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

Some requests #59

Closed
godlikehhd opened this issue Aug 23, 2024 · 1 comment
Closed

Some requests #59

godlikehhd opened this issue Aug 23, 2024 · 1 comment

Comments

@godlikehhd
Copy link

  1. if possible, please add the way to evaluate swe-bench-verified.
  2. did you use other model like LLama 3.1 or Claude as backbone, if so, could you please release the result
    Thanks a lot !
@Marti2203
Copy link
Collaborator

Hi,

  1. Yes, you can use https://github.com/nus-apr/auto-code-rover/blob/main/conf/swe_verified_tasks.txt just as you use swe_lite_tasks.txt see also https://github.com/nus-apr/auto-code-rover#swe-bench-mode-set-up-and-run-on-swe-bench-tasks
  2. We have support for both of these models and have ran preliminary tests with LLama3.1 and a lot more with Claude 3 Opus and 3.5 Sonnet. For sonnet, we have submitted the results to swe-bench
    Hope that this answers your question :)

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

No branches or pull requests

2 participants