下载transformers的预训练模型时，使用bert-base-cased等模型在AutoTokenizer和AutoModel时并不会有太多问题。但在下载deberta-v3-base时可能会发生很多报错。
首先，
from transformers import AutoTokneizer, AutoModel, AutoConfig
checkpoint = 'microsoft/deberta-v3-base'
tokenizer = AutoTokenizer.from_pretrained(checkpoint)此时会发生报错，提示
ValueError: Couldn't instantiate the backend tokenizer from one of:
(1) a `tokenizers` library serialization file,
(2) a slow tokenizer instance to convert or
(3) an equivalent slow tokenizer class to instantiate and convert.
You need to have sentencepiece installed to convert a slow tokenizer to a fast one.解决方法是文章来源：https://www.toymoban.com/news/detail-703868.html
pip install transformers sentencepiece继续导入tokenizer，又会有如下报错文章来源地址https://www.toymoban.com/news/detail-703868.html
ImportError:
DeberetaV2Converter requires the protobuf library but it was not f到了这里，关于Huggingface Transformers Deberta-v3-base安装踩坑记录的文章就介绍完了。如果您还想了解更多内容，请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章，希望大家以后多多支持TOY模板网！
![[linux] huggingface transformers 如何下载模型至本地 & git lfs install 报错](https://imgs.yssmx.com/Uploads/2024/02/688167-1.png)
