https://www.youngju.dev/blog 천천히 올바르게. AI Researcher & DevOps Engineer Youngju's blog. GPU/CUDA, LLM, MLOps, Kubernetes AI workloads, and data engineering — plus mindset essays on confidence, routines, health, and sport psychology. ko fjvbn2003@gmail.com (Youngju Kim) fjvbn2003@gmail.com (Youngju Kim) Wed, 12 Aug 2026 00:00:00 GMT https://www.youngju.dev/blog/ai/2026-08-12-huggingface-embedding-models.en https://www.youngju.dev/blog/ai/2026-08-12-huggingface-embedding-models.en What decides your embedding model in a RAG build is not a leaderboard rank but dimensionality, maximum input length, prefix conventions, multilingual coverage, and the division of labor with a reranker. This post lays out the card values read off embedding and reranker pages on 2026-08-12, explains what an MTEB score does not tell you, and covers what you have to measure yourself for Korean documents. Part 3 of the open model guide series. Wed, 12 Aug 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) aillmhuggingfaceopen-source-llmembeddingragreranker https://www.youngju.dev/blog/ai/2026-08-12-huggingface-embedding-models.ja https://www.youngju.dev/blog/ai/2026-08-12-huggingface-embedding-models.ja RAGを作るとき埋め込みモデルの選択を左右するのは、リーダーボードの順位ではなく次元、最大入力長、接頭辞の規約、多言語対応の表記、そしてリランカーとの役割分担です。この記事は2026-08-12に確認した埋め込み・リランカーモデルの実際のカード値を整理し、MTEBのスコアが何を語らないのか、日本語や韓国語の文書を扱うときに何を自分で測るべきかを説明します。オープンモデルガイドシリーズ第3回です。 Wed, 12 Aug 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) aillmhuggingfaceopen-source-llmembeddingragreranker https://www.youngju.dev/blog/ai/2026-08-12-huggingface-embedding-models https://www.youngju.dev/blog/ai/2026-08-12-huggingface-embedding-models RAG를 만들 때 임베딩 모델 선택을 좌우하는 것은 리더보드 순위가 아니라 차원, 최대 입력 길이, 접두어 규약, 다국어 표기, 그리고 리랭커와의 역할 분담입니다. 이 글은 2026-08-12에 확인한 임베딩·리랭커 모델들의 실제 카드 값을 정리하고, MTEB 점수가 무엇을 말해 주지 않는지, 한국어 문서를 다룰 때 무엇을 직접 재야 하는지를 설명합니다. 오픈 모델 가이드 시리즈 3편입니다. Wed, 12 Aug 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) aillmhuggingfaceopen-source-llmembeddingragreranker