AIF-C01: AWS Certified AI Practitioner practice questions, page 17 of 22, with answer review and explanations.
Question 81
Which option is a benefit of ongoing pre-training when fine-tuning a foundation model (FM)?
Helps decrease the model's complexity
Improves model performance over time
Decreases the training time requirement
Optimizes model inference time
Question 82
What are tokens in the context of generative AI models?
Tokens are the basic units of input and output that a generative AI model operates on, representing words, subwords, or other linguistic units.
Tokens are the mathematical representations of words or concepts used in generative AI models.
Tokens are the pre-trained weights of a generative AI model that are fine-tuned for specific tasks.
Tokens are the specific prompts or instructions given to a generative AI model to generate output.
Question 83
A company wants to assess the costs that are associated with using a large language model (LLM) to generate inferences. The company wants to use Amazon Bedrock to build generative AI applications. Which factor will drive the inference costs?
Number of tokens consumed
Temperature value
Amount of data used to train the LLM
Total training time
Question 84
A company is using Amazon SageMaker Studio notebooks to build and train ML models. The company stores the data in an Amazon S3 bucket. The company needs to manage the flow of data from Amazon S3 to SageMaker Studio notebooks. Which solution will meet this requirement?
Use Amazon Inspector to monitor SageMaker Studio.
Use Amazon Macie to monitor SageMaker Studio.
Configure SageMaker to use a VPC with an S3 endpoint.
Configure SageMaker to use S3 Glacier Deep Archive.
Question 85
A company has a foundation model (FM) that was customized by using Amazon Bedrock to answer customer queries about products. The company wants to validate the model's responses to new types of queries. The company needs to upload a new dataset that Amazon Bedrock can use for validation. Which AWS service meets these requirements?