Top-p and top-k sampling in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to set the top-k value for sampling.

Prompt Engineering / GenAI

top_k = [1]

Drag options to blanks, or click blank then click option'

A0.9

B50

C1000

DNone

Attempts:

3 left

💡 Hint

Common Mistakes

Using a float value like 0.9 for top-k instead of an integer.

Setting top-k to None disables it, not sets a value.

Top-k sampling uses an integer value to limit the number of tokens considered. Here, 50 means only the top 50 tokens are sampled from.

2fill in blank

medium

Complete the code to set the top-p value for nucleus sampling.

Prompt Engineering / GenAI

top_p = [1]

Drag options to blanks, or click blank then click option'

A50

B100

C0.9

DNone

Attempts:

3 left

💡 Hint

Common Mistakes

Using an integer like 50 for top-p instead of a float.

Setting top-p to None disables it, not sets a value.

Top-p sampling uses a probability threshold between 0 and 1. Here, 0.9 means sampling from tokens whose cumulative probability is at least 90%.

3fill in blank

hard

Fix the error in the code to apply top-k sampling correctly.

Prompt Engineering / GenAI

output = model.generate(input_ids, do_sample=True, top_k=[1])

Drag options to blanks, or click blank then click option'

ATrue

BNone

C0.9

D50

Attempts:

3 left

💡 Hint

Common Mistakes

Passing a float like 0.9 causes an error.

Passing None disables top-k but does not apply sampling.

Top-k must be an integer specifying how many top tokens to sample from. 50 is a valid integer value.

4fill in blank

hard

Fill both blanks to apply top-p and top-k sampling together.

Prompt Engineering / GenAI

output = model.generate(input_ids, do_sample=True, top_k=[1], top_p=[2])

Drag options to blanks, or click blank then click option'

A50

B0.9

C0.8

D100

Attempts:

3 left

💡 Hint

Common Mistakes

Swapping top-k and top-p values.

Using floats for top-k or integers for top-p.

Top-k is set to 50 tokens, and top-p is set to 0.9 probability threshold. Both control sampling diversity.

5fill in blank

hard

Fill all three blanks to create a dictionary of sampling parameters with top-k, top-p, and temperature.

Prompt Engineering / GenAI

sampling_params = {'top_k': [1], 'top_p': [2], 'temperature': [3]

Drag options to blanks, or click blank then click option'

A40

B0.85

C1.0

D0.7

Attempts:

3 left

💡 Hint

Common Mistakes

Using temperature as an integer.

Mixing up top-p and temperature values.

Top-k is 40 tokens, top-p is 0.85 probability, and temperature is 0.7 to control randomness.