Skip to content
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

How to use Chinese model? #124

Closed
drxmy opened this issue Mar 2, 2022 · 2 comments
Closed

How to use Chinese model? #124

drxmy opened this issue Mar 2, 2022 · 2 comments

Comments

@drxmy
Copy link

drxmy commented Mar 2, 2022

Many Chinese models in hugging face like T5 use different tokenizer and model. For example, Chinese T5 uses T5ForConditionalGeneration and BertTokenizer. Is there some way to handle this kind of problems? Thank you!

@ShengdingHu
Copy link
Collaborator

We write a tutorial to show the use case that does not fit into the default configuration of OpenPrompt. In this tutorial, we use a bert tokenizer and a T5 model to do a Chinese Classic Poetry Retrieval task. Thanks for posing this issue!

@drxmy
Copy link
Author

drxmy commented Apr 20, 2022

Thanks a lot!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants