By using AWS re:Post, you agree to the AWS re:Post Terms of Use

AWS re:Post Live | Comprehensive and Accessible Model Evaluation for Foundation Models on Amazon Bedrock - Live on October 28th!

2 minute read
Content level: Foundational
0

Join us live on Twitch.tv on Monday, October 28th to hear about all things Amazon Bedrock!

Note: This episode aired on October 28th. You can watch the recording on demand by clicking here or on the image below.

20241028_RPL_ScreenShot

Welcome to our Community Article for the upcoming AWS re:Post Live show scheduled for Monday, October 28th at 11 am PST / 2 pm EST on twitch.tv/aws! On this episode, Sr. Technical Account Manager Jay Busch and Principal Technical Account Manager Rajakumar Sampathkumar return to follow up on our October 7th show with a discussion on Comprehensive and Accessible Model Evaluation for Foundation Models on Amazon Bedrock. We'll be covering some of the information in this article published by Raj, taking you step-by-step through Amazon Bedrock's model evaluation. If you have any questions please add them in the comments section at the bottom of this article and we will answer them as part of our live show on Monday, October 28th over on Twitch. If your question is selected you will be awarded 5 re:Post points!

Amazon Bedrock is a fully managed service that makes high-performing foundation models (FMs) from leading AI companies and Amazon available for your use through a unified API. You can choose from a wide range of foundation models to find the model that is best suited for your use case. Amazon Bedrock also offers a broad set of capabilities to build generative AI applications with security, privacy, and responsible AI. Using Amazon Bedrock, you can easily experiment with and evaluate top foundation models for your use cases, privately customize them with your data using techniques such as fine-tuning and Retrieval Augmented Generation (RAG), and build agents that execute tasks using your enterprise systems and data sources.

FMEval can help you quantify model risks, such as inaccurate, toxic, or biased content. Evaluating your LLM helps you comply with international guidelines around responsible generative AI, such as the ISO 42001 AI Management System Standard and the NIST AI Risk Management Framework.