Skip to content

Conversation

mudler
Copy link
Owner

@mudler mudler commented Apr 16, 2023

This adds the following to the API:

  • Allow to set n to return more predictions in one API call
  • Exposes batch, f16 and ignore_eos (not available in the original OpenAI API, but available in llama.cpp)
  • Adds echo to return back the prompt in the response
  • Avoid returning empty message when using the completion endpoint

Signed-off-by: mudler <mudler@c3os.io>
@mudler mudler force-pushed the feat/enhance_api_support branch from 6067377 to 035df63 Compare April 16, 2023 08:06
@mudler mudler merged commit b062f31 into master Apr 16, 2023
@mudler mudler deleted the feat/enhance_api_support branch April 16, 2023 08:16
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.

1 participant