OSError: Can‘t load tokenizer for ‘bert-base-uncased‘.
一、具体报错:
报错如下:
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 dir
二、报错原因:
模型调用bert时,由于huggingface有墙导致模型无法下载
三、 解决方法:
1、通过镜像站下载
直接命令行通过huggingface
镜像运行脚本,从而下载对应bert模型权重
HF_ENDPOINT=https://hf-mirror.com python 模型脚本.py
与之相同,通过设置环境变量也可以,以linux为例
export HF_ENDPOINT=https://hf-mirror.com
2、直接下载权重
地址:https://huggingface.co/google-bert/bert-base-uncased/tree/main
镜像地址:https://hf-mirror.com/google-bert/bert-base-uncased/tree/main
下载内容:
config.json
pytorch_model.bin
tokenizer.json
tokenizer_config.json
vocab.txt
将对应文件放入一个文件夹内,如bert-base-uncased
;查看报错所在的文件具体位置,以及对应引用模型的位置
如
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
将from_pretrained()
中的内容换成模型所在文件夹的路径,建议填写绝对路径
tokenizer = BertTokenizer.from_pretrained('./bert-base-uncased')