Content writing assistance in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained language model for content writing assistance.

Prompt Engineering / GenAI

from transformers import [1]
model = [1].from_pretrained('gpt2')

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

AGPT2Model

BGPT2Tokenizer

CBertModel

DGPT2LMHeadModel

Attempts:

3 left

💡 Hint

Common Mistakes

Using GPT2Tokenizer instead of GPT2LMHeadModel

Using BertModel which is a different architecture

We use GPT2LMHeadModel to load the GPT-2 model with language modeling head for text generation.

2fill in blank

medium

Complete the code to tokenize input text for the model.

Prompt Engineering / GenAI

from transformers import GPT2Tokenizer
tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
inputs = tokenizer('[1]', return_tensors='pt')

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

AHello, how are you?

Btokenize this text

CGenerate content

DSample input

Attempts:

3 left

💡 Hint

Common Mistakes

Passing variable names instead of string literals

Using empty strings or non-text inputs

We provide a sample input text like 'Hello, how are you?' to tokenize for the model.

3fill in blank

hard

Fix the error in the code to generate text from the model.

Prompt Engineering / GenAI

outputs = model.generate([1]['input_ids'], max_length=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

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

Ainputs

Binput

Ctokens

Dtext

Attempts:

3 left

💡 Hint

Common Mistakes

Using undefined variable names like 'input' or 'tokens'

Passing raw text instead of token ids

The tokenized inputs are stored in 'inputs', so we use inputs['input_ids'] to generate text.

4fill in blank

hard

Fill both blanks to create a function that generates content given a prompt.

Prompt Engineering / GenAI

def generate_content(prompt):
    inputs = tokenizer([1], return_tensors='pt')
    outputs = model.generate(inputs[[2]], max_length=100)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

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

Aprompt

Binput_ids

Cattention_mask

Dtext

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'text' instead of 'prompt' as input

Using 'attention_mask' for generation input

We pass the prompt string to tokenizer and use 'input_ids' key for generation.

5fill in blank

hard

Fill all three blanks to create a pipeline for content writing assistance.

Prompt Engineering / GenAI

from transformers import pipeline
content_generator = pipeline('[1]', model='gpt2')
result = content_generator('[2]', max_length=[3])
print(result[0]['generated_text'])

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

Atext-generation

BWrite a short story

C50

Dtext-classification

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'text-classification' instead of 'text-generation'

Passing numeric prompt instead of string

Setting max_length too low or missing

We use 'text-generation' pipeline with a prompt and max_length for output length.