Stars
This package contains the original 2012 AlexNet code.
llama3 implementation one matrix multiplication at a time
🚀 Efficient implementations of state-of-the-art linear attention models in Torch and Triton
A JAX research toolkit for building, editing, and visualizing neural networks.
Various Python Simulations
Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
An interactive exploration of Transformer programming.
Solve puzzles. Improve your pytorch.
Latex code for making neural networks diagrams