Microsoft AI Releases Harrier-OSS-v1: A New Family of Multilingual Embedding Models Hitting SOTA on Multilingual MTEB v2

Microsoft has released Harrier-OSS-v1, a family of multilingual text embedding models that achieve state-of-the-art results on the Multilingual MTEB v2 benchmark. This release is significant for developers as it offers scalable and high-quality semantic representations across languages using decoder-only architectures with expanded context windows, enhancing retrieval accuracy in global applications.

Read the full article at MarkTechPost

---

Want to create content about this topic? Use Nemati AI tools to generate articles, social posts, and more.