本项目旨在分享大模型相关技术原理以及实战经验。

The official GitHub page for the survey paper "A Survey of Large Language Models".

Fine-tuning LLaMA with PEFT (PT+SFT+RLHF with QLoRA)

Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

Making large AI models cheaper, faster and more accessible

Code and documentation to train Stanford's Alpaca models, and generate the data.

NLP超强入门指南，包括各任务sota模型汇总（文本分类、文本匹配、序列标注、文本生成、语言模型），以及代码、技巧

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

Open Source, Distributed, RESTful Search Engine

Detectron2 for Document Layout Analysis

Style and Grammar Checker for 25+ Languages

A Python Library for Document Layout Understanding

Natural Language Processing Tutorial for Deep Learning Researchers

This repository lets you train neural networks models for performing end-to-end full-page handwriting recognition using the Apache MXNet deep learning frameworks on the IAM Dataset.

Recognize tables from images and restore them into word.

Free Offline OCR 离线的中文文本检测+识别SDK

Datasets, Transforms and Models specific to Computer Vision

text detection mainly based on ctpn model in tensorflow, id card detect, connectionist text proposal network

Tesseract Open Source OCR Engine (main repository)

超轻量级中文ocr，支持竖排文字识别, 支持ncnn推理 , psenet(8.5M) + crnn(6.3M) + anglenet(1.5M) 总模型仅17M

公式图片ocr，输入图片输出对应的latex表达式

Math formula recognition (Images to LaTeX strings)

A Python library to extract tabular data from PDFs

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

搜索所有中文NLP数据集，附常用英文NLP数据集

🎨 数学公式识别增强版：中英文手写印刷公式、支持初级符号推导（数据结构基于 LaTeX 抽象语法树）

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

Deep-learning by using TensorFlow. Basic nns like Logistic, CNN, RNN, LSTM and some examples are implemented by complex model.

✨Fast Coreference Resolution in spaCy with Neural Networks

event coreference resolution using mention-pair model and correlation clustering