IBM 發布 Granite Embedding Multilingual R2：具備 32K 上下文與 Apache 2.0 授權，100M 參數以下最強多語言嵌入模型
Original: Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality
IBM has officially released a new multilingual embedding model on the Hugging Face platform called "Granite Embedding Multilingual R2." The…
IBM 發布全新開源多語言嵌入模型 Granite Embedding Multilingual R2。該模型採用寬鬆的 Apache 2.0 授權，支援高達 32K 的上下文長度。在參數小於 1 億（Sub-100M）的同量級模型中，它展現出最頂尖的資訊檢索品質，非常適合用於建構高效能且低資源消耗的 RAG（檢索增強生成）系統。
IBM has officially released a new multilingual embedding model on the Hugging Face platform called "Granite Embedding Multilingual R2." The model's most notable highlight is achieving best-in-class information retrieval quality at an extremely compact parameter size (sub-100M parameters).
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Hugging Face Blog →Summaries are AI-generated; the original article is authoritative.