Code for paper "Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent"

Hackable open-source version of Anthropic's AI Artifacts chat

Official codebase of Data Regularised Environment Design (ICML 2024)

The HTML5 Creation Engine: Create beautiful digital content with the fastest, most flexible 2D WebGL renderer.

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

Official code for TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations

A gym environment for PushT

Implementation of Bitune: Bidirectional Instruction-Tuning

Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.

Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy

PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning -- Distributed RL/IL code for Multi-Agent Path Finding (MAPF)

Sparse autoencoders

Convert Compute And Books Into Instruct-Tuning Datasets (or classifiers)!

Isaac Gym Reinforcement Learning Environments

[ICML 2024] 3D-VLA: A 3D Vision-Language-Action Generative World Model

MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

Open Source HTML5 Puzzle Game Engine

Generative cellular automaton-like learning environments for RL.