Skip to content

Conversation

@rasdani
Copy link

@rasdani rasdani commented Apr 22, 2025

@rasdani
Copy link
Author

rasdani commented May 5, 2025

verifier pretty much done.

currently tweaking prompt for DeepSeek R1. you can track progress here: https://huggingface.co/datasets/rasdani/swe-fixer-debug-DeepSeek-R1-verified

I ditched removing newlines and refrained from other string normalization to make the verifier more strict for training. Such that the model learns to adhere more to the code base style.
For synthetic data gen the score might be to strict though.

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.

2 participants