Generative Judge for Evaluating Alignment

Example models using DeepSpeed

A curated list of reinforcement learning with human feedback resources (continually updated)

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Fastest & best convert qmc 2 mp3 | flac tools

原神抽卡概率分析工具包 - Genshin Impact Gacha Analysis Tool Kit