Christiannov / SWE-bench

SWE-Bench: Can Language Models Resolve Real-world Github Issues?

---

Code and data for paper "SWE-bench: Can Language Models Resolve Real-World GitHub Issues?".

Please refer our website for the public leaderboard and the change log for information on the latest updates to the SWE-bench benchmark.

👋 Overview

SWE-bench is a benchmark for evaluating large language models on real world software issues collected from GitHub. Given a codebase and an issue, a language model is tasked with generating a patch that resolves the described problem.

🚀 Set Up

To build SWE-bench from source, follow these steps:

1. Clone this repository locally
2. cd into the repository.
3. Run conda env create -f environment.yml to created a conda environment named swe-bench
4. Activate the environment with conda activate swe-bench

💽 Usage

You can download the SWE-bench dataset directly (dev, test sets) or from HuggingFace.

Find out more about how to use SWE-bench, such as how to...

• Evaluate models against SWE-bench
• Run SWE-bench's data collection procedure on your own repositories
• Train your own models on our pre-processed datasets or run inference on models directly.

Datasets	Models
🤗 SWE-bench	🦙 SWE-Llama 13b
🤗 "Oracle" Retrieval	🦙 SWE-Llama 13b (PEFT)
🤗 BM25 Retrieval 13K	🦙 SWE-Llama 7b
🤗 BM25 Retrieval 27K	🦙 SWE-Llama 7b (PEFT)
🤗 BM25 Retrieval 40K
🤗 BM25 Retrieval 50K (Llama tokens)

🍎 Tutorials

We've also written the following blog posts on how to use different parts of SWE-bench. If you'd like to see a post about a particular topic, please let us know via an issue.

• [Nov 1. 2023] Collecting Evaluation Tasks for SWE-Bench (🔗)
• [Nov 6. 2023] Evaluating on SWE-bench (🔗)

💫 Contributions

We would love to hear from the broader NLP, Machine Learning, and Software Engineering research communities, and we welcome any contributions, pull requests, or issues! To do so, please either file a new pull request or issue and fill in the corresponding templates accordingly. We'll be sure to follow up shortly!

Contact person: Carlos E. Jimenez and John Yang (Email: {carlosej, jy1682}@princeton.edu).

✍️ Citation

If you find our work helpful, please use the following citations.

@misc{jimenez2023swebench,
      title={SWE-bench: Can Language Models Resolve Real-World GitHub Issues?}, 
      author={Carlos E. Jimenez and John Yang and Alexander Wettig and Shunyu Yao and Kexin Pei and Ofir Press and Karthik Narasimhan},
      year={2023},
      eprint={2310.06770},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

🪪 License

MIT. Check LICENSE.md.