Stars
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Training a transformer to generate cursive handwriting
A Python script that converts boolean expressions to flowcharts or directed acyclic graphs.
Code for our paper "Hamiltonian Neural Networks"
A scientific instrument for investigating latent spaces
A 1D analogue of the MNIST dataset for measuring spatial biases and answering Science of Deep Learning questions.
Nature's Cost Function (NCF). Finding paths of least action with gradient descent.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
A latent text-to-image diffusion model
A distributed key value store in under 1000 lines. Used in production at comma.ai
You like pytorch? You like micrograd? You love tinygrad! ❤️
An autoregressive character-level language model for making more things
The self-made software package I used to make my blog. Feel free to use it!
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Extended experiments of "Growing Neural Cellular Automata" https://distill.pub/2020/growing-ca/
PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations
Flax is a neural network library for JAX that is designed for flexibility.
Neural reparameterization improves structural optimization
Differentiable, Hardware Accelerated, Molecular Dynamics
Moore Machine Networks (MMN): Learning Finite-State Representations of Recurrent Policy Networks
an implementation of Deep Image Prior using tensorflow
The Paths Perspective on Value Learning
A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.