Quiz Space

Introduction to Natural Language Processing · Quiz 2 · 1 Dec 2024 · September 2024 term

Question 7: Consider a scenario where you are fine-tuning a large lan…

Question 7

+3 marksOne or more correct options

Consider a scenario where you are fine-tuning a large language model using LoRA (Low-Rank Adaptation) and QLoRA (Quantized LoRA) techniques. Each technique has specific ways of reducing the model's memory and computational requirements. Select all statements that are correct about LoRA ans QLoRa.

Select all that apply.

  1. A

    LoRA achieves computational efficiency by performing inference with only a subset of the model's original parameters, completely ignoring any layers that are not low-rank.

  2. B

    QLoRA enables the model to dynamically switch between full and low-rank matrices during inference, improving accuracy while saving memory.

  3. C

    QLoRA applies quantization to the low-rank matrices introduced by LoRA, combining memory efficiency through quantization with a reduced number of trainable parameters from low-rank adaptation.

  4. D

    LoRA reduces the number of parameters by introducing low-rank matrices to approximate the weight updates, which minimizes the number of parameters that need to be stored and trained.

Show answer

Correct answers

  • C

    QLoRA applies quantization to the low-rank matrices introduced by LoRA, combining memory efficiency through quantization with a reduced number of trainable parameters from low-rank adaptation.

  • D

    LoRA reduces the number of parameters by introducing low-rank matrices to approximate the weight updates, which minimizes the number of parameters that need to be stored and trained.

Question 7 of 17 in the IIT Madras BS Introduction to Natural Language Processing (Intro to NLP) Quiz 2 paper sat on 1 Dec 2024, in the September 2024 term (IIT M DEGREE AN EXAM QDB2 01 Dec 2024). It carries 3 marks.

More questions from this paper

  1. Q1FastText differs from traditional word embedding models like Word2Vec because it can handle out-of-vocabulary (OOV) wor…
  2. Q2Consider the sentences: In a transformer model, each word receives positional encoding. How will the positional encodin…
  3. Q3Figure question
  4. Q4In the encoder of a transformer model, what are the sources of the queries (Q), keys (K), and values (V)?
  5. Q5Given the following statements, select all that are correct:
  6. Q6Consider the following statements about statistical-based (SMT) and example-based (EBMT) machine translation techniques…
  7. Q8You are analysing a collection of customer reviews using the Bag of Words (BoW) model. Here are three sample reviews:\ …
  8. Q9Consider the following sentences: S1: "I like studying LLMs" S2: "I like studying big data" S3: "I also like studying c…
  9. Q10Figure question
  10. Q11Figure question
  11. Q12Consider a reward model in RLHF that uses the Bradley-Terry model to compute pairwise preference probabilities between …
  12. Q13Figure question
  13. Q14Consider an RNN for a language modelling task with one hidden layer, trained with cross-entropy loss with a softmax ove…
  14. Q15Consider an RNN for a language modelling task with one hidden layer, trained with cross-entropy loss with a softmax ove…
  15. Q16Consider an RNN for a language modelling task with one hidden layer, trained with cross-entropy loss with a softmax ove…
  16. Q17Consider an RNN for a language modelling task with one hidden layer, trained with cross-entropy loss with a softmax ove…