korean-nlp

AI가 쓴 한글을 사람 글처럼 윤문하는 Claude 스킬 — Korean AI-text humanizer: detects and rewrites translationese, mechanical parallelism, and 71 other AI tells

Korean BERT pre-trained cased (KoBERT)

Pretrained ELECTRA Model for Korean

Anything — 파일 이름이 아니라 본문으로 찾는 문서 검색기. HWP·PDF·Office 전문 검색을 오프라인으로. Windows·macOS | Offline content search across Korean documents (HWP, PDF, Office). Windows and macOS

KoBERT와 CRF로 만든 한국어 개체명인식기 (BERT+CRF based Named Entity Recognition model for Korean)

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

AI-writing humanizer for KO/EN/ZH/JA

🤗 Korean Comments ELECTRA: 한국어 댓글로 학습한 ELECTRA 모델

KB국민은행에서 제공하는 경제/금융 도메인에 특화된 한국어 ALBERT 모델

🔥 Korean GPT-2, KoGPT2 FineTuning cased. 한국어 가사 데이터 학습 🔥

KoBERT on 🤗 Huggingface Transformers 🤗 (with Bug Fixed)

🦅 Pretrained BigBird Model for Korean (up to 4096 tokens)

Distillation of KoBERT from SKTBrain (Lightweight KoBERT)

Production-ready RAG Framework (Python/FastAPI). 1-line config swaps: 6 Vector DBs (Weaviate, Pinecone, Qdrant, ChromaDB, pgvector, MongoDB), 5 LLMs (Gemini, OpenAI, Claude, Ollama, OpenRouter). OpenAI-compatible API. 2100+ tests.

HanBert on 🤗 Huggingface Transformers 🤗

Transformers Pipeline with KoELECTRA

PLM 기반 한국어 개체명 인식 (NER)

Distilling Task-Specific Knowledge from Teacher Model into BiLSTM

A collection of Korean NLP hands-on labs on Amazon SageMaker

Thinking-native compiler for LEET Language Understanding item sets — killer-item design grammar, verification separation, deterministic gate chain, 3-model benchmark