Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

LLava API Improvements #757

Merged
merged 1 commit into from
May 26, 2024

Conversation

martindevans
Copy link
Member

  • Added new ways to create an image embedding which don't require a context
  • Added a way to get the embedding data directly from an image embed (one embedding vector at a time)

These are a couple of things that I've added while working on embeddings prompting support for the BatchedExecutor.

…ontext

 - Added a way to get the embedding data directly from an image embed (one embedding vector at a time)
@SignalRT
Copy link
Collaborator

@martindevans, It seems to be OK to me. I don't have the context of what are you doing with the BatchExecutor, but I don't see nothing extrange.

@martindevans martindevans merged commit 22342c6 into SciSharp:master May 26, 2024
6 checks passed
@martindevans martindevans deleted the llava_improvements branch May 26, 2024 22:06
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