多语言嵌入模型支持200+语言，长文本检索效果领先。
Granite Embedding Multilingual R2 Models
- 基于ModernBERT架构，支持52种语言和代码的双编码器模型。
- 32,768令牌上下文窗口，性能在多语言检索中达到顶尖水平。
- 开源可商用，适合企业级应用与负责任的研究使用。
我们推出了多语言Granite Embedding R2模型系列，是一组面向200多种语言的企业级稠密检索编码器模型。在之前的英文R2基础上，新增对52种语言和编程代码的支持，上下文窗口扩展至32,768个令牌（相比R1提升64倍），在多语言、跨语言文本搜索、代码检索、长文档搜索及推理检索数据集上均达到当前最优表现。该系列包含两个基于ModernBERT架构的双编码器模型：一个311M参数的全尺寸模型，以及一个通过模型剪枝和词表筛选构建的97M参数紧凑模型，后者在小于100M参数的开源多语言嵌入模型中取得了最高检索分数。全尺寸模型还支持马特约什卡表示学习，实现嵌入维度灵活调整。所有模型均在符合企业规范的数据上训练，并有治理监督，以Apache 2.0许可证发布于HuggingFace，旨在支持负责任使用并促进科研与企业自由采用。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。