karpathy

AI agents running research on single-GPU nanochat training automatically

The simplest, fastest repository for training/finetuning medium-sized GPTs.

The best ChatGPT that $100 can buy.

LLM101n: Let's build a Storyteller

LLM training in simple, raw C/CUDA

LLM Council works together to answer your hardest questions

Neural Networks: Zero to Hero

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Inference Llama 2 in one file of pure C

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

Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch

Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Web interface for browsing, search and filtering recent arxiv submissions

Video+code lecture on building nanoGPT from scratch

Efficient Image Captioning code in Torch, runs on GPU

NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.

An autoregressive character-level language model for making more things

Quick illustration of how one can easily read books together with LLMs. It's great and I highly recommend it.

Render any git repo into a single static HTML page for humans or LLMs

A research tool for visually exploring Bureau of Labor Statistics Occupational Outlook Handbook data. This is not a report, a paper, or a serious economic publication — it is a development tool...

my blog

Pure Python from-scratch zero-dependency implementation of Bitcoin for educational purposes

arxiv-sanity lite: tag arxiv papers of interest get recommendations of similar papers in a nice UI using SVMs over tfidf feature vectors based on paper abstracts.

Reinforcement Learning Agents in Javascript (Dynamic Programming, Temporal Difference, Deep Q-Learning, Stochastic/Deterministic Policy Gradients)

Notebooks and various random fun

Automatically collect and visualize usage statistics in Ubuntu/OSX environments.

Deep Recurrent Neural Networks and LSTMs in Javascript. More generally also arbitrary expression graphs with automatic differentiation.

Normalizing flows in PyTorch. Current intended use is education not production.

Implementation of t-SNE visualization algorithm in Javascript.

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.

Random notes on papers, likely a short-term repo.

Support Vector Machine in Javascript (SMO algorithm, supports arbitrary kernels) + GUI demo

Analyzing Hacker News discussions from a decade ago in hindsight with LLMs

VQVAEs, GumbelSoftmaxes and friends

MADE (Masked Autoencoder Density Estimation) implementation in PyTorch

The missing tiktoken training code

Automating research publications discovery and analysis. For example, ever wish your computer could automatically open papers that are most similar to a paper at an arbitrary url? How about...

Aspires to help the influx of bioRxiv / medRxiv papers on COVID-19

Find people you should follow on Twitter based on who the people you follow follow

Random Forest implementation for JavaScript. Supports arbitrary weak learners. Includes interactive demo.

An Academic Papers Management and Discovery System

A Random Forest implementation for MATLAB. Supports arbitrary weak learners that you can define.

root repo

Scripts that generate .html to more easily see NIPS papers

nice and effective super simple calorie counter web app

A lightweight/pretty visualizer for recent work on a git code base in multiple branches. Helps stay up to date with teams working on one git repo in many branches.

tensorflow reinforcement learning agents for OpenAI gym environments

Game making library for using Canvas element

A wrapper for LibSVM that lets you train SVM's directly on Eigen library matrices in C++

A set of tools/pages that help explore academic literature

useful scripts to work with Twitter + Python. Requires the tweepy library.

C++ convenience class to communicate with a Matlab instance. Send matrices back and forth, execute arbitrary Matlab commands, or drop into interactive Matlab session right in the middle of your...