Add Roberta for classification to FMS#466
Merged
ani300 merged 5 commits intomainfoundation-model-stack/foundation-model-stack:mainfrom Oct 1, 2025
roberta-classificationfoundation-model-stack/foundation-model-stack:roberta-classificationCopy head branch name to clipboard
Merged
Add Roberta for classification to FMS#466ani300 merged 5 commits intomainfoundation-model-stack/foundation-model-stack:mainfrom roberta-classificationfoundation-model-stack/foundation-model-stack:roberta-classificationCopy head branch name to clipboard
ani300 merged 5 commits intomainfoundation-model-stack/foundation-model-stack:mainfrom
roberta-classificationfoundation-model-stack/foundation-model-stack:roberta-classificationCopy head branch name to clipboard
Conversation
Signed-off-by: Antoni Viros i Martin <aviros@ibm.com>
Signed-off-by: Antoni Viros i Martin <aviros@ibm.com>
JRosenkranz
reviewed
Sep 15, 2025
fms/modules/head.py
Outdated
| """ | ||
| if self.apply_pooling_fn: | ||
| x = x[:, 0] | ||
| x = self.pooler_linear(x) |
Collaborator
There was a problem hiding this comment.
Does adding this break anything existing? We were not doing this before?
Collaborator
Author
There was a problem hiding this comment.
we were never pooling before, so we never hit this path, and this was not matching the HF implementation, but now it does
JRosenkranz
requested changes
Sep 15, 2025
Collaborator
JRosenkranz
left a comment
There was a problem hiding this comment.
Can we add a new model expectation test for this?
Signed-off-by: Antoni Viros i Martin <aviros@ibm.com>
Signed-off-by: Antoni Viros i Martin <aviros@ibm.com>
JRosenkranz
reviewed
Sep 18, 2025
| str_to_activation(classifier_activation_fn), | ||
| dropout=classifier_dropout, | ||
| apply_pooling_fn=True, | ||
| do_pooling=True, |
Collaborator
There was a problem hiding this comment.
Why do we need both of these?
JRosenkranz
reviewed
Sep 18, 2025
| dropout: float | ||
| the dropout to use directly after activation (default is 0.0) | ||
| apply_pooling_fn: bool | ||
| do_pooling: bool |
Collaborator
There was a problem hiding this comment.
Ah, I see, this answers my above
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
Needed for testing fine-tuning on AIU