This repository contains the code for the CodeIF project.
New Bench for Code Instruction Fellow
🏠 Home Page • 📊 Benchmark Data • 🏆 Leaderboard
-
Python Version
- Ensure that Python 3.11 is installed on your machine.
-
Install Dependencies
- Install all dependencies that are required for the project by running:
pip install -r requirements.txt
- Install all dependencies that are required for the project by running:
-
Configure the Script
- Provide the necessary configuration for the script in
script/if_pipeline.sh
:model="" api_base="" api_key=""
- Provide the necessary configuration for the script in
After setting up the environment, the scripts can be run with the provided model, API base, and API key configurations. Execution
bash scripts/if_pipeline.sh
- Note
- Replace placeholder values with your actual API credentials
- Ensure execution permissions for scripts:
chmod +x scripts/*.sh
Feel free to cite us.
@misc{yan2025codeifbenchmarkinginstructionfollowingcapabilities,
title={CodeIF: Benchmarking the Instruction-Following Capabilities of Large Language Models for Code Generation},
author={Kaiwen Yan and Hongcheng Guo and Xuanqing Shi and Jingyi Xu and Yaonan Gu and Zhoujun Li},
year={2025},
eprint={2502.19166},
archivePrefix={arXiv},
primaryClass={cs.SE},
url={https://arxiv.org/abs/2502.19166},
}
Feel free to contact us if you have any question or cooperation! Email: lin_rany@foxmail.com