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

Offline learning tweak; adding gradients for tool_choice #113

Merged
merged 5 commits into from
Oct 23, 2024

Conversation

sidnarayanan
Copy link
Collaborator

  • Separated out logic for full-batch offline learning to make it easier on the user
  • LLMCallOp was missing a gradient for tool_choice; added

ldp/alg/runners.py Outdated Show resolved Hide resolved
.pre-commit-config.yaml Outdated Show resolved Hide resolved
Comment on lines -212 to -214
# Trainable is metadata that an optimizer can use this. It enables things
# like (remote) fine-tuning with OpenAI
self.trainable: bool = False
Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Forgot to flag this earlier - removing unused flag.

Copy link
Collaborator

@jamesbraza jamesbraza left a comment

Choose a reason for hiding this comment

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

Nice little detail, wow

@sidnarayanan sidnarayanan merged commit ea8733d into main Oct 23, 2024
5 of 6 checks passed
@sidnarayanan sidnarayanan deleted the offline-improvements branch October 23, 2024 18:42
@jamesbraza jamesbraza mentioned this pull request Oct 23, 2024
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.

3 participants