-
Notifications
You must be signed in to change notification settings - Fork 44
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Issue of the path #11
Comments
如果你用的是英文的BERT的话,可以这么写: 其中MODEL_TYPE 对应的是用的什么transformer预训练模型,例如bert,albert,roberta |
好的十分感谢!还有一个小问题如果我想使用electra的话electra-base-discriminator和electra-base-generator是需要都放在pretrained_models中使用吗 |
这个不用的,只要MODEL_NAME_OR_PATH的路径写对了就行,例如/pretrained_models/electra/electra-base-discriminator,而不应该是/pretrained_models/electra/, MODEL_NAME_OR_PATH这个目录下应该要有pytorch_model.bin这个文件的 |
ok我明白了,谢谢!!! |
为什么我的路径按照这个写了还是一直加载不进来呢 一直是这个错误OSError: Can't load 'pretrained_models/bert-base-uncased/,' |
你好请问下--model_type和--model_name_or_path的对应路径是什么呢?(我修改后一直报错OSERROR:can't load.....,特来向您请教。)
The text was updated successfully, but these errors were encountered: