Practice Free AIF-C01 Exam Online Questions – Page 11

Question #101

Which technique involves training AI models on labeled datasets to adapt the models to specific industry terminology and requirements?

A . Data augmentation
B . Fine-tuning
C . Model quantization
D . Continuous pre-training

Reveal Solution Hide Solution

Correct Answer: B
B

Explanation:

Fine-tuning involves training a pre-trained AI model on a labeled dataset specific to a particular task or domain, adapting it to industry terminology and requirements. This process adjusts the model’s parameters to better fit the target use case, such as understanding specialized vocabulary or meeting domain-specific needs.

Exact Extract from AWS AI Documents:

From the AWS Bedrock User Guide:

"Fine-tuning allows you to adapt a pre-trained foundation model to your specific use case by training it on a labeled dataset. This technique is commonly used to customize models forindustry-specific terminology, improving their accuracy for specialized tasks."

(Source: AWS Bedrock User Guide, Model Customization)

Detailed

Option A: Data augmentation Data augmentation involves generating synthetic data to expand a training dataset, typically for tasks like image or text generation. It does not specifically adapt models to industry terminology or requirements.

Option B: Fine-tuning This is the correct answer. Fine-tuning trains a pre-trained model on a labeled dataset tailored to the target domain, enabling it to learn industry-specific terminology and requirements, as described in the question.

Option C: Model quantization Model quantization reduces the precision of a model’s weights to optimize it for deployment (e.g., on edge devices). It does not involve training on labeled datasets or adapting to industry terminology.

Option D: Continuous pre-training Continuous pre-training extends the initial training of a model on a large, general dataset. While it can improve general performance, it is not specifically tailored to industry requirements using labeled datasets, unlike fine-tuning.

Reference: AWS Bedrock User Guide: Model Customization (https://docs.aws.amazon.com/bedrock/latest/userguide/custom-models.html)

AWS AI Practitioner Learning Path: Module on Model Training and Customization

Amazon SageMaker Developer Guide: Fine-Tuning Models (https://docs.aws.amazon.com/sagemaker/latest/dg/algos.html)

Question #102

A company needs to log all requests made to its Amazon Bedrock API. The company must retain the logs securely for 5 years at the lowest possible cost.

Which combination of AWS service and storage class meets these requirements? (Select TWO.)

A . AWS CloudTrail
B . Amazon CloudWatch
C . AWS Audit Manager
D . Amazon S3 Intelligent-Tiering
E . Amazon S3 Standard

Reveal Solution Hide Solution

Question #103

HOTSPOT

A company is using Amazon SageMaker to develop AI models.

Select the correct SageMaker feature or resource from the following list for each step in the AI model lifecycle workflow. Each SageMaker feature or resource should be selected one time or not at all. (Select TWO.)

– SageMaker Clarify

– SageMaker Model Registry

– SageMaker Serverless Inference

Reveal Solution Hide Solution

Correct Answer:

Explanation:

SageMaker Model Registry, SageMaker Serverless interference

This question requires selecting the appropriate Amazon SageMaker feature for two distinct steps in the AI model lifecycle .

Let’s break down each step and evaluate the options:

Step 1: Managing different versions of the model

The goal here is to identify a SageMaker feature that supports version control and management of machine learning models .

Let’s analyze the options:

SageMaker Clarify: This feature is used to detect bias in models and explain model predictions, helping with fairness and interpretability. It does not provide functionality for managing model versions.

SageMaker Model Registry: This is a centralized repository in Amazon SageMaker that allows users to catalog, manage, and track different versions of machine learning models. It supports model versioning, approval workflows, and deployment tracking, making it ideal for managing different versions of a model.

SageMaker Serverless Inference: This feature enables users to deploy models for inference without managing servers, automatically scaling based on demand. It is focused on inference (predictions), not on managing model versions.

Conclusion for Step 1: The SageMaker Model Registry is the correct choice for managing different versions of the model.

Exact Extract

Reference: According to the AWS SageMaker documentation, “The SageMaker Model Registry allows you to catalog models for production, manage model versions, associate metadata, and manage approval status for deployment.” (Source: AWS SageMaker Documentation – Model Registry, https://docs.aws.amazon.com/sagemaker/latest/dg/model-registry.html).

Step 2: Using the current model to make predictions

The goal here is to identify a SageMaker feature that facilitates making predictions (inference) with a deployed model .

Let’s evaluate the options:

SageMaker Clarify: As mentioned, this feature focuses on bias detection and explainability, not on performing inference or making predictions.

SageMaker Model Registry: While the Model Registry helps manage and catalog models, it is not used directly for making predictions. It can store models, but the actual inference process requires a deployment mechanism.

SageMaker Serverless Inference: This feature allows users to deploy models for inference without managing infrastructure. It automatically scales based on traffic and is specifically designed for making predictions in a cost-efficient, serverless manner.

Conclusion for Step 2: SageMaker Serverless Inference is the correct choice for using the current model to make predictions.

Exact Extract

Reference: The AWS documentation states, “SageMaker Serverless Inference is a deployment option that allows you to deploy machine learning models for inference without configuring or managing servers. It automatically scales to handle inference requests, making it ideal for workloads with intermittent or unpredictable traffic.” (Source: AWS SageMaker Documentation – Serverless Inference, https://docs.aws.amazon.com/sagemaker/latest/dg/serverless-inference.html).

Why Not Use the Same Feature Twice?

The question specifies that each SageMaker feature or resource should be selected one time or not at all. Since SageMaker Model Registry is used for version management and SageMaker Serverless Inference is used for predictions, each feature is selected exactly once. SageMaker Clarify is not applicable to either step, so it is not selected at all, fulfilling the question’s requirements.

Reference: AWS SageMaker Documentation: Model Registry (https://docs.aws.amazon.com/sagemaker/latest/dg/model-registry.html)

AWS SageMaker Documentation: Serverless Inference (https://docs.aws.amazon.com/sagemaker/latest/dg/serverless-inference.html)

AWS AI Practitioner Study Guide (conceptual alignment with SageMaker features for model lifecycle management and inference)

Let’s format this question according to the specified structure and provide a detailed, verified answer based on AWS AI Practitioner knowledge and official AWS documentation. The question focuses on selecting an AWS database service that supports storage and queries of embeddings as vectors, which is relevant to generative AI applications.

Question #104

Which technique breaks a complex task into smaller subtasks that are sent sequentially to a large language model (LLM)?

A . One-shot prompting
B . Prompt chaining
C . Tree of thoughts
D . Retrieval Augmented Generation (RAG)

Reveal Solution Hide Solution

Question #105

A company wants to fine-tune a foundation model (FM) for a specific use case. The company needs to deploy the FM on Amazon Bedrock for internal use.

Which solution will meet these requirements?

A . Run responses that have been generated by a pre-trained FM through Amazon Bedrock Guardrails to create the custom FM.
B . Use Amazon Personalize to customize the FM with custom data.
C . Use conversational builder for Amazon Bedrock Agents to create the custom model.
D . Use Amazon SageMaker AI to customize the FM. Then, import the trained model into Amazon Bedrock.

Reveal Solution Hide Solution

Question #106

An AI practitioner is using an Amazon Bedrock base model to summarize session chats from the customer service department. The AI practitioner wants to store invocation logs to monitor model input and output data.

A . Configure AWS CloudTrail as the logs destination for the model.
B . Enable model invocation logging in Amazon Bedrock.
C . Configure AWS Audit Manager as the logs destination for the model.
D . Configure model invocation logging in Amazon EventBridge.

Reveal Solution Hide Solution

Question #107

A company is building an AI application to summarize books of varying lengths. During testing, the application fails to summarize some books.

Why does the application fail to summarize some books?

A . The temperature is set too high.
B . The selected model does not support fine-tuning.
C . The Top P value is too high.
D . The input tokens exceed the model’s context size.

Reveal Solution Hide Solution

Question #108

A company wants to improve a large language model (LLM) for content moderation within 3 months.

The company wants the model to moderate content according to the company’s values and ethics.

The LLM must also be able to handle emerging trends and new types of problematic content.

Which solution will meet these requirements?

A . Conduct continuous pre-training on a large amount of text-based internet content.
B . Create a high-quality dataset of historical moderation decisions.
C . Fine-tune the LLM on a diverse set of general ethical guidelines from various sources.
D . Conduct reinforcement learning from human feedback (RLHF) by using real-time input from skilled moderators.

Reveal Solution Hide Solution

Question #109

A company needs to build its own large language model (LLM) based on only the company’s private data. The company is concerned about the environmental effect of the training process.

Which Amazon EC2 instance type has the LEAST environmental effect when training LLMs?

A . Amazon EC2 C series
B . Amazon EC2 G series
C . Amazon EC2 P series
D . Amazon EC2 Trn series

Reveal Solution Hide Solution

Question #110

A company is using Amazon Bedrock to develop an AI assistant. The AI assistant will respond to customer questions about the company’s products. The company conducts initial tests of the AI assistant. The company finds that the AI assistant’s responses do not represent the company well and might damage customer perception.

The company needs a prompt engineering technique to improve the AI assistant’s responses so that the responses better represent the company.

Which solution will meet this requirement?

A . Use zero-shot prompting.
B . Use chain-of-thought (CoT) prompting.
C . Use Retrieval Augmented Generation (RAG).
D . Provide a persona and tone in the prompt.

Reveal Solution Hide Solution

1 2 3 4 5 6 7 8 9 10 11 12 13

Exams