D2 is a modern diagram scripting language that turns text to diagrams.

A monitor of resources

A syntax-highlighting pager for git, diff, grep, and blame output

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Unbearably fast near-real-time pure-Python runtime-static type-checker.

Code for the paper 🌳 Tree Search for Language Model Agents

Perplexica is an AI-powered answering engine. It is an Open source alternative to Perplexity AI

LLM inference in C/C++

The Modular Platform (includes MAX & Mojo)

The official PyTorch implementation of Google's Gemma models

An interactive structure/property explorer for materials and molecules

FAIR Chemistry's library of machine learning methods for chemistry

📝 Today I Learned

Inference code for Llama models

Workflow for creating and analyzing the Open Catalyst Dataset

[ICLR 2024] EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations

A book on modeling materials using VASP, ase and vasp

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Code for training embodied agents using IL and RL finetuning at scale for ObjectNav

Differentiable scientific computing library

Differentiable Quantum Chemistry (only Differentiable Density Functional Theory and Hartree Fock at the moment)

Tensors, for human consumption

jax library for E3 Equivariant Neural Networks

Fast, correct Python JSON library supporting dataclasses, datetimes, and numpy

The Fast Cross-Platform Package Manager

Code for training embodied agents using imitation learning at scale in Habitat-Lab

Graphormer is a general-purpose deep learning backbone for molecular modeling.

A modular framework for neural networks with Euclidean symmetry

Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"