Researchers from IBM have released an open-source multilingual embedding model called Granite Embedding Multilingual R2. This model is designed to provide high-quality retrieval results for a wide range of languages, with a focus on achieving sub-100M retrieval quality. The model has been made available under the Apache 2.0 license, allowing developers to use and modify it freely. --- Why it matters: This matters because multilingual embedding models like Granite R2 can improve the performance of natural language processing tasks such as search, question answering, and text classification by providing more accurate representations of languages other than English. Source: https://huggingface.co/blog/ibm-granite/granite-embedding-multilingual-r2