yichen2017

excalidraw

Virtual whiteboard for sketching hand-drawn like diagrams

milvus

A cloud-native vector database, storage for next generation AI applications

LLaMA-Factory

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

xgboost

Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow

Dive-into-DL-PyTorch

本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。

marker

Convert PDF to markdown quickly with high accuracy

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

ragflow

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

leedl-tutorial

《李宏毅深度学习教程》（李宏毅老师推荐👍），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases

metersphere

MeterSphere 是新一代的开源持续测试工具，让软件测试工作更简单、更高效，不再成为持续交付的瓶颈。

surya

OCR, layout analysis, reading order, line detection in 90+ languages

nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

pdfplumber

Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.

Lhy_Machine_Learning

李宏毅2021/2022/2023春季机器学习课程课件及作业

donut

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

sahi

Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

PDF-Extract-Kit

A Comprehensive Toolkit for High-Quality PDF Content Extraction

pdf2docx

Open source Python library for converting PDF to DOCX.

MuseTalk

MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting

Pix2Text

An Open-Source Python3 tool for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conversion of visual content into text-based representations. 80+ languages are supported.

meet-libai

​ 李白 :bust_in_silhouette: 作为唐代杰出诗人，其诗歌作品在**文学史上具有重要地位。近年来，随着数字技术和人工智能的快速发展，传统文化普及推广的形式也面临着创新与变革。国内外对于李白诗歌的研究虽已相当深入，但在数字化、智能化普及方面仍存在不足。因此，本项目旨在通过构建李白知识图谱，结合大模型训练出专业的AI智能体，以生成式对话应用的形式，推动李白文化的普及与推广。

AutoCoder

We introduced a new model designed for the Code generation task. Its test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024) and GPT-4o.

DocumentLayoutAnalysis

Document Layout Analysis resources repos for development with PdfPig.

haupt

Lineage metadata API, artifacts streams, sandbox, API, and spaces for Polyaxon

MegaParse

File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx, PPTx in a format that is ideal for LLMs.

PointTransformerV2

[NeurIPS'22] An official PyTorch implementation of PTv2.

document-ai-transformers

point2cad

Code for "Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds"

RapidStructure

版面分析 | 表格识别 | 文档方向分类

Docs2KG

Docs2KG: Unified Knowledge Graph Construction from Heterogeneous Documents Assisted by Large Language Models