Introducing Llama 3.2 models from Meta in Amazon Bedrock: A new generation of multimodal vision and lightweight models

This article introduces the new Llama 3.2 models from Meta available in Amazon Bedrock, which offer enhanced capabilities for multimodal vision and lightweight applications.

Specifically, the article covers:

• Overview of the Llama 3.2 model collection: 90B, 11B, 3B, and 1B models for vision and text tasks
• How to access and use the models in the Amazon Bedrock console, AWS CLI, and AWS SDKs
• Key features like multimodal vision support, improved multilingualism, and lightweight options for edge devices
• Model architecture details including auto-regressive language modeling, fine-tuning techniques, and optimized inference
• Availability of the models in various AWS regions and pricing information