wip: add swe-fixer verifier #79
Draft
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
apaz-cli
reviewed
Apr 22, 2025
Author
|
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. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Adds a verifier for patching real world Github issues, inspired from InternLM's SWE-fixer.
still WIP.
https://github.com/InternLM/SWE-Fixer
https://huggingface.co/datasets/internlm/SWE-Fixer-Train-Editing-CoT-70K
https://huggingface.co/datasets/rasdani/swe-fixer-debug-pi-format