Intermediate layers output (MLP + hidden_states)#9
Open
Antebe wants to merge 6 commits into
Open
Conversation
rmovva
reviewed
Aug 7, 2025
Owner
There was a problem hiding this comment.
I think we should just leave the get_local_embeddings() function untouched, and create a separate function get_internal_representations() function so as to avoid adding parameters/complexity to get_local_embeddings().
This latter function can just be a simple wrapper on extract_intermediate_representations
Also, I wonder if we should test with a non-embedding model that one might actually use for language generation, such as Llama or Qwen etc?
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
would appreciate if someone could work on the attention