AWS Machine Learning Blog

Category: Expert (400)

Fine-tune large multimodal models using Amazon SageMaker

Large multimodal models (LMMs) integrate multiple data types into a single model. By combining text data with images and other modalities during training, multimodal models such as Claude3, GPT-4V, and Gemini Pro Vision gain more comprehensive understanding and improved ability to process diverse data types. The multimodal approach allows models to handle a wider range […]

Evaluation of generative AI techniques for clinical report summarization

In this post, we provide a comparison of results obtained by two such techniques: zero-shot and few-shot prompting. We also explore the utility of the RAG prompt engineering technique as it applies to the task of summarization.
Evaluating LLMs is an undervalued part of the machine learning (ML) pipeline.

Build a Hugging Face text classification model in Amazon SageMaker JumpStart

Amazon SageMaker JumpStart provides a suite of built-in algorithms, pre-trained models, and pre-built solution templates to help data scientists and machine learning (ML) practitioners get started on training and deploying ML models quickly. You can use these algorithms and models for both supervised and unsupervised learning. They can process various types of input data, including […]

Information extraction with LLMs using Amazon SageMaker JumpStart

Large language models (LLMs) have unlocked new possibilities for extracting information from unstructured text data. Although much of the current excitement is around LLMs for generative AI tasks, many of the key use cases that you might want to solve have not fundamentally changed. Tasks such as routing support tickets, recognizing customers intents from a […]

Fine tuning workflow

Improve LLM performance with human and AI feedback on Amazon SageMaker for Amazon Engineering

The Amazon EU Design and Construction (Amazon D&C) team is the engineering team designing and constructing Amazon warehouses. The team navigates a large volume of documents and locates the right information to make sure the warehouse design meets the highest standards. In the post A generative AI-powered solution on Amazon SageMaker to help Amazon EU […]

Integrate HyperPod clusters with Active Directory for seamless multi-user login

Amazon SageMaker HyperPod is purpose-built to accelerate foundation model (FM) training, removing the undifferentiated heavy lifting involved in managing and optimizing a large training compute cluster. With SageMaker HyperPod, you can train FMs for weeks and months without disruption. Typically, HyperPod clusters are used by multiple users: machine learning (ML) researchers, software engineers, data scientists, […]

Boost inference performance for Mixtral and Llama 2 models with new Amazon SageMaker containers

In January 2024, Amazon SageMaker launched a new version (0.26.0) of Large Model Inference (LMI) Deep Learning Containers (DLCs). This version offers support for new models (including Mixture of Experts), performance and usability improvements across inference backends, as well as new generation details for increased control and prediction explainability (such as reason for generation completion […]

Build a receipt and invoice processing pipeline with Amazon Textract

In today’s business landscape, organizations are constantly seeking ways to optimize their financial processes, enhance efficiency, and drive cost savings. One area that holds significant potential for improvement is accounts payable. On a high level, the accounts payable process includes receiving and scanning invoices, extraction of the relevant data from scanned invoices, validation, approval, and […]

Large language model inference over confidential data using AWS Nitro Enclaves

This post discusses how Nitro Enclaves can help protect LLM model deployments, specifically those that use personally identifiable information (PII) or protected health information (PHI). This post is for educational purposes only and should not be used in production environments without additional controls.