Data and models for the paper "Configurable Safety Tuning of Language Models with Synthetic Preference Data"

distilled Self-Critique refines the outputs of a LLM with only synthetic data

API for the GPT-J language model 🦜. Including a FastAPI backend and a streamlit frontend

ZYN: Zero-Shot Reward Models with Yes-No Questions

Personalization for Stable Diffusion via Aesthetic Gradients 🎨