Hierarchical Reasoning Model Official Release

An Infinitely Large Napkin

Gemma open-weight LLM library, from Google DeepMind

Run PyTorch in JAX. 🤝

LLaMA implementation with Jax and Equinox

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Mastering Diverse Domains through World Models

Named Tensors for Legible Deep Learning in JAX

The ultimate list of which programs support Vim-like keybindings natively, or how they can be added with extensions. A collaborative project.

Algorithms for solving temporal planning problems

Rust bindings for ROS 2

The Fast Downward domain-independent classical planning system

Large language models for PDDL domains

Official inference library for Mistral models

Simple code for generating a color-coded latex table from raw data

PIPs++

a distributed Hyperband implementation on Steroids

A. Cropper, R. Evans, and M. Law. Inductive general game playing. Machine learning, 2019.

Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax

ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

Instant-ngp in pytorch+cuda trained with pytorch-lightning (high quality with high speed, with only few lines of legible code)

NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning

Lark is a parsing toolkit for Python, built with a focus on ergonomics, performance and modularity.

A Declarative Language for Expressing Partial World Knowledge to Reinforcement Learning Agents

Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.

A project that provides help for using DeepMind's mctx on gym-style environments.