KURE: 고려대학교에서 개발한, 한국어 검색에 특화된 임베딩 모델

A high-throughput and memory-efficient inference and serving engine for LLMs

KorNLI and KorSTS: New Benchmark Datasets for Korean Natural Language Understanding

Korean NLI Datasets

Solving Semantic Textual Similarity task for KLUE Benchmark dataset within 12 days

ONNXMLTools enables conversion of models to ONNX

Official inference framework for 1-bit LLMs

arXiv 논문을 자동으로 한국어로 번역하고, LaTeX 소스에서 PDF 파일을 생성하는 도구입니다. OpenAI GPT API를 사용하여 번역을 수행합니다.

한국어 언어모델 다분야 사고력 벤치마크

All Algorithms implemented in Python

한글 텍스트 임베딩 모델 리더보드

Korean Sentence Embedding Repository

🍰 Desktop utility to download images/videos/music/text from various websites, and more.

Korean Moview Review Emotion (KMRE) Dataset

KoRean based ELECTRA pre-trained models (KR-ELECTRA) for Tensorflow and PyTorch

Model interpretability and understanding for PyTorch

Korean Sentence Embedding Model Performance Benchmark for RAG

Data augmentation for NLP

A principled instruction benchmark on formulating effective queries and prompts for large language models (LLMs). Our paper: https://arxiv.org/abs/2312.16171

Awesome list of Korean Large Language Models.

Text-To-Speech, RAG, and LLMs. All local!

The Universe of Evaluation. All about the evaluation for LLMs.

Merge and split PDF with a simple right click

금융 도메인에 특화된 한국어 임베딩 모델

카카오뱅크 & 에프엔가이드에서 학습한 금융 도메인 특화 언어모델