Add MultipleChoice & QuestionAnswering heads to ModernBERT #35825
+464
−47
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Hi @warner-benjamin, we already have a PR for the QuestionAnswering head at #35566, which should have been merged by now, but I'm slow at reviewing We definitely appreciate the |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR adds the ForQuestionAnswering and ForMultipleChoice heads to ModernBERT. It also updates the existing heads to use the
self.loss_functionloss implementations where one exists.At the moment I have removed the full model sequence packing inputs from the
ModernBertForMultipleChoicehead, as I don't think we can guarantee they would be correct post flattening. I think it would be better to haveModernBertBasehandle unpadding for this head to reduce complexity and edge cases.cc @ArthurZucker, @tomaarsen