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

AWS Release Notes

AWS announced the availability of all-MiniLM-L12-v2 in Amazon SageMaker JumpStart, enhancing the range of models for AWS customers. This model maps sentences and paragraphs to a 384-dimensional dense vector space, ideal for semantic search, text clustering, and sentence similarity applications.

all-MiniLM-L12-v2 excels at encoding sentences and short paragraphs into dense vector representations that capture semantic meaning, suitable for information retrieval, semantic search systems, document clustering, duplicate detection, and paraphrase identification. Its compact architecture ensures fast inference with strong embedding quality, perfect for production workloads requiring efficient text representations at scale.

Customers can deploy this model with just a few clicks in SageMaker JumpStart. To start, navigate to the Models section in SageMaker Studio or use the SageMaker Python SDK to deploy the model to your AWS account.

What to do

• Navigate to the Models section in SageMaker Studio.
• Use the SageMaker Python SDK to deploy the model.

Source: AWS release notes

If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.