An experiment to see if an LLM trained from scratch on text prior to 1900 can come up with quantum mechanics and relativity.

AI agents running research on single-GPU nanochat training automatically

A code to generate atomic structure with symmetry

NeuralGCM's differentiable dycore

basic python module for gnss analysis

Computational abilities and efficiency of neural networks

could we make an ml stack in 100,000 lines of code?

A minimal GPU design in Verilog to learn how GPUs work from the ground up

From the Transistor to the Web Browser, a rough outline for a 12 week course

OpenTTD - http://www.openttd.org/ - with additional patches

yet another network load monitor

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

Official code for STARCOP: Semantic Segmentation of Methane Plumes with Hyperspectral Machine Learning models 🌈🛰️

AlphaFold 3 inference pipeline.

Refresher Material for DS ML Fundamental Concepts

Classical equations and diagrams in machine learning

The guide to online assessments and interviews

Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!

Inference code for Llama models

A comprehensive 10-page probability cheatsheet that covers a semester's worth of introduction to probability.

Extended pickling support for Python objects

Software developer resume in Latex

NanoGPT (124M) in 2 minutes

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

dSGP4: differentiable SGP4. Supports differentiability, ML integration & embarassingly parallel computations

RAD Expansion Unit for C64/C128

Style guides for Google-originated open-source projects