all-MiniLM-L12-v2 for semantic search and sentence similarity is now available in Amazon SageMaker JumpStart

This article announces the availability of all-MiniLM-L12-v2 in Amazon SageMaker JumpStart, enabling customers to build semantic search and text analysis applications.

• Maps sentences and paragraphs to 384-dimensional dense vector space for semantic understanding
• Ideal for semantic search, text clustering, duplicate detection, and paraphrase identification
• Compact architecture delivers fast inference while maintaining strong embedding quality
• Deploy with a few clicks via SageMaker Studio or Python SDK
• Well-suited for production workloads requiring efficient text representations at scale

The all-MiniLM-L12-v2 model expands SageMaker JumpStart's foundation model portfolio for text embedding and semantic analysis tasks.