Stars
Fully open reproduction of DeepSeek-R1
Crawlee—A web scraping and browser automation library for Python to build reliable crawlers. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Wo…
A framework for serving and evaluating LLM routers - save LLM costs without compromising quality
Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C.
Code for the EMNLP 2024 paper "Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps"
The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
RAGOnMedicalKG，将大模型RAG与KG结合，完成demo级问答，旨在给出基础的思路。
MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.
[ICLR 2025] Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision
Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks
DSPy: The framework for programming—not prompting—language models
Deploy your agentic worfklows to production
Code for Husky, an open-source language agent that solves complex, multi-step reasoning tasks. Husky v1 addresses numerical, tabular and knowledge-based reasoning tasks.
Official github repo for AutoDetect, an automated weakness detection framework for LLMs.
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.
Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & C…
A natural language interface for computers
A library for efficient similarity search and clustering of dense vectors.
Test your prompts, agents, and RAGs. Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with comma…
Doing simple retrieval from LLM models at various context lengths to measure accuracy
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
llama3 implementation one matrix multiplication at a time
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
Llama3、Llama3.1 中文后训练版仓库 - 微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档。