English

Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data

Computation and Language 2023-12-05 v4 Artificial Intelligence

Abstract

Chat models, such as ChatGPT, have shown impressive capabilities and have been rapidly adopted across numerous domains. However, these models are only accessible through a restricted API, creating barriers for new research and progress in the field. We propose a pipeline that can automatically generate a high-quality multi-turn chat corpus by leveraging ChatGPT to engage in a conversation with itself. Subsequently, we employ parameter-efficient tuning to enhance LLaMA, an open-source large language model. The resulting model, named Baize, demonstrates good performance in multi-turn dialogues with guardrails that minimize potential risks. Furthermore, we propose a new technique called Self-Distill with Feedback, to further improve the performance of the Baize models with feedback from ChatGPT. The Baize models and data are released for research purposes only at https://github.com/project-baize/baize-chatbot. An online demo is also available at https://huggingface.co/spaces/project-baize/chat-with-baize.

Keywords

Cite

@article{arxiv.2304.01196,
  title  = {Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data},
  author = {Canwen Xu and Daya Guo and Nan Duan and Julian McAuley},
  journal= {arXiv preprint arXiv:2304.01196},
  year   = {2023}
}

Comments

Baize v2; EMNLP 2023

R2 v1 2026-06-28T09:47:22.919Z