Category: Technical How-to

As customers seek to incorporate their corpus of knowledge into their generative artificial intelligence (AI) applications, or to build domain-specific models, their data science teams often want to conduct A/B testing and have repeatable experiments. In this post, we discuss a solution that uses infrastructure as code (IaC) to define the process of retrieving and […]

In today’s fast-paced corporate landscape, employee mental health has become a crucial aspect that organizations can no longer overlook. Many companies recognize that their greatest asset lies in their dedicated workforce, and each employee plays a vital role in collective success. As such, promoting employee well-being by creating a safe, inclusive, and supportive environment is […]

Pre-train HyenaDNA, a transformer model exceeding 1M tokens, using HealthOmics storage and SageMaker’s managed training environment to catalyze breakthroughs in precision medicine, agriculture, and biotechnology.

Today, we are excited to announce that the first model in the next generation Falcon 2 family, the Falcon 2 11B foundation model (FM) from Technology Innovation Institute (TII), is available through Amazon SageMaker JumpStart to deploy and run inference. Falcon 2 11B is a trained dense decoder model on a 5.5 trillion token dataset […]

In this post, we show you how to accelerate the full pre-training of LLM models by scaling up to 128 trn1.32xlarge nodes, using a Llama 2-7B model as an example. We share best practices for training LLMs on AWS Trainium, scaling the training on a cluster with over 100 nodes, improving efficiency of recovery from system and hardware failures, improving training stability, and achieving convergence.

This post shows you how to predict domain-specific product attributes from product images by fine-tuning a VLM on a fashion dataset using Amazon SageMaker, and then using Amazon Bedrock to generate product descriptions using the predicted attributes as input. So you can follow along, we’re sharing the code in a GitHub repository.

While Generative AI can create highly realistic content, including text, images, and videos, it can also generate outputs that appear plausible but are verifiably incorrect. Incorporating human judgment is crucial, especially in complex and high-risk decision-making scenarios. This involves building a human-in-the-loop process where humans play an active role in decision making alongside the AI system. In this blog post, you will learn about prompt chaining, how to break a complex task into multiple tasks to use prompt chaining with an LLM in a specific order, and how to involve a human to review the response generated by the LLM.

This post is co-written with HyeKyung Yang, Jieun Lim, and SeungBum Shim from LotteON. LotteON aims to be a platform that not only sells products, but also provides a personalized recommendation experience tailored to your preferred lifestyle. LotteON operates various specialty stores, including fashion, beauty, luxury, and kids, and strives to provide a personalized shopping […]

ONNX is an open source machine learning (ML) framework that provides interoperability across a wide range of frameworks, operating systems, and hardware platforms. ONNX Runtime is the runtime engine used for model inference and training with ONNX. AWS Graviton3 processors are optimized for ML workloads, including support for bfloat16, Scalable Vector Extension (SVE), and Matrix […]

In this post, we provide an overview of the state-of-the-art embedding models by Voyage AI and show a RAG implementation with Voyage AI’s text embedding model on Amazon SageMaker Jumpstart, Anthropic’s Claude 3 model on Amazon Bedrock, and Amazon OpenSearch Service. Voyage AI’s embedding models are the preferred embedding models for Anthropic. In addition to general-purpose embedding models, Voyage AI offers domain-specific embedding models that are tuned to a particular domain.