This project includes the project files for our quadruped robot simulation. We used ADAMS to simulate a quadruped locomotion

Open-source, community-driven agent harness

The agent that grows with you

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

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

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

FinRL®: Financial Reinforcement Learning. 🔥

This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

FinRL®: Financial Reinforcement Learning. 🔥

中文nlp解决方案(大模型、数据、模型、训练、推理)

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

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

State-of-the-art 2D and 3D Face Analysis Project

每日分享免费节点、免费机场、ssr节点、v2ray节点、v2ray订阅、clash节点、clash订阅、shadowrocket订阅、Quantumult X订阅、Clash .NET订阅、小火箭节点、小猫咪节点、免费翻墙、免费科学上网、免费梯子、免费trojan节点、蓝灯、谷歌商店、翻墙梯子、安卓VPN、iphone翻墙节点、iphone vpn、一键翻墙浏览器、节点分享、免费SSR、蓝灯…

deep learning for image processing including classification and object-detection etc.

A PyTorch implementation of EfficientNet

Reference models and tools for Cloud TPUs.

Official code and checkpoint release for mobile robot foundation models: GNM, ViNT, and NoMaD.

Official code and checkpoint release for "GNM: A General Navigation Model to Drive Any Robot".

A simulation platform for versatile Embodied AI research and developments.

This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)

从零实现一个小参数量中文大语言模型。

从0开始，将chatgpt的技术路线跑一遍。

用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调，给出三元组信息抽取微调示例。

🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

Height Control and Optimal Torque Planning for Jumping with Wheeled-Bipedal Robots

An OpenAI Gym style reinforcement learning interface for Agility Robotics' biped robot Cassie