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. The Baize models and data are released for research purposes only at https://github.com/project-baize/baize. An online demo is also available at https://huggingface.co/spaces/project-baize/baize-lora-7B.

翻译：摘要：聊天模型（如ChatGPT）已展现出卓越能力，并迅速被广泛应用于众多领域。然而，这些模型仅能通过受限的API访问，为该领域的新研究与进展设置了障碍。我们提出了一种流水线方法，通过利用ChatGPT进行自我对话，自动生成高质量的多轮对话语料库。随后，我们采用参数高效调优技术来增强LLaMA这一开源大语言模型。由此产生的模型名为Baize，在多轮对话中表现出良好性能，并具备最小化潜在风险的防护机制。Baize模型及数据仅用于研究目的，可通过https://github.com/project-baize/baize获取。在线演示也可在https://huggingface.co/spaces/project-baize/baize-lora-7B中使用。