KURE-v2 도입 검토 후기 → Multi-Vector 임베딩은 왜 아직 못 쓰나2026.10.15·4 분AI Engineering Embedding Kure Multi-Vector Colbert Maxsim Rag
Veil-PII-Ko-Lite — 경량 한국어 PII 모델 개발 리포트2026.09.28·18 분AI Engineering Pii Ner Koelectra Onnx Quantization Fine-Tuning
Indexing 임베딩 모델 도메인 최적화 → 긴 약관을 위한 KURE-v1 LoRA Fine-Tuning2026.05.20·7 분AI Engineering Embedding Fine-Tuning Lora Kure Long-Context Rag
Retrieval 임베딩 모델 도메인 최적화 → 보험 도메인 e5-small-ko-v2 LoRA Fine-Tuning2026.05.11·7 분AI Engineering Embedding Fine-Tuning Lora E5 Retrieval Mnrl
Python에서 Thread는 어떻게 사용하는가?2025.03.31·11 분Dev Notes Deadlock Gil Global Interpreter Lock I/O Thread 스레드
Python 3.10.12 install - At distribution #Debian #Ubuntu 22.042025.03.07·1 분MLOps & Infra Debian Install Python Linux Ubuntu
[RAG] RAPTOR(Recrusive Abstractive Processing for Tree-Organized Retrieval) Parth Sarthi et al. 20242024.11.19·14 분Paper Review Embedding Llm Rag Raptor Recrusive Abstractive Processing for Tree-Organized Retrivall Retrival Sllm Slm Tree
[PEFT] LoRA(Low-Rank Adaptation of Large Language Models) Fine-Tuning 학습 방식 뜯어보기! (내부 학습 코드 해석)2024.10.18·10 분AI Engineering Adapter Fine-Tuning Lora Lora Fine-Tuning Peft Rank 로라
[Fine-Tuning] SimCSE + LoRA를 활용해서 임베딩 모델을 Fine-Tuning해보자!2024.10.15·15 분AI Engineering Contrastive Learning Embedding Fine-Tuning Lora Peft Positive Pair Simcse Transfer Learning 임베딩모델 파인튜닝
Llama3-70B(Llama-cpp)로 Langchain Function Call 구현하기2024.05.28·19 분AI Engineering Agent Chatbot Function Call Langchain Llama-Cpp Llama3 Llama3 70b Rag
Mecab 설치 및 trouble shooting 하기(+user-dict 셋팅)2024.05.02·7 분Troubleshooting Mecab Token Tokenizer Tokenizing User-Dic User-Dict 형태소분석기
![[RAG] RAPTOR(Recrusive Abstractive Processing for Tree-Organized Retrieval) Parth Sarthi et al. 2024](/img/covers/paper_hu_8352ebb3f7413067.jpg)
![[PEFT] LoRA(Low-Rank Adaptation of Large Language Models) Fine-Tuning 학습 방식 뜯어보기! (내부 학습 코드 해석)](/img/covers/ai_hu_6e55decd95559988.jpg)
