Quiz Space

Large Language Models · Quiz 1 · 19 Jul 2026 · May 2026 term

Question 4: A Transformer model processes a sequence containing 6 tok…

Question 4

+4 marksNumerical answer

A Transformer model processes a sequence containing 6 tokens using Multi-Head Attention. The model initially uses 4 attention heads. If the number of attention heads is doubled to 8, while the sequence length remains unchanged, how many additional attention scores are computed across all heads?

Show answer

Correct answer: 144

See the whole paperTake it as a mock test

Question 4 of 16 in the IIT Madras BS Large Language Models (LLM) Quiz 1 paper sat on 19 Jul 2026, in the May 2026 term (Large Language Models 16 Jul 26). It carries 4 marks.

More questions from this paper

  1. Q1Which statements are true about traditional attention used in sequence-to-sequence models?
  2. Q2The query, key, and value projection matrices are given by: Based on the above data, answer the given subquestions.
  3. Q3The query, key, and value projection matrices are given by: Based on the above data, answer the given subquestions. Cho…
  4. Q5Figure question
  5. Q6Figure question
  6. Q7Figure question
  7. Q8Consider the following statements regarding the use of Teacher Forcing while training autoregressive sequence-to-sequen…
  8. Q9Based on the above data, answer the given subquestions.
  9. Q10Choose the option corresponding to the sentence with the highest joint probability under the given language model.
  10. Q11Using the given probability tree calculate the conditional probability of predicting "apples" given "like" [i.e P(apple…
  11. Q12Which of the following are components found within a GPT decoder layer?
  12. Q13The table below represents the conditional probability distribution over the vocabulary. Each column corresponds to a d…
  13. Q14The table below represents the conditional probability distribution over the vocabulary. Each column corresponds to a d…
  14. Q15The table below represents the conditional probability distribution over the vocabulary. Each column corresponds to a d…
  15. Q16The table below represents the conditional probability distribution over the vocabulary. Each column corresponds to a d…