CFBench: A Comprehensive Constraints-Following Benchmark for LLMs

The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization

A series of large language models developed by Baichuan Intelligent Technology

NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark

A 13B large language model developed by Baichuan Intelligent Technology

A large-scale 7B pretraining language model developed by BaiChuan-Inc.