Hugging Face fine-tuning in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pretrained model from Hugging Face.

Prompt Engineering / GenAI

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

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

Ascikit-learn

Bpytorch-lightning

Cbert-base-uncased

Dtensorflow

Attempts:

3 left

💡 Hint

Common Mistakes

Using framework names like 'tensorflow' instead of model names.

Confusing model names with unrelated libraries.

The correct model name to load a pretrained BERT model is 'bert-base-uncased'.

2fill in blank

medium

Complete the code to prepare the tokenizer for the model.

Prompt Engineering / GenAI

from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('[1]')

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

Agpt2

Broberta-base

Cdistilbert-base-uncased

Dbert-base-uncased

Attempts:

3 left

💡 Hint

Common Mistakes

Using a tokenizer from a different model family.

Using a tokenizer that does not match the model.

The tokenizer must match the model, so 'bert-base-uncased' is correct here.

3fill in blank

hard

Fix the error in the training loop by completing the missing optimizer step.

Prompt Engineering / GenAI

for batch in train_dataloader:
    outputs = model(**batch)
    loss = outputs.loss
    loss.backward()
    [1]
    optimizer.zero_grad()

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

Aoptimizer.step()

Bloss.step()

Cmodel.step()

Dloss.backward()

Attempts:

3 left

💡 Hint

Common Mistakes

Calling loss.backward() twice.

Calling step() on loss or model instead of optimizer.

After backward(), optimizer.step() updates the model weights.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps words to their lengths only if length is greater than 3.

Prompt Engineering / GenAI

{word: [1] for word in words if len(word) [2] 3}

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

Alen(word)

B<

C>

Dword

Attempts:

3 left

💡 Hint

Common Mistakes

Using the word itself as value instead of its length.

Using '<' instead of '>' in the condition.

We want the length as value and filter words longer than 3 characters.

5fill in blank

hard

Fill all three blanks to create a filtered dictionary with uppercase keys, values as counts, and only include counts greater than 1.

Prompt Engineering / GenAI

filtered_counts = { [1]: [2] for [3], count in counts.items() if count > 1 }

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

Aword.upper()

Bcount

Cword

Dcount.upper()

Attempts:

3 left

💡 Hint

Common Mistakes

Using count.upper() which is invalid for integers.

Swapping keys and values in the dictionary comprehension.

Keys are uppercase words, values are counts, and iteration uses word and count.