[GH-ISSUE #4699] Computing Context Embeddings, Instead of averagning token embeddings #64996

Open
opened 2026-05-03 19:29:10 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @Demirrr on GitHub (May 29, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4699

I was wondering whether we can return the context embeddings used before the next token prediction instead of averaging the token embeddings as currently done.

Originally created by @Demirrr on GitHub (May 29, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4699 I was wondering whether we can return the context embeddings used before the next token prediction instead of averaging the token embeddings as currently done.
GiteaMirror added the feature request label 2026-05-03 19:29:10 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#64996