A trainable PyTorch reproduction of AlphaFold 3.

Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

Official Repository for the Uni-Mol Series Methods

GoldFinch and other hybrid transformer components

MLX inference for ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

Fast modular code to create and train cutting edge LLMs

An open-source platform for developing protein models beyond AlphaFold.

A collection of memory efficient attention operators implemented in the Triton language.

an efficient distributed PyTorch framework

RWKV centralised docs for the community

Uni-Dock: a GPU-accelerated molecular docking program

ChemNLP project

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

INT4 and FP16 inference on CPU for RWKV language model

Hypermodern Python Cookiecutter

Deep learning operations reinvented (for pytorch, tensorflow, jax and others)

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

Implementation of the Equiformer, SE3/E3 equivariant attention network that reaches new SOTA, and adopted for use by EquiFold for protein folding

Python-centric Cookiecutter for Molecular Computational Chemistry Packages

📜 Collection of the most awesome Math learning resources in the form of notes, videos and cheatsheets.

Implementation of E(n)-Transformer, which extends the ideas of Welling's E(n)-Equivariant Graph Neural Network to attention

Open source code for AlphaFold.