AWS Machine Learning Blog

Category: Generative AI

Generative AI-powered technology operations

Generative AI-powered technology operations

In this post we describe how AWS generative AI solutions (including Amazon Bedrock, Amazon Q Developer, and Amazon Q Business) can further enhance TechOps productivity, reduce time to resolve issues, enhance customer experience, standardize operating procedures, and augment knowledge bases.

Align Meta Llama 3 to human preferences with DPO, Amazon SageMaker Studio, and Amazon SageMaker Ground Truth

Align Meta Llama 3 to human preferences with DPO, Amazon SageMaker Studio, and Amazon SageMaker Ground Truth

In this post, we show you how to enhance the performance of Meta Llama 3 8B Instruct by fine-tuning it using direct preference optimization (DPO) on data collected with SageMaker Ground Truth.

Ground truth curation and metric interpretation best practices for evaluating generative AI question answering using FMEval

Ground truth curation and metric interpretation best practices for evaluating generative AI question answering using FMEval

In this post, we discuss best practices for working with Foundation Model Evaluations Library (FMEval) in ground truth curation and metric interpretation for evaluating question answering applications for factual knowledge and quality.

Effectively manage foundation models for generative AI applications with Amazon SageMaker Model Registry

Effectively manage foundation models for generative AI applications with Amazon SageMaker Model Registry

In this post, we explore the new features of Model Registry that streamline foundation model (FM) management: you can now register unzipped model artifacts and pass an End User License Agreement (EULA) acceptance flag without needing users to intervene.