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

GPT-4 Only Option #733

Merged

Conversation

keenborder786
Copy link
Contributor

Background

There was no option that allowed the model to run in GPT-4 only mode.

Changes

Changed main.py module. parse_argument function was modified and the gpt4only argument was added to the parser. If gpt4only is provided by the user then fast_llm_model is set to smart_llm_model just like vice versa is happening in gpt3only mode.

Documentation

No additional documentation was needed.

Test Plan

PR Quality Checklist

  • My pull request is atomic and focuses on a single change.
  • I have thouroughly tested my changes with multiple different prompts.
  • I have considered potential risks and mitigations for my changes.
  • I have documented my changes clearly and comprehensively.
  • I have not snuck in any "extra" small tweaks changes

@keenborder786
Copy link
Contributor Author

@Torantulino please have a look.

@keenborder786
Copy link
Contributor Author

Please let me know if this is the correct way to go about it or do you want me to make any more changes to make gpt4only mode. I tested it and it seem to be working. Thank you.

Copy link
Contributor

@nponeccop nponeccop left a comment

Choose a reason for hiding this comment

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

LGTM but @Torantulino will inspect the logic

@nponeccop nponeccop mentioned this pull request Apr 11, 2023
1 task
@richbeales richbeales merged commit a0cebb0 into Significant-Gravitas:master Apr 12, 2023
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.

4 participants