Embeddings fix for truncation without room for begin/end and for batch truncation #343
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
Contributor
markstur
commented
Apr 3, 2024
markstur
commented
- Attempting truncate_input_tokens=2 (or 1) was creating a strange error (or misbehaving) because it takes at least 3 tokens for [CLS] TOK [SEP] for meaningful results.
- Now that truncate value generally means number of tokens not including begin/end.
- On the max end the 2 special tokens will be allowed to consume 2 from the limit.
- Batch embedding processing was returning odd/misordered results when combined with truncation. Added a re tokenize() call to avoid sending the overflow tokens as features to be processed.
markstur
requested review from
alex-jw-brooks,
gkumbhat,
evaline-ju,
gabe-l-hart,
tharapalanivel and
Ssukriti
as code owners
…h truncation * Attempting truncate_input_tokens=2 (or 1) was creating a strange error (or misbehaving) because it takes at least 3 tokens for [CLS] TOK [SEP] for meaningful results. * Now that truncate value generally means number of tokens not including begin/end. * On the max end the 2 special tokens will be allowed to consume 2 from the limit. * Batch embedding processing was returning odd/misordered results when combined with truncation. Added a re tokenize() call to avoid sending the overflow tokens as features to be processed. Signed-off-by: Mark Sturdevant <mark.sturdevant@ibm.com>
markstur
force-pushed
the
embed_trunc_fix
branch
from
9862a6d
to
780ddfa
Compare
evaline-ju
approved these changes
Apr 3, 2024
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Outdated suggestions cannot be applied.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.