Amazon SageMaker JumpStart adds all-MiniLM-L12-v2 for semantic search
Amazon SageMaker JumpStart now offers the all-MiniLM-L12-v2 model for semantic search and sentence similarity. This allows AWS customers to efficiently build applications like information retrieval and document clustering using dense vector representations. The model is readily deployable via SageMaker Studio or the Python SDK, ideal for production workloads needing fast, high-quality text embeddings.
- →SageMaker JumpStart includes all-MiniLM-L12-v2 model
- →Model ideal for efficient semantic search and information retrieval
- →Easy deployment for AI use cases
Features (1) ›
- SageMaker JumpStart includes all-MiniLM-L12-v2 model
Amazon SageMaker JumpStart now provides the all-MiniLM-L12-v2 model. This model generates 384-dimensional dense vectors for sentences and paragraphs, useful for semantic search, text clustering, and sentence similarity applications.
Enhancements (1) ›
- Model ideal for efficient semantic search and information retrieval
The all-MiniLM-L12-v2 model excels at capturing semantic meaning in text for applications like information retrieval, semantic search, document clustering, and duplicate detection. Its compact architecture ensures fast inference while maintaining high embedding quality, suitable for scalable production workloads.
Notes (1) ›
- Easy deployment for AI use cases
Customers can deploy the all-MiniLM-L12-v2 model with minimal effort through SageMaker Studio or the SageMaker Python SDK. Further details on deploying and using foundation models are available in the Amazon SageMaker JumpStart documentation.
https://aws.amazon.com/about-aws/whats-new/2026/06/all-minilm-l12-v2-on-sagemaker-jumpstart/