rlhf

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

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

Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-176B/bloom/gpt/bart/T5/MetaICL)

A collection of papers and resources related to Large Language Models.

Implementation of Reinforcement Learning from Human Feedback (RLHF)

Code accompanying the paper Pretraining Language Models with Human Preferences

Preference Transformer: Modeling Human Preferences using Transformers for RL (ICLR2023 Accepted)

Library of Environments, Human Actor UIs and Agent implementation for Human In the Loop Learning & Reinforcement Learning

A Practical Guide to Developing a Reliable FAQ Chatbot with Reinforcement Learning and Human Feedback using GPT-2 on AWS

The open source implementation of chatgpt and RLHF. 从0开始实现一个ChatGPT.

Zero-Shot Reward Models with the trlx library

LLaMA-TRL: Fine-tuning LLaMA with PPO and LoRA

Create your own ChatGPT with Python

Implementations of Baseline Methods for Aligning Text2Img Diffusion Models with Human FeedBack

The open source implementation of chatgpt and RLHF. ChaGPT 的开源平替解决方案

EasyRLHF aims to providing an easy and minimal interface to train RLHF LMs, using off-the-shelf solutions and datasets

Researching the reinforcement learning algorithm of ChatGPT