fix(m3): exclude EOS token from colbert_vecs output #1558
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
The _process_colbert_vecs function was incorrectly including the EOS token. Since CLS is already excluded in colbert_embedding (via last_hidden_state[:, 1:]), we need to use tokens_num - 2 instead of tokens_num - 1 to also exclude the EOS token. Fixes FlagOpen#1490 Signed-off-by: majiayu000 <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Summary
_process_colbert_vecsto correctly exclude EOS tokentokens_num - 1totokens_num - 2Problem
The function was including the EOS token in the output. Since CLS is already excluded by
colbert_embedding(vialast_hidden_state[:, 1:]), usingtokens_num - 1still included EOS.Test plan
Fixes #1490