From the source
From the source
Hugging Face announces the release of two new multilingual embedding models from IBM: a 311M-parameter full-size model and a 97M-parameter compact model, both under Apache 2.0 license, supporting 200+ languages with 32K token context and improved retrieval quality.
From the source
We're releasing two new multilingual embedding models: granite-embedding-311m-multilingual-r2 — A 311M-parameter full-size model with 768-dimensional embeddings, Matryoshka dimension support, and top-tier multilingual retrieval quality. granite-embedding-97m-multilingual-r2 — A 97M-parameter compact model with 384-dimensional embeddings that delivers strong retrieval quality for its size.
huggingface.co
