xcxhy

mPLUG-Owl

mPLUG-Owl: The Powerful Multi-modal Large Language Model Family

MindSearch

🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

Diffree

Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model

PDF-Guru

PDF Guru Anki是一款以PDF为中心的多功能办公学习工具箱软件，包含四大板块功能：PDF实用工具箱、Anki制卡神器、Anki最强辅助、视频笔记神器，软件功能众多且强大，熟练运用可以大幅提高办公和学习效率，绝对是您不可多得的效率神器。人生苦短，我用Guru!

yolov10

YOLOv10: Real-Time End-to-End Object Detection

YOLOv10-Document-Layout-Analysis

YOLOv10 trained on DocLayNet dataset.

PaddleDetection

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

tesseract

Tesseract Open Source OCR Engine (main repository)

AdvancedLiterateMachinery

A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.

DUP-ocropy

Python-based tools for document analysis and OCR

doctr

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

websockets

Library for building WebSocket servers and clients in Python

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

deepdoctection

A Repo For Document AI

MiniCPM-V

MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

unsloth

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

xtuner

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

PosterLLaVA

reader

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

llama_parse

Parse files for optimal RAG

llmsherpa

Developer APIs to Accelerate LLM Projects

Lumix

Pre-Processing data before pre-train and sft

corenet

CoreNet: A library for training deep neural networks

pdfcrowd-python

A Python client library for the Pdfcrowd HTML to PDF API

YOLOS

[NeurIPS 2021] You Only Look at One Sequence

donut

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

moondream

tiny vision language model

OmniFusion

OmniFusion — a multimodal model to communicate using text and images

InternLM-XComposer

InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output