This repository contains pre-built examples to help customers get started with the Amazon SageMaker and Multi-Modal Large Language Models (MLLMs).
⚠️ Note : All Labs are built and tested on SageMaker Studio JupyterLab IDE or SageMaker Notebooks. Please feel free to create to cut us a ticket if you experience any issues running this inside other IDEs.
- Navigate to Amazon SageMaker from AWS Console
- To get started using these notebooks - Select your Domain and UserProfile from the drop-down. If you don't have a SageMaker Studio Domain - refer to Create a new Studio Domain
To create a new SageMaker Studio Domain follow [Option 1: Set up for single user (Quick setup)] or [Option 2: Set up for organizations]
The Set up for single users (quick setup) procedure gets you set up with default settings. Use this option if you want to get started with SageMaker quickly and you do not intend to customize your settings at this time. The default settings include granting access to the common SageMaker services for individual users to get started. For example, Amazon SageMaker Studio and Amazon SageMaker Canvas.
To quickly launch a new domain and get started with JupyterLab IDE,
And setup a new domain. That's all!
The Set up for organizations (custom setup) guides you through an advanced setup for your Amazon SageMaker domain. This option provides information and recommendations to help you understand and control all aspects of the account configuration, including permissions, integrations, and encryption. Use this option if you want to set up a custom domain.
To get started use the following infrastructure as code templates,
We welcome community contributions! Please see CONTRIBUTING.md for guidelines.
See CONTRIBUTING for more information.
This library is licensed under the MIT-0 License. See the LICENSE file.