AI in practice

Meta's LLM Llama Guard is now available via AWS

Matthias Bastian
A portrait of a normal llama wearing a full-body purple raincoat. The raincoat is sleek and shiny, covering the llama from head to toe in a bright purple color. It features a hood that gently covers the llama's head and large buttons down the front. The background is a simple, outdoor setting, possibly hinting at rainy weather, enhancing the appropriateness of the raincoat. The image captures the llama standing calmly, showcasing the unique outfit in a natural, serene setting.

DALL-E 3 prompted by THE DECODER

Amazon SageMaker JumpStart now offers Llama Guard, a component of Meta's Purple Llama project. Llama Guard is a safety classifier for input/output filtering. It provides input and output safeguards for large language model deployments, enabling developers to build AI models responsibly. The model has been trained on a mix of publicly available datasets to detect potentially risky or offensive content. It can be integrated into developers' risk mitigation strategies for applications such as chatbots and content moderation. Llama Guard can be used alongside other foundational models available in SageMaker JumpStart.

Sources:
AWS blog