BELLE

The goal of this project is to promote the development of the open source community for Chinese dialogue big models, with the vision of becoming an LLM Engine that can help everyone.

Compared to how to do well in pre training of large language models, BELLE focuses more on how to help everyone obtain their own language model with the best possible instruction expression ability on the basis of open-source pre training of large language models, and reduce the research and application threshold of large language models, especially Chinese large language models. To this end, the BELLE project will continue to open up instruction training data, related models, training code, application scenarios, etc., and will also continuously evaluate the impact of different training data, training algorithms, etc. on model performance. BELLE has been optimized for Chinese, and model tuning only uses data produced by ChatGPT (excluding any other data).