An unnecessarily tiny implementation of GPT-2 in NumPy.

Structured Outputs

Fully open reproduction of DeepSeek-R1

Molecular dynamics simulations with an LLM agent

Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

AlphaFold 3 inference pipeline.

AI-powered ab initio biomolecular dynamics simulation

Code for the paper "Resource-efficient quantum algorithm for protein folding"

Deploy a solution to research on drug discovery problems using quantum computing and classical computing resources.

Bio-Computing Platform Featuring Large-Scale Representation Learning and Multi-Task Deep Learning “螺旋桨”生物计算工具集

This repository contains implementations and illustrative code to accompany DeepMind publications

Jupyter Notebooks for learning the PyRosetta platform for biomolecular structure prediction and design

A generative model for programmable protein design

Protein structure diffusion model for unconditional protein generation and motif scaffolding

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Attention is all you need implementation

Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/TPU/CPU.

Diffusion models of protein structure; trigonometry and attention are all you need!

Implementation of the paper "Denoising Diffusion Probabilistic Models" in PyTorch

Short tutorials on the use of machine learning methods for causal inference