Llama 3.1 models are now available in Amazon SageMaker JumpStart

This article announces the availability of Meta's Llama 3.1 large language models (LLMs) in Amazon SageMaker JumpStart for inference deployment. SageMaker JumpStart provides a broad selection of pre-trained foundation models that can be customized for specific use cases.

Specifically, the article covers:

• Overview of Llama 3.1 models (8B, 70B, 405B sizes) with multi-lingual support and improved reasoning capabilities
• Features of Amazon SageMaker JumpStart for secure model deployment and customization
• How to discover and deploy Llama 3.1 models in SageMaker JumpStart UI and via Python SDK
• Example prompts and inference for the Llama 3.1 405B Instruct model
• Llama Guard model for adding guardrails to LLM deployments