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

Add DEBERTA-V2 #53

Open
tjake opened this issue Sep 16, 2024 · 3 comments
Open

Add DEBERTA-V2 #53

tjake opened this issue Sep 16, 2024 · 3 comments

Comments

@tjake
Copy link
Owner

tjake commented Sep 16, 2024

Hi I'd love to use one model of Meta based on DEBERTA-V2 model from Microsoft. When I run the model on jlama I got a : java.lang.IllegalArgumentException: No enum constant com.github.tjake.jlama.model.ModelSupport.ModelType.DEBERTA-V2.

Is there any plan to provide support for this kind of models?

Thank you very much.

Originally posted by @lordofthejars in #52

@lordofthejars
Copy link
Contributor

Thank you very much, I don't know how I could help you on this, if you need I test it, or help in documentation, anytihng please ping me.

@tjake
Copy link
Owner Author

tjake commented Sep 16, 2024

The architecture looks quite different so it may take some time for me to figure it out (on top of other priorities)

@lordofthejars
Copy link
Contributor

Ok, I understand that, Deberta seems also quite popular as it is been pushed by Microsoft for some tasks like text classification, running really fast.

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