exam questions

Exam AWS Certified AI Practitioner AIF-C01 All Questions

View all questions & answers for the AWS Certified AI Practitioner AIF-C01 exam

Exam AWS Certified AI Practitioner AIF-C01 topic 1 question 76 discussion

A company is using few-shot prompting on a base model that is hosted on Amazon Bedrock. The model currently uses 10 examples in the prompt. The model is invoked once daily and is performing well. The company wants to lower the monthly cost.
Which solution will meet these requirements?

  • A. Customize the model by using fine-tuning.
  • B. Decrease the number of tokens in the prompt.
  • C. Increase the number of tokens in the prompt.
  • D. Use Provisioned Throughput.
Show Suggested Answer Hide Answer
Suggested Answer: B 🗳️

Comments

Chosen Answer:
This is a voting comment (?). It is better to Upvote an existing comment if you don't have anything to add.
Switch to a voting comment New
Blair77
Highly Voted 3 months, 3 weeks ago
Selected Answer: B
Bedrock pricing is based on the number of tokens processed, which includes both input tokens (from the prompt) and output tokens (generated by the model). By decreasing the number of tokens in the prompt, you directly reduce the cost associated with each invocation of the model.
upvoted 6 times
...
Jessiii
Most Recent 2 weeks, 6 days ago
Selected Answer: B
B. Decrease the number of tokens in the prompt: In a few-shot learning scenario, the number of tokens used in the prompt contributes directly to the cost, as you're billed based on the number of tokens processed during each invocation. By decreasing the number of tokens in the prompt, the company can reduce the cost per invocation while still maintaining the model's performance. This can be done by reducing the number of examples or making the examples more concise.
upvoted 1 times
...
AzureDP900
1 month, 1 week ago
Selected Answer: D
D. Use Provisioned Throughput To lower the monthly cost, the company can use Provisioned Throughput (PT) to scale their model's resource utilization. This allows them to pay only for the actual compute time used by the model, rather than paying a fixed monthly fee.
upvoted 1 times
djeong95
4 weeks, 1 day ago
you are right to point this out but B is a more correct answer. There is a limit as to how much you can save with Provisioned Throughput (given that you were using On Demand before and that the company is okay with a longer term commitment). However, Decrease the number of tokens in the prompt is going to be more effective and doesn't require a longer term commitment.
upvoted 1 times
...
...
Community vote distribution
A (35%)
C (25%)
B (20%)
Other
Most Voted
A voting comment increases the vote count for the chosen answer by one.

Upvoting a comment with a selected answer will also increase the vote count towards that answer by one. So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.

SaveCancel
Loading ...
exam
Someone Bought Contributor Access for:
SY0-701
London, 1 minute ago