- hangzhou
- http://www.wmtcore.com
Stars
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts,用于评估和提升大模型的安全性。
A high-throughput and memory-efficient inference and serving engine for LLMs
🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.
Production-ready platform for agentic workflow development.
Netease Youdao's open-source embedding and reranker models for RAG products.
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.
Start building LLM-empowered multi-agent applications in an easier way.
Question and Answer based on Anything.
Retrieval and Retrieval-augmented LLMs
「Java学习+面试指南」一份涵盖大部分 Java 程序员所需要掌握的核心知识。准备 Java 面试,首选 JavaGuide!
🦜🔗 Build context-aware reasoning applications
Next generation of automated data exploratory analysis and visualization platform.
Stable Diffusion web UI
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.
A latent text-to-image diffusion model
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
A modular geospatial engine written in JavaScript and TypeScript
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。
Enterprise job scheduling middleware with distributed computing ability.
Netty project - an event-driven asynchronous network application framework
A modern replacement for Redis and Memcached