Qwissit Artificial Intelligence

AWS AIF-C01

Training and Evaluating Foundation Models

12 of 60 questions in the app

Training foundation models

  1. What happens during the pre-training of a foundation model? Easy
  2. What is the goal of fine-tuning? Easy
  3. What is continued pre-training? Easy
  4. What happens when a model is distilled? Easy

Fine-tuning methods

  1. What is instruction tuning? Easy
  2. What is meant by transfer learning? Easy
  3. A model should understand medical terminology better. What is this customisation called? Easy

Data for fine-tuning

  1. What matters most in data for fine-tuning? Easy

Training foundation models

  1. Which mappings of goal and training method are appropriate? Medium
  2. Which data format does fine-tuning in Amazon Bedrock typically expect? Medium

Training foundation models

  1. A pharmaceutical company has 2 million unlabelled specialist articles and 3,000 reviewed question-answer pairs. The model should understand the specialist language and answer questions in the company format. Which sequence makes sense? Hard
  2. A retailer wants an assistant to (a) state current stock levels, (b) write in the typical brand tone and (c) keep to a particular structure in follow-up questions. Which combination fits? 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