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.

Sign up for GitHub

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

Jump to bottom

Create Evals #130

Open
mathewpareles opened this issue Oct 28, 2024 · 0 comments
Open

Create Evals #130

mathewpareles opened this issue Oct 28, 2024 · 0 comments
Assignees
@mathewpareles
Labels
new feature New feature or request

Comments

@mathewpareles
Copy link
Contributor

mathewpareles commented Oct 28, 2024 •
edited
Loading

We want to create evals for judging how well our LLMs perform on inline completions (ctrl+K), whole-file edits (ctrl+L), and autocomplete (tab).

A good starting task is to find an open-source eval for judging ctrl+L file completions (where the LLM rewrites a file given instructions). If you know of a high-quality data set for any of these tasks, we'd love to hear about it.
@andrewpareles andrewpareles added the new feature New feature or request label Oct 28, 2024
@mathewpareles mathewpareles self-assigned this Nov 4, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@mathewpareles mathewpareles

Labels
new feature New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@andrewpareles @mathewpareles