Lists (1)
Starred repositories
A JAX research toolkit for building, editing, and visualizing neural networks.
Real-Time Detection of Hallucinated Entities in Long-Form Generation
Implementation for FP8/INT8 Rollout for RL training without performence drop.
slime is an LLM post-training framework for RL Scaling.
The evaluation framework for training-free sparse attention in LLMs
Customized Inference Engine for Multiverse Models
Storing long contexts in tiny caches with self-study
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
A fast GPU memory copy library based on NVIDIA GPUDirect RDMA technology
The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.
SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
Inverse Constitutional AI [ICLR 2025]: compressing pairwise preference data into a short constitution of principles.
Agent S: an open agentic framework that uses computers like a human
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / verl / LLaMA Factory / ms-swift / U…
🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about infrastructure.
🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"
LeanUniverse: A Library for Consistent and Scalable Lean4 Dataset Management
🌎💪 BrowserGym, a Gym environment for web task automation
open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.
Industry leading face manipulation platform
A coding agent for open models like Kimi K3
browse the modern web on vintage computers
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.