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

Focus on prompting and generating

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

🤗 smolagents: a barebones library for agents that think in code.

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

Devika is the first open-source implementation of an Agentic Software Engineer. Initially started as an open-source alternative to Devin.

Train transformer language models with reinforcement learning.

Automated Penetration Testing Agentic Framework Powered by Large Language Models

SD.Next: All-in-one WebUI for AI generative image and video creation, captioning and processing

Model parallel transformers in JAX and Haiku

Auto detecting, masking and inpainting with detection model.

[WIP] Layer Diffusion for WebUI (via Forge)

Create randomly insecure VMs

Control Any Computer Using LLMs.

Minimalistic large language model 3D-parallelism training

AsyncSSH is a Python package which provides an asynchronous client and server implementation of the SSHv2 protocol on top of the Python asyncio framework.

Implementation of Alphafold 3 from Google Deepmind in Pytorch

Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)

ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

Official code and checkpoint release for mobile robot foundation models: GNM, ViNT, and NoMaD.

Helping Ethical Hackers use LLMs in 50 Lines of Code or less..

Implementation of Muse: Text-to-Image Generation via Masked Generative Transformers, in Pytorch

Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch

A microframework on top of PyTorch with first-class citizen APIs for foundation model adaptation

A fully open source biomolecular structure prediction model based on AlphaFold3

Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-176B/bloom/gpt/bart/T5/MetaICL)

D-Adaptation for SGD, Adam and AdaGrad

Open reproduction of MUSE for fast text2image generation.

Symbolic Music Generation with Diffusion Models