Bo Liu

DeepSeek-VL: Towards Real-World Vision-Language Understanding

No description.

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

Natural Language Reinforcement Learning

NeurIPS-2022: A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning.

🐫 CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society

Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

No description.

:zap: Dynamically generated stats for your github readmes

Make Any Website & Tool Your CLI. A universal CLI Hub and AI-native runtime. Transform any website, Electron app, or local binary into a standardized command-line interface. Built for AI Agents to discover, learn, and execute tools seamlessly via a unified AGENT.md integration.

A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning

No description.

Wesbite for the Social Reinforcement Learning Lab at the University of Washington

Post-training with Tinker

Minimal and scalable research codebase in JAX, designed for rapid iteration on frontier research in LLM and other autoregressive models.

The best ChatGPT that $100 can buy.

A Gym for Generalist LLMs

FAIR Sequence Modeling Toolkit 2

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

The n-gram Language Model

LLM training in simple, raw C/CUDA

An elegant PyTorch deep reinforcement learning library.

No description.

Evals is a framework for evaluating OpenAI models and an open-source registry of benchmarks.

The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.

OpTree: Optimized PyTree

Multi-Joint dynamics with Contact. A general purpose physics simulator.

Code for Gym documentation website

NeurIPS-2021: Neural Auto-Curricula in Two-Player Zero-Sum Games.

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

NOOOOO_noFORK

哔哩哔哩 bilibili go-common

No description.