Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.13521 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916013533036544 |
|---|---|
| author | Awasthy, Parul Trivedi, Aashka Yang, Yushu Barker, Ken Li, Yulong Iyer, Bhavani Franz, Martin Bross, Juergen Doshi, Meet P, Vignesh Kumar, Vishwajeet Ward, Todd Daniels, Abraham Lee, Madison Lastras, Luis Sen, Jaydeep Florian, Radu |
| author_facet | Awasthy, Parul Trivedi, Aashka Yang, Yushu Barker, Ken Li, Yulong Iyer, Bhavani Franz, Martin Bross, Juergen Doshi, Meet P, Vignesh Kumar, Vishwajeet Ward, Todd Daniels, Abraham Lee, Madison Lastras, Luis Sen, Jaydeep Florian, Radu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_13521 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Granite Embedding Multilingual R2 Models Awasthy, Parul Trivedi, Aashka Yang, Yushu Barker, Ken Li, Yulong Iyer, Bhavani Franz, Martin Bross, Juergen Doshi, Meet P, Vignesh Kumar, Vishwajeet Ward, Todd Daniels, Abraham Lee, Madison Lastras, Luis Sen, Jaydeep Florian, Radu Information Retrieval 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. |
| title | Granite Embedding Multilingual R2 Models |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2605.13521 |