Category: HAQM SageMaker

This is a guest post co-authored by Ajay K Gupta, Jean Felipe Teotonio and Paul A Churchyard from HSR.health. HSR.health is a geospatial health risk analytics firm whose vision is that global health challenges are solvable through human ingenuity and the focused and accurate application of data analytics. In this post, we present one approach […]

One of the most useful application patterns for generative AI workloads is Retrieval Augmented Generation (RAG). In the RAG pattern, we find pieces of reference content related to an input prompt by performing similarity searches on embeddings. Embeddings capture the information content in bodies of text, allowing natural language processing (NLP) models to work with […]

Data is the foundation to capturing the maximum value from AI technology and solving business problems quickly. To unlock the potential of generative AI technologies, however, there’s a key prerequisite: your data needs to be appropriately prepared. In this post, we describe how use generative AI to update and scale your data pipeline using HAQM […]

In the first part of this three-part series, we presented a solution that demonstrates how you can automate detecting document tampering and fraud at scale using AWS AI and machine learning (ML) services for a mortgage underwriting use case. In this post, we present an approach to develop a deep learning-based computer vision model to […]

With the advent of generative AI, today’s foundation models (FMs), such as the large language models (LLMs) Claude 2 and Llama 2, can perform a range of generative tasks such as question answering, summarization, and content creation on text data. However, real-world data exists in multiple modalities, such as text, images, video, and audio. Take […]

When deploying a large language model (LLM), machine learning (ML) practitioners typically care about two measurements for model serving performance: latency, defined by the time it takes to generate a single token, and throughput, defined by the number of tokens generated per second. Although a single request to the deployed endpoint would exhibit a throughput […]

In this post, we demonstrate how to use neural architecture search (NAS) based structural pruning to compress a fine-tuned BERT model to improve model performance and reduce inference times. Pre-trained language models (PLMs) are undergoing rapid commercial and enterprise adoption in the areas of productivity tools, customer service, search and recommendations, business process automation, and […]

Today, we’re excited to announce the availability of Llama 2 inference and fine-tuning support on AWS Trainium and AWS Inferentia instances in HAQM SageMaker JumpStart. Using AWS Trainium and Inferentia based instances, through SageMaker, can help users lower fine-tuning costs by up to 50%, and lower deployment costs by 4.7x, while lowering per token latency. […]

Geospatial data is data about specific locations on the earth’s surface. It can represent a geographical area as a whole or it can represent an event associated with a geographical area. Analysis of geospatial data is sought after in a few industries. It involves understanding where the data exists from a spatial perspective and why […]

OpenAI Whisper is an advanced automatic speech recognition (ASR) model with an MIT license. ASR technology finds utility in transcription services, voice assistants, and enhancing accessibility for individuals with hearing impairments. This state-of-the-art model is trained on a vast and diverse dataset of multilingual and multitask supervised data collected from the web. Its high accuracy […]