For using this code in your project, you should modify configs.py
and also extract_label()
function in opro.py
file.
pip install -r requirements.txt
.
This project support Llama-3, GPT-4 and GPT-3.5 LLMs. The default mode is Llama-3.
@article{yang2023large,
title={Large language models as optimizers},
author={Yang, Chengrun and Wang, Xuezhi and Lu, Yifeng and Liu, Hanxiao and Le, Quoc V and Zhou, Denny and Chen, Xinyun},
journal={arXiv preprint arXiv:2309.03409},
year={2023}
}