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

A simple screen parsing tool towards pure vision based GUI agent

A guidance language for controlling large language models.

Instruct-tune LLaMA on consumer hardware

A hands-on introduction to video technology: image, video, codec (av1, vp9, h265) and more (ffmpeg encoding). Translations: 🇺🇸 🇨🇳 🇯🇵 🇮🇹 🇰🇷 🇷🇺 🇧🇷 🇪🇸

llama3 implementation one matrix multiplication at a time

Foundational Models for State-of-the-Art Speech and Text Translation

Official inference library for Mistral models

Zero-Shot Speech Editing and Text-to-Speech in the Wild

A series of large language models trained from scratch by developers @01-ai

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion

A unified framework for 3D content generation.

Official Code for Stable Cascade

An Open Source text-to-speech system built by inverting Whisper.

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

Incredibly fast Whisper-large-v3

Vision utilities for web interaction agents 👀

General Assembly's 2015 Data Science course in Washington, DC

Concept Sliders for Precise Control of Diffusion Models

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

LLM verified with Monte Carlo Tree Search

Completely Hackable Amateur Radio Telescope

Ruby client for Chroma DB

Something in the middle of Karpathy's mingpt model and video lectures, BabyGPT is an easy to use model on a much smaller scale (16 and 256 out channels , 5 heads, fine tuned). To be made useful on …