QLoRA: Efficient Finetuning of Quantized LLMs

A guidance language for controlling large language models.

Solve puzzles. Learn CUDA.

Synthetic question-answering dataset to formally analyze the chain-of-thought output of large language models on a reasoning task.

Code for STaR: Bootstrapping Reasoning With Reasoning (NeurIPS 2022)

Aligning pretrained language models with instruction data generated by themselves.

Code and documentation to train Stanford's Alpaca models, and generate the data.

A tiny library for coding with large language models.

Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

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

Stable diffusion for real-time music generation

The KiloGram Tangrams dataset

A framework for few-shot evaluation of language models.

Infinite chains of captions and generations

Neovim's answer to the mouse 🦘

Drive a browser with GPT-3

A modular RL library to fine-tune language models to human preferences

Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference, and more.

Dataset of prompts, synthetic AI generated images, and aesthetic ratings.

A customisable 2D platform for agent-based AI research

Learning to Ground Multi-Agent Communication with Autoencoders [NeurIPS 2021]

Building Open-Ended Embodied Agents with Internet-Scale Knowledge

A suite of test scenarios for multi-agent reinforcement learning.

DALL·E Mini - Generate images from a text prompt

Probabilistic language based on pattern matching and constraint propagation, 153 examples

Repo for external large-scale work