Llama 3.2 generative AI models now available in Amazon SageMaker JumpStart

This article announces the availability of Llama 3.2 generative AI models in Amazon SageMaker JumpStart, a machine learning hub that offers pre-trained models and algorithms to help users get started with ML quickly.

Specifically, the article covers:

• Llama 3.2 models of various sizes, including 90B, 11B, 3B, 1B, and Llama Guard 3 11B Vision, are available in SageMaker JumpStart
• These models offer capabilities in sophisticated reasoning tasks, multimodal support for high-resolution images, and lightweight text-only models suitable for edge devices
• Llama 3.2 is the first Llama model to support vision tasks, with a new architecture that integrates image encoder representations into the language model
• The new models are designed for improved efficiency, reduced latency, and better performance for AI workloads
• Users can deploy and fine-tune Llama 3.2 models with a few clicks in SageMaker Studio or programmatically through the SageMaker Python SDK