🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.

A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

#1 Locally hosted web application that allows you to perform various operations on PDF files

Vision agent

从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)

从零实现一个小参数量中文大语言模型。

从0开始，将chatgpt的技术路线跑一遍。

🚀🚀 「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!

ONNX-compatible LightGlue: Local Feature Matching at Light Speed. Supports TensorRT, OpenVINO

RTMPose series (RTMPose, DWPose, RTMO, RTMW) without mmcv, mmpose, mmdet etc.

Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.

中国大模型

[CVPR 2023] DepGraph: Towards Any Structural Pruning

MediaPipeのPythonパッケージのサンプルです。2024/9/1時点でPython実装のある15機能について用意しています。

A toolbox for skeleton-based action recognition.

🔥🔥🔥 Use streamlit framework to increase yolov8 front-end page interaction function

yolort is a runtime stack for yolov5 on specialized accelerators such as tensorrt, libtorch, onnxruntime, tvm and ncnn.

Multi-camera live traffic and object counting with YOLO v4, Deep SORT, and Flask.

Real-time multi-camera multi-object tracker using YOLO varients

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

[CVPR 2025] You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale

Official Code for DragGAN (SIGGRAPH 2023)

More relighting!

Let us control diffusion models!

Official Repository for DenseMatcher Learning 3D Semantic Correspondence for Category-Level Manipulation from One Demo

[ICLR 2025] CatVTON is a simple and efficient virtual try-on diffusion model with 1) Lightweight Network (899.06M parameters totally), 2) Parameter-Efficient Training (49.57M parameters trainable) …