【无标题】

Can‘t load tokenizer for ‘bert-base-uncased’

在复现Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models过程中，加载模型是调用lavis.models加载模型，如果在国内的同学出现以下错误：

OSError: Can't load tokenizer for 'bert-base-uncased'.
If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name.
Otherwise, make sure 'bert-base-uncased' is the correct path to a directory containing all r
elevant files for a BertTokenizer tokenizer.

那么大概率是由于国内网络的问题，我们只需要添加镜像源即可：

 HF_ENDPOINT=https://hf-mirror.com python BLIP_2.py 

这里的 BLIP_2.py 更改为你自己的代码即可
该文章转载来自：Kawords 的分享。