WizardCoder: Empowering Code Large Language Models with Evol-Instruct

By Ziyang Luo, Can Xu, Pu Zhao, Qingfeng Sun, Xiubo Geng, Wenxiang Hu, Chongyang Tao, Jing Ma, Qingwei Lin, Daxin Jiang. 2023

1,012 citations recorded by the source corpus.

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

Subfields: Artificial Intelligence, Information Systems, Alignment & RLHF, Code Generation & Program Synthesis

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Yejin Choi
  2. Jianfeng Gao
  3. Mohit Bansal
  4. Luke S. Zettlemoyer
  5. Percy Liang
  6. Noah A. Smith
  7. Hannaneh Hajishirzi
  8. Hongsheng Li

In Information Systems

  1. Yinlin Deng
  2. Chun Xia
  3. Lingming Zhang
  4. Ling-Ming Zhang
  5. Soren Dunn
  6. Ge Li
  7. Zhi Jin
  8. Jiawei Liu

In Alignment & RLHF

  1. Yejin Choi
  2. Nouha Dziri

In Code Generation & Program Synthesis

  1. Ge Li
  2. Zhi Jin
  3. Armando Solar-Lezama
  4. Chun Xia
  5. Koushik Sen
  6. Jiawei Liu
  7. Lingming Zhang
  8. Peng Jin

Citations in the corpus