Paraphrase-multilingual-MiniLM-L12-v2, Table Transformer Detection, and Bielik-11B-v3.0-Instruct are now available in Amazon SageMaker JumpStart

AWS SageMaker JumpStart Updates

AWS has introduced new models in Amazon SageMaker JumpStart: paraphrase-multilingual-MiniLM-L12-v2, Microsoft Table Transformer Detection, and Bielik-11B-v3.0-Instruct.

Paraphrase-multilingual-MiniLM-L12-v2

This lightweight semantic similarity model maps sentences and paragraphs to a 384-dimensional dense vector space across 50+ languages. Ideal for cross-lingual semantic search, multilingual document clustering, and sentence similarity scoring.

Microsoft Table Transformer Detection

A DETR-based object detection model for locating tables in unstructured documents. Suitable for document digitization pipelines and automated data extraction workflows.

Bielik-11B-v3.0-Instruct

An 11-billion-parameter generative language model trained on multilingual corpora, emphasizing Polish and other European languages. Excellent for dialogue, STEM reasoning, logic tasks, and enterprise applications.

What to do

• Deploy models via SageMaker Studio or the SageMaker Python SDK.
• Explore the Amazon SageMaker JumpStart documentation for deployment and usage details.

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.