Skip to content

Intermediate layers output (MLP + hidden_states)#9

Open
Antebe wants to merge 6 commits into
rmovva:mainfrom
Antebe:chore
Open

Intermediate layers output (MLP + hidden_states)#9
Antebe wants to merge 6 commits into
rmovva:mainfrom
Antebe:chore

Conversation

@Antebe

@Antebe Antebe commented Aug 6, 2025

Copy link
Copy Markdown
Contributor

would appreciate if someone could work on the attention

Comment thread hypothesaes/embedding.py

Copy link
Copy Markdown
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants