Starred repositories
First dynamic frontend library based on AI components 🚀
A simple, performant and scalable Jax LLM!
🐉 Loong: Synthesize Long CoTs at Scale through Verifiers.
An alignment auditing agent capable of quickly exploring alignment hypothesis
[NeurIPS 2025] The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
PyTorch implementation of Audio Flamingo: Series of Advanced Audio Understanding Language Models
PhD/MBA-level human-annotated rubrics dataset across Physics, Chemistry, Finance and Consulting
Post-training with Tinker
Super basic implementation (gist-like) of RLMs with REPL environments.
nbgradio converts Jupyter notebooks with gradio code into static websites with live gradio apps!
A scalable asynchronous reinforcement learning implementation with in-flight weight updates.
Provider-agnostic, open-source evaluation infrastructure for language models
Inspect: A framework for large language model evaluations
Collection of evals for Inspect AI
Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!
A Python package that makes it easy for developers to create AI apps powered by various AI providers.
Collection of scripts and notebooks for OpenAI's latest GPT OSS models
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Renderer for the harmony response format to be used with gpt-oss
Fast and accurate systemic data extraction with LLM assistance
Communicate with an LLM provider using a single interface
A powerful tool for creating datasets for LLM fine-tuning and RAG
A powerful AI coding agent. Built for the terminal.
Kimi K2 is the large language model series developed by Moonshot AI team
A course on building and sharing AI datasets