There are 2 repositories under human-feedback topic.
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
A curated list of reinforcement learning with human feedback resources (continually updated)
Open-source pre-training implementation of Google's LaMDA in PyTorch. Adding RLHF similar to ChatGPT.
Implementation of Reinforcement Learning from Human Feedback (RLHF)
The first user analytics platform for AI models
BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).
[ NeurIPS 2023 ] Official Codebase for "Aligning Synthetic Medical Images with Clinical Knowledge using Human Feedback"
Reinforcement Learning from Human Feedback with 🤗 TRL
A curated list of reinforcement learning with human feedback resources[awesome-RLHF-Turkish] (continually updated)