/skills to route dexterous hand policies

SGLang is a high-performance serving framework for large language models and multimodal models.

Generate any location from the real world in Minecraft with a high level of detail.

Poker simulator and solver

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

A live stream development of RL tunning for LLM agents

Official implementation of paper: SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Official Repo for Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

Entropy Based Sampling and Parallel CoT Decoding

Estimating Body and Hand Motion in an Ego-sensed World

MOKA: Open-World Robotic Manipulation through Mark-based Visual Prompting (RSS 2024)

Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.

Train transformer language models with reinforcement learning.

An Extensible Deep Learning Library

The simplest, fastest repository for training/finetuning medium-sized GPTs.

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

LLM101n: Let's build a Storyteller

A simple library for scaling up JAX programs

Minimal but scalable implementation of large language models in JAX

A generative and self-guided robotic agent that endlessly propose and master new skills.

Grok open release

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

Code for CRATE (Coding RAte reduction TransformEr).