Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.5, DeepSeek, gpt-oss locally.

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Python bindings for llama.cpp

PyTorch code and models for VJEPA2 self-supervised learning from video.

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

g2o: A General Framework for Graph Optimization

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Code and dataset for photorealistic Codec Avatars driven from audio

A framework to enable multimodal models to operate a computer.

A high-throughput and memory-efficient inference and serving engine for LLMs

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

(CVPR 2023) NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior

StarCraft II Client - protocol definitions used to communicate with StarCraft II.

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

Fast and memory-efficient exact attention

StarCraft II Learning Environment

♞ lichess.org: the forever free, adless and open source chess server ♞

The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."

Rembg is a tool to remove images background

Official implementation of the CVPR 2022 Paper "Neural RGB-D Surface Reconstruction"

Repo for external large-scale work

A multi-voice TTS system trained with an emphasis on quality

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

Qiskit is an open-source SDK for working with quantum computers at the level of circuits, algorithms, and application modules.

Build Applications for Single-Use Devices

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Emscripten: An LLVM-to-WebAssembly Compiler

Unofficial implementation of 'Implicit Neural Representations with Periodic Activation Functions'

A pipeline to reconstruct 3d meshes based on Neural Radiance Fields