AlphaFold 3 inference pipeline.

A kernel library written in tilelang

A project implementing various agentic RL based on the Slime post-training framework

Give your agents the power of the Hugging Face ecosystem

Local 4B codebase explorer agent distilled from Qwen3-Coder-Next.

Code for "ConsistentChat: Building Skeleton-Guided Consistent Multi-Turn Dialogues for Large Language Models from Scratch", where dataset is publicly available at https://huggingface.co/datasets/ji…

Exploration of automated dataset selection approaches at large scales.

A small library of LLM judges

All insights extracted from relevant context engineering and memory papers

Training Transformers with knowledge localization (SGTM)

An open infrastructure to democratize and decentralize the development of superintelligence for humanity.

Provider-agnostic, open-source evaluation infrastructure for language models

The best ChatGPT that $100 can buy.

A concise, beginner-friendly introduction to the core ideas of linear algebra.

🐉 Loong: Synthesize Long CoTs at Scale through Verifiers.

Landing repository for the paper "Predicting the Order of Upcoming Tokens Improves Language Modeling"

The Amazon S3 Connector for PyTorch delivers high throughput for PyTorch training jobs that access and store data in Amazon S3.

Production-ready AI chat. Start here and make it your own. Formerly Sparka AI

RL environments + evals for AI agents. Define once, train anything.

Ultra-lightweight AI Agent

Autonomous coding agent as an SDK, IDE extension, or CLI assistant.

Build compute kernels and load them from the Hub.

Dion optimizer algorithm

Glamourous agentic coding for all 💘

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM