Awesome RLHF
A curated collection of datasets, models, Spaces, and papers on Reinforcement Learning from Human Feedback (RLHF).
Running173📊Note A multi-turn evaluation benchmark for chatbots which uses GPT-4 as a judge to evaluate the quality of responses.
garage-bAInd/Open-Platypus
Viewer • Updated • 24.9k • 8.37k • 363Note A high quality blend of human and synthetic datasets focused on dialogues and reasoning abilities. A good source for SFT and PPO.
meta-llama/Llama-2-7b-chat-hf
Text Generation • Updated • 709k • 3.85kNote The first series of open access models trained at scale using RLHF. Based on https://huggingface.co./papers/2307.09288
meta-llama/Llama-2-70b-chat-hf
Text Generation • Updated • 54.8k • 2.14kNote The first series of open access models trained at scale using RLHF. Based on https://huggingface.co./papers/2307.09288
lightonai/alfred-40b-0723
Text Generation • Updated • 9 • 45Note An RLHF tuned version of Falcon 40B
Anthropic/hh-rlhf
Viewer • Updated • 169k • 44.1k • 1.17kNote A dataset of dialogues between human annotators and a 52B parameter language model from Anthropic. Contains "helpfulness" and "harmlessness" subsets that can be used for training reward models. Basis for https://huggingface.co./papers/2112.00861 and https://huggingface.co./papers/2204.05862
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Paper • 2204.05862 • Published • 2A General Language Assistant as a Laboratory for Alignment
Paper • 2112.00861 • Published • 2stanfordnlp/SHP
Viewer • Updated • 386k • 1.01k • 289openai/summarize_from_feedback
Viewer • Updated • 194k • 3.06k • 181openai/webgpt_comparisons
Viewer • Updated • 19.6k • 705 • 221