AWS Machine Learning Blog

Category: Amazon SageMaker

John Snow Labs Medical LLMs are now available in Amazon SageMaker JumpStart

Today, we are excited to announce that John Snow Labs’ Medical LLM – Small and Medical LLM – Medium large language models (LLMs) are now available on Amazon SageMaker Jumpstart. For medical doctors, this tool provides a rapid understanding of a patient’s medical journey, aiding in timely and informed decision-making from extensive documentation. This summarization capability not only boosts efficiency but also makes sure that no critical details are overlooked, thereby supporting optimal patient care and enhancing healthcare outcomes.

Accelerating Mixtral MoE fine-tuning on Amazon SageMaker with QLoRA

In this post, we demonstrate how you can address the challenges of model customization being complex, time-consuming, and often expensive by using fully managed environment with Amazon SageMaker Training jobs to fine-tune the Mixtral 8x7B model using PyTorch Fully Sharded Data Parallel (FSDP) and Quantized Low Rank Adaptation (QLoRA).

Amazon SageMaker Inference now supports G6e instances

G6e instances on SageMaker unlock the ability to deploy a wide variety of open source models cost-effectively. With superior memory capacity, enhanced performance, and cost-effectiveness, these instances represent a compelling solution for organizations looking to deploy and scale their AI applications. The ability to handle larger models, support longer context lengths, and maintain high throughput makes G6e instances particularly valuable for modern AI applications.

Improve factual consistency with LLM Debates

In this post, we demonstrate the potential of large language model (LLM) debates using a supervised dataset with ground truth. In this post, we navigate the LLM debating technique with persuasive LLMs having two expert debater LLMs (Anthropic Claude 3 Sonnet and Mixtral 8X7B) and one judge LLM (Mistral 7B v2 to measure, compare, and contrast its performance against other techniques like self-consistency (with naive and expert judges) and LLM consultancy.

solution__architecture

Governing the ML lifecycle at scale, Part 3: Setting up data governance at scale

This post dives deep into how to set up data governance at scale using Amazon DataZone for the data mesh. The data mesh is a modern approach to data management that decentralizes data ownership and treats data as a product. It enables different business units within an organization to create, share, and govern their own data assets, promoting self-service analytics and reducing the time required to convert data experiments into production-ready applications.

Enhance speech synthesis and video generation models with RLHF using audio and video segmentation in Amazon SageMaker

In this post, we show you how to implement an audio and video segmentation solution using SageMaker Ground Truth. We guide you through deploying the necessary infrastructure using AWS CloudFormation, creating an internal labeling workforce, and setting up your first labeling job. By the end of this post, you will have a fully functional audio/video segmentation workflow that you can adapt for various use cases, from training speech synthesis models to improving video generation capabilities.

Add image architecture

Fine-tune large language models with Amazon SageMaker Autopilot

Fine-tuning foundation models (FMs) is a process that involves exposing a pre-trained FM to task-specific data and fine-tuning its parameters. It can then develop a deeper understanding and produce more accurate and relevant outputs for that particular domain. In this post, we show how to use an Amazon SageMaker Autopilot training job with the AutoMLV2 […]

How FP8 boosts LLM training by 18% on Amazon SageMaker P5 instances

LLM training has seen remarkable advances in recent years, with organizations pushing the boundaries of what’s possible in terms of model size, performance, and efficiency. In this post, we explore how FP8 optimization can significantly speed up large model training on Amazon SageMaker P5 instances.

Customize small language models on AWS with automotive terminology

In this post, we guide you through the phases of customizing SLMs on AWS, with a specific focus on automotive terminology for diagnostics as a Q&A task. We begin with the data analysis phase and progress through the end-to-end process, covering fine-tuning, deployment, and evaluation. We compare a customized SLM with a general purpose LLM, using various metrics to assess vocabulary richness and overall accuracy.

Cohere Embed multimodal embeddings model is now available on Amazon SageMaker JumpStart

The Cohere Embed multimodal embeddings model is now generally available on Amazon SageMaker JumpStart. This model is the newest Cohere Embed 3 model, which is now multimodal and capable of generating embeddings from both text and images, enabling enterprises to unlock real value from their vast amounts of data that exist in image form. In this post, we discuss the benefits and capabilities of this new model with some examples.