IBM releases open-source multilingual embedding model with 32K context

IBM has released Granite Embedding Multilingual R2, an open-source embedding model. This model supports 32,000 tokens of context and is designed to achieve high search quality with fewer than 100 million parameters. It is available under the Apache 2.0 license. AI

IMPACT Provides a new open-source embedding model with a large context window, potentially improving search and retrieval tasks.

RANK_REASON This is a release of an open-source model with a paper, fitting the research bucket. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — fosstodon.org →

• Apache 2.0
• Granite Embedding Multilingual R2
• Hugging Face
• IBM

• model release
• paper

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →