Author: R Jemaiel

Accelerating Mixtral MoE fine-tuning on Amazon SageMaker with QLoRA

TutoSartup excerpt from this article:
However, building or fine-tuning these pre-trained LLMs on extensive datasets demands substantial computational resources and engineering effort... With the increase in sizes of these pre-trained LLMs, the model customization process becomes complex, time-consuming, and often prohibitively expensive for most organizations that lack the necessary infrastructure and skilled talent... Mixtral employ...

Introducing a new experience for AWS Systems Manager

TutoSartup excerpt from this article:
Today, I’m excited to introduce a new and improved version of AWS Systems Manager that brings a highly requested cross-account, and cross-Region experience for managing nodes at scale... The new System Manager experience provides centralized visibility of all your managed nodes which include various infrastructure types, such as Amazon Elastic Compute Cloud (EC2) instances, containers, virtual ...

Amazon SageMaker Inference now supports G6e instances

TutoSartup excerpt from this article:
xlarge—to host powerful open-source foundation models such as Llama 3... The key highlights for G6e instances include: Twice the GPU memory compared to G5 and G6 instances, enabling deployment of large language models in FP16 up to: 14B parameter model on a single GPU node (G6e...xlarge) 72B parameter model on a 4 GPU node (G6e...12xlarge) 90B parameter model on an 8 GPU nod...

Orchestrate generative AI workflows with Amazon Bedrock and AWS Step Functions

TutoSartup excerpt from this article:
5 Haiku on Amazon Bedrock in a supported AWS Region (we will use us-west-2) Create a State Machine and add a Map state In the AWS console in the us-west-2 Region, launch into Step Functions, and select Get started and Create your own to open a blank canvas in Step Functions Workflow Studio... This post discusses how to use AWS Step Functions to efficiently coordinate multi-step generative AI ...

AWS named as a leader again in the Gartner Magic Quadrant for Distributed Hybrid Infrastructure

TutoSartup excerpt from this article:
Gartner published the second Magic Quadrant for Distributed Hybrid Infrastructure (DHI), which includes Amazon Web Services (AWS) as a leader again... In the accompanying Gartner’s Critical Capabilities for DHI, AWS is ranked number one in four out of six use cases evaluated by Gartner—including hybrid infrastructure management, edge computing, assured workloads, and artificial intelligence &a...

Build generative AI applications on Amazon Bedrock with the AWS SDK for Python (Boto3)

TutoSartup excerpt from this article:
Amazon Bedrock is a fully managed service that offers a choice of high-performing foundation models (FMs) from leading AI companies like AI21 Labs, Anthropic, Cohere, Meta, Mistral AI, Stability AI, and Amazon through a single API, along with a broad set of capabilities to build generative AI applications with security, privacy, and responsible AI...client( service_name="bedrock-runtime", ...

Improve your app authentication workflow with new Amazon Cognito features

TutoSartup excerpt from this article:
Introduced 10 years ago, Amazon Cognito is a service that helps you implement customer identity and access management (CIAM) in your web and mobile applications... You can use Amazon Cognito for various use cases, from providing your customers to quickly add sign-in and sign-up experiences to your applications and authorization to securing machine-to-machine authentication and enabling role-based ...