Quiz Space

Deep Learning Practice · Quiz 1 · 13 Jul 2025 · May 2025 term

Question 2: When fully fine-tuning a large pre-trained Transformer mo…

Question 2

+2 marksOne correct option

When fully fine-tuning a large pre-trained Transformer model (e.g., >1 Billion parameters), which of the following contributes LEAST significantly to the GPU memory bottleneck compared to the others?

  1. A

    Storing the model parameters themselves.

  2. B

    Storing the gradients for each parameter.

  3. C

    Storing the optimizer states (e.g., momentum and variance for Adam).

  4. D

    Storing the input batch data (token IDs).

Show answer

Correct answer

  • D

    Storing the input batch data (token IDs).

See the whole paperTake it as a mock test

Question 2 of 16 in the IIT Madras BS Deep Learning Practice (Deep Learning Practice) Quiz 1 paper sat on 13 Jul 2025, in the May 2025 term (IIT M DEGREE AN EXAM QDB2 13 July 2025). It carries 2 marks.

More questions from this paper

  1. Q1A start-up is building a new language model for a low-resource language with many compound words and complex morphology…
  2. Q3A research team wants their pre-trained language model to generate more helpful and harmless responses without extensiv…
  3. Q4Consider the following Python code snippet using Hugging Face tokenizers: Which of the following attributes would be pr…
  4. Q5Consider the following Python code snippet: After executing the code above, what will dataset.column_names return?
  5. Q6Which of the following statements accurately describe common characteristics or goals of subword tokenization algorithm…
  6. Q7A team has a powerful pre-trained language model (e.g., a GPT-3 class model). They want to adapt it for a new summariza…
  7. Q8Figure question
  8. Q9You start with an initial vocabulary consisting only of individual characters: {"a":10, "b":8, "c":5, "\</w>":15}. Your…
  9. Q10Consider the following Python code snippet: How many samples will filtered_dataset contain after executing the code?
  10. Q11Figure question
  11. Q12Based on the above data, answer the given subquestions.
  12. Q13Based on the provided configuration, calculate the total number of parameters in the model’s embedding layer (token emb…
  13. Q14Based on the provided configuration, what is a primary characteristic of this language model’s architecture and trainin…
  14. Q15Considering the Adam optimizer stores 2 floating-point values per model parameter and parameters are 32-bit floats (4 b…
  15. Q16The configuration states the model uses Byte Pair Encoding (BPE). What is a key implication of this choice for handling…