Stars
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.
Task driven LLM multi agent framework that gives you the building blocks to create anything you wish
All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.
✨ 易上手的多平台 LLM 聊天机器人及开发框架 ✨ 平台支持 QQ、QQ频道、Telegram、微信、企微、飞书 | MCP 服务器、OpenAI、DeepSeek、Gemini、硅基流动、月之暗面、Ollama、OneAPI、Dify 等。附带 WebUI。
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
The most no-nonsense, locally or API-hosted AI code completion plugin for Visual Studio Code - like GitHub Copilot but 100% free.
Digital Human Resource: 2D/3D/4D Human Modeling, Avatar Generation & Animation, Clothed People Digitalization, Virtual Try-On, and Others.
Real time interactive streaming digital human
[NeurIPS 2024] Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources
Moxin is a family of fully open-source and reproducible LLMs
This is the repo for the paper "PANGEA: A FULLY OPEN MULTILINGUAL MULTIMODAL LLM FOR 39 LANGUAGES"
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
The Simple Config Template Of Rime By Mintimate. QQ Chat-Group: 703260572
Fully open data curation for reasoning models
ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。
No fortress, purely open ground. OpenManus is Coming.
A simple screen parsing tool towards pure vision based GUI agent
A real-time collaborative code editor featuring unique room generation, syntax highlighting, and auto-suggestions. Users can seamlessly edit, save, and download files while communicating through gr…
Janus-Series: Unified Multimodal Understanding and Generation Models
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
DeepEP: an efficient expert-parallel communication library
FlashMLA: Efficient MLA decoding kernels