Starred repositories
A minimal vectorized automatic differentiation engine for learning how backpropagation, broadcasting, and neural networks work under the hood.
Recreating PyTorch from scratch, using Numpy. Supports FCN, CNN, RNN layers.
A nano-sized autograd engine Implementing backpropagation. including neural net, loss functions and optimizers
Introduction to Machine Learning Systems
Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
An extremely fast Python package and project manager, written in Rust.
A pure Python HTML5 parser that just works. No C extensions to compile. No system dependencies to install. No complex API to learn.
A toy Python DL training library with PyTorch like API
Code samples for my book "Neural Networks and Deep Learning"
Source for the book Computer Science from Scratch
A TypeScript library for decoding and validating Vehicle Identification Numbers (VINs) using a customized VPIC database.
With awesome options like micrograd or tinygrad out there, why not write another small autodiff engine? Β―\_(γ)_/Β―
Minimal yet performant LLM examples in pure JAX
Small deep learning library written from scratch in Python, using NumPy/CuPy.
A collection of Space Invaders games built by different LLMs and coding agents
TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, PyTorch, and Hugging Face libraries.
π€π AI-powered toolkit for generating, editing, and publishing books. Create outlines, chapters, covers, and export EPUB/PDF ready for Amazon KDP. πβ‘οΈπ
Quick illustration of how one can easily read books together with LLMs. It's great and I highly recommend it.
A lightweight CLI Markdown editor with live preview.
Like Karpathy's micrograd but following JAX's functional style
Concatenate a directory full of files into a single prompt for use with LLMs
Render any git repo into a single static HTML page for humans or LLMs