Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

A latent text-to-image diffusion model

Python programs, usually short, of considerable difficulty, to perfect particular skills.

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…

Neural Networks: Zero to Hero

Instruct-tune LLaMA on consumer hardware

Kolmogorov Arnold Networks

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

Natural Language Processing Tutorial for Deep Learning Researchers

Official inference library for Mistral models

A collection of pre-trained, state-of-the-art models in the ONNX format

Python implementation of algorithms from Russell And Norvig's "Artificial Intelligence - A Modern Approach"

this repository accompanies the book "Grokking Deep Learning"

Silero Models: pre-trained text-to-speech models made embarrassingly simple

Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.

Think DSP: Digital Signal Processing in Python, by Allen B. Downey.

A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more

Tutorials for creating and using ONNX models

An interactive book on deep learning. Much easy, so MXNet. Wow. [Straight Dope is growing up] ---> Much of this content has been incorporated into the new Dive into Deep Learning Book available at …

An educational software system of a tiny self-compiling C compiler, a tiny self-executing RISC-V emulator, and a tiny self-hosting RISC-V hypervisor.

Chess reinforcement learning by AlphaGo Zero methods.

The official code repository for the second edition of the O'Reilly book Generative Deep Learning: Teaching Machines to Paint, Write, Compose and Play.

Some ipython notebooks implementing AI algorithms

Supporting code for short YouTube series Neural Networks Demystified.

Tools to train a generative model on arbitrary audio samples

Utility functions for handling MIDI data in a nice/intuitive way.

Efficient Deep Learning Systems course materials (HSE, YSDA)

TruthfulQA: Measuring How Models Imitate Human Falsehoods

From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)

Reproducing Yann LeCun 1989 paper "Backpropagation Applied to Handwritten Zip Code Recognition", to my knowledge the earliest real-world application of a neural net trained with backpropagation.