Fabio Oliveira’s Post

AWS re:Invent 2023 - Accelerate foundation model evaluation with Amazon SageMaker Clarify (AIM367)

AWS re:Invent 2023 - Improve FMs with Amazon SageMaker human-in-the-loop capabilities (AIM334)

Excited to announce “llm-sagemaker” a new Terraform module to easily deploy open LLMs from Hugging Face to Amazon Web Services (AWS) SageMaker real-time endpoints! 👀 Infrastructure as Code (IaC) tools are crucial for moving your AI Applications from Notebooks into production! 🚀 TL;DR: 🚀 New HashiCorp Terraform module simplifies LLM deployment to Amazon SageMaker 🤖 Support for popular models like Meta Llama 3, Mistral AI, Mixtral, and Cohere Command 🛠️ Handles IAM roles, SageMaker Model, Endpoint Configuration, and Autoscaling ⚡ Example deploy Llama 3.1 8B Instruct in just minutes 🔧 Customizable configurations for TGI 💻 Easy integration with AWS SDK for inference ✅ Includes integration tests using Gruntwork terratest Blog: https://lnkd.in/eQM5KtSD Module: https://lnkd.in/e8THb3Rd If you have feature requests, please open an issue. 🤗

Big time game changer if you are using Terraform! If you are using CDK - no worries there is also the GenAI CDK library that helps you aswell to accelerate your IaC operations. 👉 AWS CDK GenAI constructs: https://lnkd.in/eG88VMJV

Announcing API support for creating Amazon SageMaker notebook jobs. 🚀📝💻 https://go.aws/3GA1yvb Now you can programmatically run notebooks as jobs using APIs provided by Amazon SageMaker Pipelines, the ML workflow orchestration feature of Amazon SageMaker. Furthermore, you can create a multi-step ML workflow with multiple dependent notebooks using these APIs. Learn more and get started today! #AWS #MachineLearning #SageMaker #JupyterNotebooks

Amazon SageMaker provides model training container access for debugging. 🚀🚫🐛 https://go.aws/3unHom0 With this new capability, you can easily and securely perform remote debugging of model training code running in SageMaker from your local development environment. #MachineLearning #AWS #AmazonSageMaker

AWS re:Invent 2023 - Scaling FM inference to hundreds of models with Amazon SageMaker (AIM327)

Get hands-on experience scaling foundation model training using #AmazonSageMaker HyperPod & #AWSTrainium. 🤖 https://go.aws/45Juf4O At this workshop, you'll gain insights into setting up the software stack, optimizing resources, ensuring fault tolerance, & leveraging high-performance Trainium instances as #AWS solutions architects guide you through the labs.

Want to learn how Amazon SageMaker HyperPod offers easy cluster management and resiliency mechanisms for your LLM training? Join Arun Kumar Lokanatha and me at our upcoming event. Get hands-on experience scaling foundation model training using #AmazonSageMaker HyperPod! About HyperPod Amazon SageMaker HyperPod is a purpose-built infrastructure designed to streamline and optimize the training of foundation models (FMs) at scale. By leveraging SageMaker HyperPod, customers can reduce training time by up to 40% and ensure a resilient training environment that automatically handles hardware failures and resumes training from the last checkpoint.

In just THREE days, Andy Tante has: 1️⃣ Hosted a static website with Amazon S3 2️⃣ Visualised a dataset with Amazon QuickSight 3️⃣ Created a chatbot with Amazon Lex Want beginner friendly #AWS projects with FREE step by step guides and documentation templates? Just comment or DM "I'm in!" to get access ⚡ #awscloudpractitioner #cloudcomputing