A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.

Unified Structure Generation for Universal Information Extraction

TPlinker for NER 中文/英文命名实体识别

This is the official implementation to the EMNLP 2024 paper: Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding.

This is an unofficial implementation to the EMNLP 2023 paper: Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction

[MM'2024] PEneo, an effective algorithm for key-value pair extraction from form-like documents, designed for real-world applications.

A toolbox of ocr models and algorithms based on MindSpore

使用torch整合两种经典的指针NER抽取范式，分别是SpanBert和苏神的GlobalPointer，简单加了些tricks，配置后一键运行

CMeIE/CBLUE/CHIP/实体关系抽取/SPO抽取

Official PyTorch implementation of "ML-Decoder: Scalable and Versatile Classification Head" (2021)

Mac软件清单、Mac使用技巧整理，正在不断完善中。努力做到最全。

🐙 关于提示词工程（prompt）的指南、论文、讲座、笔记本和资源大全（自动持续更新）

✨✨Latest Advances on Multimodal Large Language Models

Official implementation for "Automatic Chain of Thought Prompting in Large Language Models" (stay tuned & more will be updated)

This repo includes ChatGPT prompt curation to use ChatGPT and other LLM tools better.

面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

The official repo for “TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding”.

PaddleOCR 输出结果的行对齐，表格制式图像OCR行对齐

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…

Related work with Graph neural networks

This repo provides Geometric LayoutLM for Vietnamese document and code for export to ONNX

This is the official repository of the EMNLP 2023 paper Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction.

Pytorch Implementation of Value Retrieval with Arbitrary Queries for Form-like Documents.

Doc2Graph transforms documents into graphs and exploit a GNN to solve several tasks.