-
Tsinghua University
- Beijing, China
Stars
Eclipse SUMO is an open source, highly portable, microscopic and continuous traffic simulation package designed to handle large networks. It allows for intermodal simulation including pedestrians a…
SuperSonic is the next-generation BI AI platform that unifies Chat BI (powered by LLM) and Headless BI (powered by semantic layer) paradigms.
A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具,支持PDF/网页/多格式电子书提取。
The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
A modular graph-based Retrieval-Augmented Generation (RAG) system
Start building LLM-empowered multi-agent applications in an easier way.
Provide best practices for LMOps, as well as elegant and convenient access to the features of the Qianfan MaaS Platform. (提供大模型工具链最佳实践,以及优雅且便捷地访问千帆大模型平台)
A lightweight, fast, and secure code execution environment that supports multiple programming languages
📰 Must-read papers and blogs on Speculative Decoding ⚡️
Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of …
ModelScope-Agent: An agent framework connecting models in ModelScope with the world
Question and Answer based on Anything.
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]
🔎 A deep-dive into HyDE for Advanced LLM RAG 💡 Introducing AutoHyDE, a semi-supervised framework to improve the effectiveness, coverage and applicability of HyDE
Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.
FinGLM: 致力于构建一个开放的、公益的、持久的金融大模型项目,利用开源开放来促进「AI 金融」。
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…
A curated, but incomplete, list of data-centric AI resources.
ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]
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。
Summarize existing representative LLMs text datasets.
DSIR large-scale data selection framework for language model training
Parkar and Kim et al.'s paper on :SelectLLM: Can LLMs Select Important Instructions to Annotate?"
Code and data for CoachLM, an automatic instruction revision approach LLM instruction tuning.