Granite Embedding Multilingual R2 Models
摘要
We introduce the multilingual Granite Embedding R2 models, a family of encoder-based embedding models for enterprise-scale dense retrieval across 200+ languages. Extending our English-focused R2 release, these models add enhanced support for 52 languages and programming code, a 32,768-token context window (a 64x expansion over R1), and state-of-the-art overall performance across multilingual and cross-lingual text search, code retrieval, long-document search, and reasoning retrieval datasets. The release consists of two bi-encoder models based on the ModernBERT architecture with an expanded multilingual vocabulary: a 311M-parameter full-size, and a 97M-parameter compact model built via model pruning and vocabulary selection that achieves the highest retrieval score of any open multilingual embedding model under 100M parameters. The full-size also supports Matryoshka Representation Learning for flexible embedding dimensionality. Both models are trained on enterprise-appropriate data with governance oversight, and released under the Apache 2.0 license at https://huggingface.co/collections/ibm-granite, designed to support responsible use and enable unrestricted research and enterprise adoption.
引用
@article{arxiv.2605.13521,
title = {Granite Embedding Multilingual R2 Models},
author = {Parul Awasthy and Aashka Trivedi and Yushu Yang and Ken Barker and Yulong Li and Bhavani Iyer and Martin Franz and Juergen Bross and Meet Doshi and Vignesh P and Vishwajeet Kumar and Todd Ward and Abraham Daniels and Madison Lee and Luis Lastras and Jaydeep Sen and Radu Florian},
journal= {arXiv preprint arXiv:2605.13521},
year = {2026}
}