openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.

Interact with your documents using the power of GPT, 100% privately, no data leaks

The world's simplest facial recognition api for Python and the command line

Official inference framework for 1-bit LLMs

Let us control diffusion models!

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Prefect is a workflow orchestration framework for building resilient data pipelines in Python.

Automate browser based workflows with AI

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

Go ahead and axolotl questions

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audi…

An advanced memory forensics framework

Reverse Engineering: Decompiling Binary Code with Large Language Models

NVIDIA's Deep Imagination Team's PyTorch Library

Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch

A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF

RAG that intelligently adapts to your use case, data, and queries

Make images look as if they are made out of 1x1 LEGO blocks

a Python API for your car

Transform ML models into a native code (Java, C, Python, Go, JavaScript, Visual Basic, C#, R, PowerShell, PHP, Dart, Haskell, Ruby, F#, Rust) with zero dependencies

An unofficial client library for Google Music.

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

Pytorch implementation for few-shot photorealistic video-to-video translation.

first base model for full-duplex conversational audio

Open-Unmix - Music Source Separation for PyTorch

A decompiler with multiple backend support, written in Python. Works with IDA and Capstone.

Reimplementation of LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory