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

Use modAL on BERT models #180

Open
XinY-Z opened this issue Oct 2, 2023 · 1 comment
Open

Use modAL on BERT models #180

XinY-Z opened this issue Oct 2, 2023 · 1 comment

Comments

@XinY-Z
Copy link

XinY-Z commented Oct 2, 2023

Hi, I'm new to active learning and modAL. I want to fine-tune a RoBERTa model on a (yet) unannotated dataset with active learning. Has anyone tried applying modAL to huggingface models like RoBERTa or DeBERTa? I wonder if the two modules are ever compatible.

@amirothman
Copy link

You're gonna have to elaborate your use-case a bit. As long as your classifier has a .predict method you should be able to use it. You would need to measure with the evaluation metric that you decide to determine whether it is a success or not.

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