Question 6
Hotspot Question
A team is provisioning a new Azure Machine Learning workspace for a production project.
The workspace must support secure secret storage and operational monitoring. The team requires the workspace to be created with the correct dependent resources to meet security and monitoring requirements.
You need to configure the required dependencies when the team creates the workspace.
Which resources should you associate with the workspace? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Question 7
You have a deployment of an Azure OpenAI Service base model.
You plan to fine-tune the model.
You need to prepare a file that contains training data for multi-turn chat.
Which file encoding method should you use?
Question 8
An organization runs a customer-facing generative AI application built by using Microsoft Foundry. The application uses multiple prompts linked to multiple workflows to generate responses in production.
The application occasionally returns incomplete responses. The model call succeeds, but the final message sometimes stops early.
The issue cannot be reproduced reliably in development.
You need to identify where and why response generation is terminating early in production.
Which approach should you use?
Question 9
Hotspot Question
You manage a Microsoft Foundry project.
You plan to build a RAG solution.
The solution must include two models:
- One for text output, named Model1. This model must resemble human
language and read naturally.
- One for creating embeddings, named Model2. This model must maximize
the retrieval of relevant results (high recall) while minimizing
irrelevant or incorrect matches (high precision).
You need to compare different models by using benchmarking metrics to select the appropriate models for Model1 and Model2.
Which benchmarking metric should you select for each model? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Question 10
You manage an Azure Machine Learning workspace. You build a model for which you must configure a Responsible Al dashboard.
Based on what you learn from the dashboard, you must perform the following activities:
- Determine what must be done to get a desirable outcome from the
model.
- Identify the features that have the most direct effect on your
outcome of interest.
You need to select the components to use for the Responsible Al dashboard configuration.
Which two components should you add? Each correct answer presents part of the solution.
NOTE: Each correct selection is worth one point.