@inproceedings{luo2023wizardcoder,
author = {Luo, Ziyang and Xu, Can and Zhao, Pu and Sun, Qingfeng and Geng, Xiubo and Hu, Wenxiang and Tao, Chongyang and Ma, Jing and 林庆维, Qingwei Lin and Jiang (姜大昕), Daxin},
title = {WizardCoder: Empowering Code Large Language Models with Evol-Instruct},
booktitle = {ICLR 2024},
year = {2023},
month = {June},
abstract = {Code Large Language Models (Code LLMs), such as StarCoder, have demonstrated exceptional performance in code-related tasks. However, most existing models are solely pre-trained on extensive raw code data without instruction fine-tuning. In this paper, we introduce WizardCoder, which empowers Code LLMs with complex instruction fine-tuning, by adapting the Evol-Instruct method to the domain of code. Through comprehensive experiments on four prominent code generation benchmarks, namely HumanEval, HumanEval+, MBPP, and DS-1000, we unveil the exceptional capabilities of our model. It surpasses all other open-source Code LLMs by a substantial margin. Moreover, our model even outperforms the largest closed LLMs, Anthropic's Claude and Google's Bard, on HumanEval and HumanEval+. Our code, model weights, and data are public at https://github.com/nlpxucan/WizardLM},
url = {http://approjects.co.za/?big=en-us/research/publication/wizardcoder-empowering-code-large-language-models-with-evol-instruct/},
}