Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)

Korean HateSpeech Dataset

Korean GPT-2 pretrained cased (KoGPT2)

ELMo Performance Experiment using Pytorch

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

Korean Parallel Corpus

Fast BPE

🤗 Pretrained BERT model & WordPiece tokenizer trained on Korean Comments 한국어 댓글로 프리트레이닝한 BERT 모델과 데이터셋

SentencePiece Python Implementation

Pretrained ELECTRA Model for Korean

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 2, and other large language models.

《한 권으로 끝내는 실전 LLM 파인튜닝》 예제 코드

Unsupervised Word Segmentation for Neural Machine Translation and Text Generation

Unsupervised text tokenizer for Neural Network-based text generation.

This is a simple demonstration of more advanced, agentic patterns built on top of the Realtime API.

Korean corpus repository

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

Inspect: A framework for large language model evaluations

가짜연구소 인과추론팀 특강 및 발표자료 모음입니다.

Source code for end-to-end dialogue model from the MultiWOZ paper (Budzianowski et al. 2018, EMNLP)

Korean SAT leader board

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

Assembly tool for de novo genome alignment

Convert PDF to markdown + JSON quickly with high accuracy

모두의 한국어 텍스트 분석 with 파이썬

Personal Assistant built using python libraries. It does almost anything which includes sending emails, Optical Text Recognition, Dynamic News Reporting at any time with API integration, Todo list …

huggingface에 있는 한국어 데이터 세트

Huly — All-in-One Project Management Platform (alternative to Linear, Jira, Slack, Notion, Motion)

All Algorithms implemented in Python