Incorporate embedding pooling layer fixes #1194
Merged
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
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Outdated suggestions cannot be applied.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.
Made some fixes to the pooling layer in
llama.cppthat are reflected here. Previously we had to divide by the number of tokens in the sequence. Now we can just take them as-is and optionally normalize. Also changed the truncation ton_batchrather thann_ctxsince that's what we're writing to.Embedding numbers now match up very closely with SentenceTransformers. Usually around
1-(1e-7)cosine similarity, though there are some remaining issues with tokenizing text with accents.