BTechibtechi.in
Loading Loading
Free IIT Madras BS notes, PYQs and mock tests at btechi.in

DLP · Fine-tuning LLMs: PEFT & GPU memory

8 questions · 24 marks · 1 paper

Answer key

Indian Institute of Technology Madras

BS Degree Programme · Examination & Study Paper

Deep Learning Practice

Fine-tuning LLMs: PEFT & GPU memory

Official Paper

Examination Instructions & Guidelines

Solve on notebook/paper first before checking solutions.
MCQ: Exactly 1 option is correct. Negative marking applies.
MSQ: One or more options correct. Select all to score.
NAT: Numerical response. No negative marking.
Scientific calculator allowed for all calculations.
Official answer key is sealed at the end of this sheet.

Q1MCQ2 Marks·Choose one option
Key ↓
When performing full fine-tuning of a large language model (e.g., 10B parameters) using Adam, which component consumes the most GPU memory?
1. AThe model’s weights (parameters).
2. BThe gradients calculated for each parameter.
3. CThe optimizer states (e.g., momentum and variance).
4. DThe vocabulary and embedding matrix.
Q2MCQ2 Marks·Choose one option
Key ↓
A company wants to align its chatbot with values of being helpful, harmless, and honest. Human labelers provide ideal responses and rank AI-generated outputs. Which adaptation technique is designed for this?
1. AInstruction Tuning
2. BZero-shot prompting
3. CReinforcement Learning from Human Feedback (RLHF)
4. DContinued pre-training
Q3MCQ3 Marks·Choose one option
Key ↓
1. A
2. B
3. C
4. D
Q4MCQ3 Marks·Choose one option
Key ↓
1. A
2. B
3. C
4. D
Q5MCQ3 Marks·Choose one option
Key ↓
What is a key implication of using a Parameter-Efficient Fine-Tuning (PEFT) method like LoRA when adapting a large language model for a new task?
1. AInference speed is 10x faster.
2. BOnly a small number of new parameters are trained while freezing original weights.
3. CIt eliminates the need for labeled data.
4. DModel must be retrained from scratch.
Q6MSQ4 Marks·Choose all correct options
Key ↓
A research lab has access to a powerful 175B parameter language model. They need to adapt it for a highly specialized legal text analysis task, but they only have about 500 labeled examples and limited access to high-end GPUs for fine-tuning. Which of the following are viable and computationally efficient adaptation strategies? (Select ALL that apply)
1. AFull fine-tuning
2. BZero-shot prompting
3. CFew-shot in-context learning
4. DLoRA (PEFT)
5. EPre-training from scratch
Q7MSQ4 Marks·Choose all correct options
Key ↓
A team is fine-tuning a 7B parameter model on a single GPU with 24GB of memory. They are using the Adam optimizer (which stores 2 states per parameter) and 32-bit precision (4 bytes per parameter/ state/gradient). They find that they run out of memory even with a batch size of 1. Which of the following strategies could help them complete the fine-tuning process on this GPU? (Select ALL that apply)
1. AIncrease learning rate
2. BUse LoRA
3. CUse quantization (8/4-bit)
4. DSwitch to SGD
5. EGradient accumulation
Q8NAT3 Marks·Write the number
Key ↓
Your answer:

Official Key

Master Answer Key & Explanations

Official answer keys from IIT Madras BS past papers. Click any question to review.

Reveal Key

Q1C

Q2C

Q3C

Q4C

Q5B

Q6B, C, D

Q7B, C, D

Q84.8

Questions and answer keys are reproduced from the official IIT Madras BS papers. Topics and repeated question types are BTechi’s own grouping. BTechi is not affiliated with IIT Madras.