aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)

A multi-voice TTS system trained with an emphasis on quality

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

PyTorch code and models for the DINOv2 self-supervised learning method.

Solve puzzles. Learn CUDA.

QLoRA: Efficient Finetuning of Quantized LLMs

🤖 💬 Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)

Flax is a neural network library for JAX that is designed for flexibility.

NYU Deep Learning Spring 2020

Solve puzzles. Improve your pytorch.

Keras Implementation of Neural Style Transfer from the paper "A Neural Algorithm of Artistic Style" (http://arxiv.org/abs/1508.06576) in Keras 2.0+

Puzzles for learning Triton

Code, data, and instructions for mapping orbits of asteroids in the solar system

What would you do with 1000 H100s...

Fast, general, and tested differentiable structured prediction in PyTorch

A pedagogical implementation of Autograd

TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching

Minimal implementation of scalable rectified flow transformers, based on SD3's approach

100 exercises to learn JAX

Cleora AI is a general-purpose open-source model for efficient, scalable learning of stable and inductive entity embeddings for heterogeneous relational data. Created by Synerise.com team.

Animated GIF patterns made in Python Matplotlib.

Customized matrix multiplication kernels