Microsoft AI Releases Harrier-OSS-v1: A New Family of Multilingual Embedding Models Beats SOTA in Multilingual MTEB v2
Microsoft announced the release of the Harrier-OSS-v1a family of three multilingual text embedding models designed to provide high-quality semantic representations in a wide range of languages. Emissions include three different scales: a 270M model parameter, a 0.6B model, and a 27B model. Harrier-OSS-v1 models have achieved modern results (SOTA) in the MTEB Multilingual (Large Text … Read more