Suport for embedded representation #3156
Merged
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
Radu1999
changed the title
tomaarsen
reviewed
Jan 9, 2025
|
Looks good! Thanks for this.
|
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Outdated suggestions cannot be applied.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.
Previously, the SentenceTransformer wrapper did not allow passing precomputed embeddings (embedded representation).
Many models from the transformers library support this, such as llama, gemma, gemma2, mistral, bert etc.
This feature is particularly (but not only) useful for experimenting with different techniques of custom soft prompting.
The implementations do not support passing both
input_idsandinputs_embedssimultaneously: example. Therefore, i implemented them as being mutually exclusive, withinputs_embedstaking precedence.