Granite Embedding R2 Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916923776696320 |
|---|---|
| author | Awasthy, Parul Trivedi, Aashka Li, Yulong Doshi, Meet Bhat, Riyaz P, Vignesh Kumar, Vishwajeet Yang, Yushu Iyer, Bhavani Daniels, Abraham Murthy, Rudra Barker, Ken Franz, Martin Lee, Madison Ward, Todd Roukos, Salim Cox, David Lastras, Luis Sen, Jaydeep Florian, Radu |
| author_facet | Awasthy, Parul Trivedi, Aashka Li, Yulong Doshi, Meet Bhat, Riyaz P, Vignesh Kumar, Vishwajeet Yang, Yushu Iyer, Bhavani Daniels, Abraham Murthy, Rudra Barker, Ken Franz, Martin Lee, Madison Ward, Todd Roukos, Salim Cox, David Lastras, Luis Sen, Jaydeep Florian, Radu |
| contents | We introduce the Granite Embedding R2 models, a comprehensive family of high-performance English encoder-based embedding models engineered for enterprise-scale dense retrieval applications. Building upon our first-generation release, these models deliver substantial improvements, including 16x expanded context length (8,192 tokens), state-of-the-art performance across diverse retrieval domains - text, code, long-document search, multi-turn conversational, and tabular data - and measurable speed advantages of 19-44\% over leading competitors while maintaining superior accuracy. Our release encompasses both bi-encoder and cross-encoder architectures, featuring a highly effective 22-layer retriever model and its efficient 12-layer counterpart, alongside a high-quality reranker model, all trained exclusively on enterprise-appropriate data with comprehensive governance oversight. The models demonstrate exceptional versatility across standard benchmarks, IBM-developed evaluation suites, and real-world enterprise use cases, establishing new performance standards for open-source embedding models. In an era where retrieval speed and accuracy are paramount for competitive advantage, the Granite R2 models deliver a compelling combination of cutting-edge performance, enterprise-ready licensing, and transparent data provenance that organizations require for mission-critical deployments. All models are publicly available under the Apache 2.0 license at https://huggingface.co/collections/ibm-granite, enabling unrestricted research and commercial use. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_21085 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Granite Embedding R2 Models Awasthy, Parul Trivedi, Aashka Li, Yulong Doshi, Meet Bhat, Riyaz P, Vignesh Kumar, Vishwajeet Yang, Yushu Iyer, Bhavani Daniels, Abraham Murthy, Rudra Barker, Ken Franz, Martin Lee, Madison Ward, Todd Roukos, Salim Cox, David Lastras, Luis Sen, Jaydeep Florian, Radu Computation and Language Information Retrieval We introduce the Granite Embedding R2 models, a comprehensive family of high-performance English encoder-based embedding models engineered for enterprise-scale dense retrieval applications. Building upon our first-generation release, these models deliver substantial improvements, including 16x expanded context length (8,192 tokens), state-of-the-art performance across diverse retrieval domains - text, code, long-document search, multi-turn conversational, and tabular data - and measurable speed advantages of 19-44\% over leading competitors while maintaining superior accuracy. Our release encompasses both bi-encoder and cross-encoder architectures, featuring a highly effective 22-layer retriever model and its efficient 12-layer counterpart, alongside a high-quality reranker model, all trained exclusively on enterprise-appropriate data with comprehensive governance oversight. The models demonstrate exceptional versatility across standard benchmarks, IBM-developed evaluation suites, and real-world enterprise use cases, establishing new performance standards for open-source embedding models. In an era where retrieval speed and accuracy are paramount for competitive advantage, the Granite R2 models deliver a compelling combination of cutting-edge performance, enterprise-ready licensing, and transparent data provenance that organizations require for mission-critical deployments. All models are publicly available under the Apache 2.0 license at https://huggingface.co/collections/ibm-granite, enabling unrestricted research and commercial use. |
| title | Granite Embedding R2 Models |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2508.21085 |