshop.cn/w/不正经/article/detail/365444
推荐阅读
相关标签
  

闽ICP备14008679号