examples : allow extracting embeddings from decoder contexts #13797
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
|
@ggerganov does this mean that models that benefited from cache-less embeddings will still benefit from the feature introduced in #13108 |
|
@aviallon Yes, this change should not modify the behavior for encoder-only (a.k.a. cache-less) models like BERT. |
|
@ggerganov @ngxson you just earned a new sponsor. |
ngxson
approved these changes
May 26, 2025
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Outdated suggestions cannot be applied.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.
fix #13795
cont #13108
ref #13108 (comment)
Sometimes it might be necessary to extract embeddings from a decoder-only model. To support this, update the examples to call
llama_decode()instead ofllama_encode()when computing embeddings. The call will internally fallback tollama_encode()if the model is encoder-only.