MauryaHub PYQ Practice

Large Language Models · Quiz 2 · Sep 2024

Large Language Models · Quiz 2 · Sep 2024

← Course papers · Start practice / exam

This page contains the reliably extracted subset, not the complete original paper.

Questions and published explanations below are available without starting a test. Some questions may not have a published solution yet.

0 / 18 published solutions

Question 137 MCQ · 3.0 marks

Source diagram or notation
6406533484107.Source diagram or notation
6406533484108.Source diagram or notation
6406533484109.Source diagram or notation
6406533484110.Source diagram or notation
      **LLM** **Section Id :** 64065374262 **Section Number :** 8 **Section type :** Online **Mandatory or Optional :** Mandatory **Number of Questions :** 12 **Number of Questions to be attempted :** 12 **Section Marks :** 40 **Display Number Panel :** Yes **Section Negative Marks :** 0 **Group All Questions :** No **Enable Mark as Answered Mark for Review and** No **Clear Response :** **Section Maximum Duration :** 0 **Section Minimum Duration :** 0 **Section Time In :** Minutes **Maximum Instruction Time :** 0

A published solution is not available for this question yet.

Report a correction for Q137

Question 139 MCQ · 0.0 marks

**General Note:** • If you find the given information is insufficient in any of the Numerical Answer Type (NAT) questions, enter -1 as the answer. • In all your calculations, take at least two digits. For example, if the intermediate result is 1.860875, then take it as 1.86 to the next step.
6406533484113.
Instructions has been mentioned above.
6406533484114.
This Instructions is just for a reference & not for an evaluation.

A published solution is not available for this question yet.

Report a correction for Q139

Question 140 NAT · 2.0 marks

Source diagram or notation
How many tokens are there in the initial vocabulary?

A published solution is not available for this question yet.

Report a correction for Q140

Question 141 MCQ · 3.0 marks

Source diagram or notation
Which of the following pairs has the least frequency before any merge?
6406533484116.Source diagram or notation
6406533484117.Source diagram or notation
6406533484118.Source diagram or notation
6406533484119.Source diagram or notation
6406533484120.Source diagram or notation
6406533484121.Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q141

Question 142 SHORT_TEXT · 3.0 marks

Source diagram or notation
What is the most frequent byte-pair before the very first merge? Say the most frequent byte pair is (‘a’,‘b’), then enter **“ab”** (without quotes and white spaces). If there is a tie between two or more candidates, pick the one that occurs first in the original vocabulary.

A published solution is not available for this question yet.

Report a correction for Q142

Question 143 NAT · 2.0 marks

Source diagram or notation
What is the frequency of the most frequent byte-pair before the very first merge?

A published solution is not available for this question yet.

Report a correction for Q143

Question 144 NAT · 2.0 marks

Source diagram or notation
How many tokens in the vocabulary will have their frequency revised/reduced after first merge?

A published solution is not available for this question yet.

Report a correction for Q144

Question 145 NAT · 2.0 marks

Source diagram or notation
After the first merge, how many tokens are there in the updated vocabulary?

A published solution is not available for this question yet.

Report a correction for Q145

Question 146 NAT · 2.0 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q146

Question 147 NAT · 2.0 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q147

Question 148 MSQ · 2.0 marks

Which of the following represent(s) the normalization step(s) in building a tokenizer for the English language?
6406533484128.
removing accents from characters.
6406533484129.
converting upper case letters to small case letters.
6406533484130.
assigning integers to tokens.
6406533484131.
splitting a sentence by whitespaces.
6406533484132.
the final post-processing step where the tokenizer adds the special tokens.
6406533484133.
none of these.

A published solution is not available for this question yet.

Report a correction for Q148

Question 149 MSQ · 2.0 marks

Choose all the aspects of the pre-training datasets that impact the model’s performance.
6406533484143.
Quality
6406533484144.
Size
6406533484145.
Diversity
6406533484146.
None of these

A published solution is not available for this question yet.

Report a correction for Q149

Question 150 MSQ · 4.0 marks

Source diagram or notation
6406533484134.
[v] is an awareness [w] can take many forms [x] particular strategies [y] and cognitive regulation
6406533484135.
[v] is an awareness [w] can take many forms [x] particular strategies [y] and cognitive regulation [z]
6406533484136.
[v] is an awareness [w] can take many forms [x] and cognitive regulation [y] particular strategies
6406533484137.
[v] is an awareness [w] particular strategies [x] can take many forms [y] and cognitive regulation
6406533484138.
[a] is an awareness [b] can take many forms [c] particular strategies [d] and cognitive regulation
6406533484139.
[a] is an awareness [b] can take many forms [c] particular strategies [d] and cognitive regulation[z]
6406533484140.
[a] is an awareness [b] can take many forms [c] and cognitive regulation
6406533484141.
None of these.

A published solution is not available for this question yet.

Report a correction for Q150

Question 151 NAT · 3.0 marks

Suppose you are working on prefix language modeling. The sequence length is 32 and the first two tokens represent the task specific prefix. How many non-infinity elements are there in the mask for computing attention scores?

A published solution is not available for this question yet.

Report a correction for Q151

Question 152 MCQ · 3.0 marks

Which of the following components in the data pre-processing pipeline removes pages that contain bad words?
6406533484147.
Language Identification
6406533484148.
Exact Deduplication
6406533484149.
Fuzzy Deduplication
6406533484150.
ML classifiers for quality filtering
6406533484151.
Simple heuristics to detect toxic contents

A published solution is not available for this question yet.

Report a correction for Q152

Question 153 MCQ · 2.0 marks

Which of the following is an important implication of the scaling law:
6406533484152.
Increasing the size of the model only can improve test performance, irrespective of the size of the training data.
6406533484153.
Increasing the size of the data only can improve test performance, irrespective of the size of the model.
6406533484154.
Both the size of the model and that of the data, have to be increased appropriately to improve test performance.
6406533484155.
None of these.

A published solution is not available for this question yet.

Report a correction for Q153

Question 154 MSQ · 3.0 marks

Which of the following are the design choices for building a large language model?
6406533484156.
Activation function in feed forward layer
6406533484157.
Training dataset.
6406533484158.
Positional encoding
6406533484159.
Attention mechanism.
6406533484160.
None of these.

A published solution is not available for this question yet.

Report a correction for Q154

Question 155 MSQ · 3.0 marks

Consider an ideal data preprocessing pipeline to prepare a dataset. Which of the following sentences or sets of paragraphs will NOT pass through the pipeline as it is?
6406533484161.
“You idiot. All those people from the country Sumatrazia are taking our jobs. If I get a chance, I will wipe that country off of the face of the planet.”
6406533484162.
Rajesh is an amazing businessman. He holds a savings account with Dena bank. His phone number is 9876543210.
6406533484163.
Deep learning is a subset of Machine Learning. Deep learning is a subset of Machine Learning.
6406533484164.
India’s space agency ISRO says it has successfully brought back into Earth’s orbit a part of the rocket that carried its historic Moon mission recently.
6406533484165.
Last Saturday, the Board of Control for Cricket in India (BCCI) officially communicated to the International Cricket Council (ICC) its decision to not send a team for the 2025 ICC Champions Trophy to be held in Pakistan from February 19 to March 9.
6406533484166.
None of these.       **i-NLP** **Section Id :** 64065374263 **Section Number :** 9 **Section type :** Online **Mandatory or Optional :** Mandatory **Number of Questions :** 15 **Number of Questions to be attempted :** 15 **Section Marks :** 50 **Display Number Panel :** Yes **Section Negative Marks :** 0 **Group All Questions :** No **Enable Mark as Answered Mark for Review and** No **Clear Response :** **Section Maximum Duration :** 0 **Section Minimum Duration :** 0 **Section Time In :** Minutes **Maximum Instruction Time :** 0

A published solution is not available for this question yet.

Report a correction for Q155