You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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.
The text was updated successfully, but these errors were encountered:
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.
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.
The text was updated successfully, but these errors were encountered: