Baize is an open-source chat model trained with LoRA, which improves upon the open-source large-scale language model LLaMA by fine-tuning LLaMA with a newly generated chat corpus, which runs on a single GPU, making it available to a wider range of researchers .

Bai Ze currently includes four models in English: Bai Ze-7B, 13B, and 30B (generic dialogue model), and a vertical domain Bai Ze-Medical model for research/non-commercial use, and plans to release Chinese Bai Ze in the future Ze model.

All the codes of Bai Ze’s data processing, training model, and Demo have been open sourced.