🐛 Fix pad token id resolution in padding function#512
Merged
Ssukriti merged 4 commits intoApr 29, 2026
Conversation
Signed-off-by: Gaurav-Kumbhat <Gaurav.Kumbhat@ibm.com>
Signed-off-by: Gaurav-Kumbhat <Gaurav.Kumbhat@ibm.com>
Ssukriti
reviewed
Apr 28, 2026
| use_cache: bool = False, | ||
| contiguous_cache: bool = False, | ||
| eos_token_id: Optional[int] = None, | ||
| pad_token_id: Optional[int] = None, |
Contributor
|
can you update PR @gkumbhat ? |
Collaborator
Author
|
@Ssukriti yep. I'll update the PR |
Ssukriti
reviewed
Apr 29, 2026
Signed-off-by: Gaurav-Kumbhat <Gaurav.Kumbhat@ibm.com>
Ssukriti
approved these changes
Apr 29, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Changes
Currently
pad_input_idsdoesn't take into account padding token id for model and assumes it to be0for all users. However, this can sometimes be not the case, for example for mistral-3 models, the padding token id is actually11. This can cause very confusing problems. This PR fixes it by taking optionalpad_token_idparameter and using that instead of doingtorch.zeros