Microsoft drops Harrier-OSS-v1 multilingual embeddings

// 56d agoMODEL RELEASE

Microsoft drops Harrier-OSS-v1 multilingual embeddings

Microsoft released Harrier-OSS-v1, a family of decoder-only multilingual text embedding models supporting 94 languages and 32k context. The models achieve SOTA results on Multilingual MTEB v2 through architectural shifts and knowledge distillation.

// ANALYSIS

Microsoft is aggressively moving into the open-weights embedding space, proving that decoder-only backbones are the future for retrieval.

–32k token context window eliminates complex chunking strategies and "lost in the middle" issues for long-form RAG.
–Smaller variants (270M, 0.6B) punch far above their weight due to distillation from 27B+ parameter backbones.
–94-language support and instruction-tuning make it a versatile foundation for global retrieval and classification tasks.

// TAGS

harrier-oss-v1llmembeddingmultilingualopen-sourcerag

DISCOVERED

56d ago

2026-04-02

PUBLISHED

56d ago

2026-04-02

RELEVANCE

9/ 10

AUTHOR

AI Revolution

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE49m ago

Grok Build widens access, adds subagents

xAI’s Grok Build is an early-beta terminal coding agent with plan-review-approve flows, parallel subagents, worktree isolation, and support for plugins, hooks, skills, and MCP. The latest improvements make it feel less like a demo and more like xAI’s bid to compete seriously in the AI coding CLI race.

MODEL55m ago

Krea 2 lands on Replicate

Krea 2 is now available on Replicate, giving developers access to Krea's style-first image model outside the Krea app. It emphasizes aesthetic diversity, style control, and reference-driven creative workflows.

MODEL1h ago

ElevenLabs launches Music v2 for creators

ElevenLabs has released Music v2, a new music generation model that improves vocals, instrumentation, arrangement, and multilingual output. The model supports longer, section-by-section composition, inpainting to regenerate specific parts of a track, and more complex shifts within a song without losing coherence. It powers ElevenMusic and ElevenCreative now, with ElevenAPI access coming soon, and is trained on licensed data for commercial use.