#
gaojing8500
Follow
Starred repositories
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
Knowledge Table is an open-source package designed to simplify extracting and exploring structured data from unstructured documents.
🧑🚀 全世界最好的LLM资料总结（数据处理、模型训练、模型部署、o1 模型、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.
A bibliography and survey of the papers surrounding o1
Chat with your documents using Vision Language Models. This repo implements an End to End RAG pipeline with both local and proprietary VLMs
DSPy: The framework for programming—not prompting—language models
Turns Data and AI algorithms into production-ready web applications in no time.
A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The …
An opensource AI & model as a service platform.
Neo4j graph construction from unstructured data using LLMs
A modular graph-based Retrieval-Augmented Generation (RAG) system
Turn any glasses into AI-powered smart glasses
MinHash, LSH, LSH Forest, Weighted MinHash, HyperLogLog, HyperLogLog++, LSH Ensemble and HNSW
Efficient visual programming for AI language models
This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)
A generative speech model for daily dialogue.
⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)
End-to-end stack for WebRTC. SFU media server and SDKs.
Vision utilities for web interaction agents 👀
llama3 implementation one matrix multiplication at a time
Llama-3 agents that can browse the web by following instructions and talking to you
GeoSpy is an OSINT analysis and research tool, which allows people to track and execute intelligent social engineering attacks in real time. It was created with the aim of teaching the world how la…
Friends don't let friends make certain types of data visualization - What are they and why are they bad.
A minimal GPU design in Verilog to learn how GPUs work from the ground up
LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath
A fast inference library for running LLMs locally on modern consumer-class GPUs