fix: stripping logic in Update check_fingerprints.py #14
Conversation
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
This PR fixes a bug where bos_token was intended to be stripped from the signature_tokenized sequences, but the processed list was not reassigned back — effectively leaving the original tokens unchanged. The code correctly creates new_signature_tokenized without the bos_token, but then mistakenly keeps using the original signature_tokenized. This fix ensures that the model's output is compared against the expected signature without the BOS token, as originally intended. It should improve the accuracy of the backdoor detection evaluation, especially in cases where BOS token presence causes mismatch.
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Outdated suggestions cannot be applied.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 fixes a bug where bos_token was intended to be stripped from the signature_tokenized sequences, but the processed list was not reassigned back — effectively leaving the original tokens unchanged.
The code correctly creates new_signature_tokenized without the bos_token, but then mistakenly keeps using the original signature_tokenized.
This fix ensures that the model's output is compared against the expected signature without the BOS token, as originally intended.
It should improve the accuracy of the backdoor detection evaluation, especially in cases where BOS token presence causes mismatch.