BroadJJ

mwp_kr

AGC 5차 대회 소스 코드 저장소입니다.

DB

A PyTorch implementation of "Real-time Scene Text Detection with Differentiable Binarization".

synthtiger

Official Implementation of SynthTIGER (Synthetic Text Image Generator), ICDAR 2021

ColossalAI

Making large AI models cheaper, faster and more accessible

stanford_alpaca

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

WeeklyArxivTalk

[Zoom & Facebook Live] Weekly AI Arxiv 시즌2

llama

Inference code for Llama models

FlexGen

Running large language models on a single GPU for throughput-oriented scenarios.

text-to-text-transfer-transformer

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

mae

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

ke-t5

i-Code

OFA

Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

KorWikiTableQuestions

This repo is for Korean wiki table question answering datasets described in the paper of Korean-Specific Dataset for Table Question Answering

tapas

End-to-end neural table-text understanding models.

PaddleNLP

👑 Easy-to-use and powerful NLP and LLM library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Search, ❓ Question Answering, ℹ️ Information Extraction, 📄 Document Intelligence, 💌 Sentiment Analysis etc.

TextRecognitionDataGenerator

A synthetic data generator for text recognition

wikipedia-word-frequency

Gather modern English word frequencies from all enwiki articles.

korquad.github.io

Korean wiki QA dataset for MRC

wptools

Wikipedia tools (for Humans): easily extract data from Wikipedia, Wikidata, and other MediaWikis

wikiextractor

A tool for extracting plain text from Wikipedia dumps

parseq

Scene Text Recognition with Permuted Autoregressive Sequence Models (ECCV 2022)

polyglot

Polyglot: Large Language Models of Well-balanced Competence in Multi-languages

pawls

Software that makes labeling PDFs easy.

KcELECTRA

🤗 Korean Comments ELECTRA: 한국어 댓글로 학습한 ELECTRA 모델

table-transformer

Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS evaluation metric.

tunib-electra

Korean-English Bilingual Electra Models

CascadeTabNet

This repository contains the code and implementation details of the CascadeTabNet paper "CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents"

TUTA_table_understanding

TUTA and ForTaP for Structure-Aware and Numerical-Reasoning-Aware Table Pre-Training

vit-explain

Explainability for Vision Transformers