AWS Machine Learning Blog
Category: Best Practices
How GoDaddy built a category generation system at scale with batch inference for Amazon Bedrock
This post provides an overview of a custom solution developed by the for GoDaddy, a domain registrar, registry, web hosting, and ecommerce company that seeks to make entrepreneurship more accessible by using generative AI to provide personalized business insights to over 21 million customers. In this collaboration, the Generative AI Innovation Center team created an accurate and cost-efficient generative AI–based solution using batch inference in Amazon Bedrock, helping GoDaddy improve their existing product categorization system.
Benchmarking customized models on Amazon Bedrock using LLMPerf and LiteLLM
This post begins a blog series exploring DeepSeek and open FMs on Amazon Bedrock Custom Model Import. It covers the process of performance benchmarking of custom models in Amazon Bedrock using popular open source tools: LLMPerf and LiteLLM. It includes a notebook that includes step-by-step instructions to deploy a DeepSeek-R1-Distill-Llama-8B model, but the same steps apply for any other model supported by Amazon Bedrock Custom Model Import.
Time series forecasting with LLM-based foundation models and scalable AIOps on AWS
In this blog post, we will guide you through the process of integrating Chronos into Amazon SageMaker Pipeline using a synthetic dataset that simulates a sales forecasting scenario, unlocking accurate and efficient predictions with minimal data.
Ground truth generation and review best practices for evaluating generative AI question-answering with FMEval
In this post, we discuss best practices for applying LLMs to generate ground truth for evaluating question-answering assistants with FMEval on an enterprise scale. FMEval is a comprehensive evaluation suite from Amazon SageMaker Clarify, and provides standardized implementations of metrics to assess quality and responsibility. To learn more about FMEval, see Evaluate large language models for quality and responsibility of LLMs.
Customize DeepSeek-R1 distilled models using Amazon SageMaker HyperPod recipes – Part 1
In this two-part series, we discuss how you can reduce the DeepSeek model customization complexity by using the pre-built fine-tuning workflows (also called “recipes”) for both DeepSeek-R1 model and its distilled variations, released as part of Amazon SageMaker HyperPod recipes. In this first post, we will build a solution architecture for fine-tuning DeepSeek-R1 distilled models and demonstrate the approach by providing a step-by-step example on customizing the DeepSeek-R1 Distill Qwen 7b model using recipes, achieving an average of 25% on all the Rouge scores, with a maximum of 49% on Rouge 2 score with both SageMaker HyperPod and SageMaker training jobs. The second part of the series will focus on fine-tuning the DeepSeek-R1 671b model itself.
Reduce conversational AI response time through inference at the edge with AWS Local Zones
This guide demonstrates how to deploy an open source foundation model from Hugging Face on Amazon EC2 instances across three locations: a commercial AWS Region and two AWS Local Zones. Through comparative benchmarking tests, we illustrate how deploying foundation models in Local Zones closer to end users can significantly reduce latency—a critical factor for real-time applications such as conversational AI assistants.
Best practices for Amazon SageMaker HyperPod task governance
In this post, we provide best practices to maximize the value of SageMaker HyperPod task governance and make the administration and data science experiences seamless. We also discuss common governance scenarios when administering and running generative AI development tasks.
Automate bulk image editing with Crop.photo and Amazon Rekognition
In this post, we explore how Crop.photo uses Amazon Rekognition to provide sophisticated image analysis, enabling automated and precise editing of large volumes of images. This integration streamlines the image editing process for clients, providing speed and accuracy, which is crucial in the fast-paced environments of ecommerce and sports.
Governing the ML lifecycle at scale, Part 4: Scaling MLOps with security and governance controls
This post provides detailed steps for setting up the key components of a multi-account ML platform. This includes configuring the ML Shared Services Account, which manages the central templates, model registry, and deployment pipelines; sharing the ML Admin and SageMaker Projects Portfolios from the central Service Catalog; and setting up the individual ML Development Accounts where data scientists can build and train models.
Protect your DeepSeek model deployments with Amazon Bedrock Guardrails
This blog post provides a comprehensive guide to implementing robust safety protections for DeepSeek-R1 and other open weight models using Amazon Bedrock Guardrails. By following this guide, you’ll learn how to use the advanced capabilities of DeepSeek models while maintaining strong security controls and promoting ethical AI practices.