Qwissit Artificial Intelligence

AWS AIF-C01

Applications with Foundation Models

12 of 60 questions in the app

Inference parameters

  1. What does a low temperature do in a language model? Easy
  2. What is the parameter for the maximum number of output tokens for? Easy
  3. What is a stop sequence? Easy

Model selection

  1. A team wants product photos to be described automatically. Which criterion must be checked first when choosing the model? Easy
  2. For a voice assistant in telephone customer service, a fast answer matters most. Which criterion is especially important here? Easy
  3. A model is to analyse 200-page contracts in one go. Which model property is decisive? Easy

Retrieval Augmented Generation

  1. What is Retrieval Augmented Generation (RAG)? Easy
  2. Which advantage is typical of RAG? Easy

Inference parameters

  1. For which applications is a rather high temperature sensible? Medium
  2. What does the top-k parameter with the value 1 do? Medium

Customising models

  1. Which mappings of requirement and customisation approach make sense? Hard
  2. A team appends 30 examples to every prompt so that the model keeps to a special format. With millions of calls per month the token costs become high. Which options make sense? Hard

Certifications & exams

Which exam comes next?

You can already practise for 19 exams, and 21 are up for a vote. See all certifications with their official information, cast your vote or suggest your exam.

See all certifications