RAG and search
Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality
Our short summary of Hugging Face’s engineering write-up. The full story, with all the detail, is on their blog.
Read the full write-up on huggingface.co (opens in a new tab)Problem
Developers needed fast, high‑quality multilingual search without large models.
Solution
Created two Apache‑2.0 embedding models (97M and 311M) that cover 200+ languages, support 32K tokens, and deliver top retrieval scores, usable as drop‑in replacements.
MTEB scores 60.3 and 65.2
Want the architecture, code and numbers? They’re in the original post.
Read the full write-up on huggingface.co (opens in a new tab)