Model selection (GPT-4, GPT-3.5) in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to select the GPT-4 model for generating text.

Prompt Engineering / GenAI

model = "[1]"

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

Agpt-3.5-turbo

Bcurie

Cgpt-4

Ddavinci

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing 'gpt-3.5-turbo' instead of 'gpt-4'.

Using older model names like 'davinci' or 'curie'.

The GPT-4 model is selected by setting the model string to "gpt-4".

2fill in blank

medium

Complete the code to set the temperature parameter for more creative responses.

Prompt Engineering / GenAI

response = openai.ChatCompletion.create(model="gpt-4", temperature=[1], messages=messages)

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

A0.7

B0.0

C1.5

D-0.5

Attempts:

3 left

💡 Hint

Common Mistakes

Using a temperature like 1.5, which produces overly random output.

Setting temperature to 0.0, which makes output very deterministic.

A temperature of 0.7 encourages creativity without being too random.

3fill in blank

hard

Fix the error in the code to correctly select GPT-3.5 model.

Prompt Engineering / GenAI

model_name = "[1]"

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

Agpt-4

Btext-davinci-003

Cgpt-3

Dgpt-3.5-turbo

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'gpt-4' instead of GPT-3.5.

Using older names like 'text-davinci-003'.

The correct model name for GPT-3.5 is 'gpt-3.5-turbo'.

4fill in blank

hard

Fill both blanks to create a dictionary with model and max tokens for GPT-4.

Prompt Engineering / GenAI

config = {"model": "[1]", "max_tokens": [2]

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

Agpt-4

Bgpt-3.5-turbo

C8192

D4096

Attempts:

3 left

💡 Hint

Common Mistakes

Using GPT-3.5 model name with GPT-4 max tokens.

Setting max tokens too low for GPT-4.

GPT-4 supports max_tokens up to 8192, so model is 'gpt-4' and max_tokens is 8192.

5fill in blank

hard

Fill all three blanks to create a request with GPT-3.5, temperature 0.5, and max tokens 4096.

Prompt Engineering / GenAI

response = openai.ChatCompletion.create(model="[1]", temperature=[2], max_tokens=[3], messages=messages)

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

Agpt-4

B0.5

C4096

Dgpt-3.5-turbo

Attempts:

3 left

💡 Hint

Common Mistakes

Using GPT-4 model name instead of GPT-3.5.

Setting temperature too high or too low.

Using max tokens not supported by GPT-3.5.

The request uses GPT-3.5 model 'gpt-3.5-turbo', temperature 0.5 for moderate creativity, and max_tokens 4096.