DEV Community

Karthik Sakthivel
Karthik Sakthivel

Posted on

3

Amazon Bedrock Model Evaluation now supports evaluating custom model import models

What's new at AWS πŸ“’

⚜️ Amazon Bedrock Model Evaluation now supports evaluating custom model import models

⚜️ This feature allows customer to evaluate, compare, and select the best foundation models for your use case.

⚜️ Amazon Bedrock also offers a choice of automatic evaluation and human evaluation.

⚜️ This automatic evaluation with predefined algorithms for metrics such as accuracy, robustness, and toxicity.

⚜️ Additionally, for those metrics or subjective & custom metrics, such as friendliness, style, and alignment to brand voice, you can set up a human evaluation workflow with a few clicks.

⚜️ Human evaluation workflows can leverage your own employees or an AWS-managed team as reviewers. Model evaluation provides built-in curated datasets or you can bring your own datasets.

⚜️ It enables customers to evaluate their own models they imported to Amazon Bedrock through the Custom Model Import feature.

⚜️ Importantly, it allows customers to complete the cycle of selecting a base model, customizing it, evaluating it, and customizing it again or continuing to production if they are satisfied.

⚜️ To evaluate an imported model, simply select the custom model from the list of models to evaluate in the model selector tool when creating an evaluation job.

πŸ“Œ https://aws.amazon.com/bedrock/developer-experience/
Explore more about Model Evaluation on Amazon Bedrock:

πŸ“Œ Evaluate best foundation models in Amazon Bedrock
https://aws.amazon.com/blogs/aws/evaluate-compare-and-select-the-best-foundation-models-for-your-use-case-in-amazon-bedrock-preview/

Postmark Image

Speedy emails, satisfied customers

Are delayed transactional emails costing you user satisfaction? Postmark delivers your emails almost instantly, keeping your customers happy and connected.

Sign up

Top comments (0)

A Workflow Copilot. Tailored to You.

Pieces.app image

Our desktop app, with its intelligent copilot, streamlines coding by generating snippets, extracting code from screenshots, and accelerating problem-solving.

Read the docs

πŸ‘‹ Kindness is contagious

Please leave a ❀️ or a friendly comment on this post if you found it helpful!

Okay