Stars
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!
🚀 The fast, Pythonic way to build MCP servers and clients
分享 GitHub 上有趣、入门级的开源项目。Share interesting, entry-level open source projects on GitHub.
《SGT: A Generalized Processing Model for 1-D Remote Sensing Signal Classification》
🪄 Create rich visualizations with AI
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Document (PDF, Word, PPTX ...) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents. Remove PII. Convert any document or picture to structured …
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
The main repository for building Pascal-compatible versions of ML applications and libraries.
Streamlit — A faster way to build and share data apps.
An extremely fast Python package and project manager, written in Rust.
LlamaIndex is the leading framework for building LLM-powered agents over your data.
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
A modular graph-based Retrieval-Augmented Generation (RAG) system
A web-based tool for visualizing and exploring artifacts from Microsoft's GraphRAG.
A self-supervised method for feature extraction from audio.
A lightweight library for portable low-level GPU computation using WebGPU.
Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks
airda(Air Data Agent)是面向数据分析的多智能体，能够理解数据开发和数据分析需求、理解数据、生成面向数据查询、数据可视化、机器学习等任务的SQL和Python代码
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents
An Open-source Neural Hierarchical Multi-label Text Classification Toolkit
This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型