Language modeling concept in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained language model using Hugging Face Transformers.

NLP

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

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

A"bert-base-uncased"

B"gpt2"

C"resnet50"

D"vgg16"

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing BERT which is not a causal language model.

Selecting image models like ResNet or VGG.

The correct model for language modeling here is "gpt2", which is a causal language model. BERT is not a causal LM, and ResNet/VGG are image models.

2fill in blank

medium

Complete the code to tokenize input text for the language model.

NLP

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

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

A['Hello, how are you?']

B12345

C"Hello, how are you?"

DNone

Attempts:

3 left

💡 Hint

Common Mistakes

Passing a list instead of a string.

Passing a number or None.

The tokenizer expects a string input for text. Passing a string like "Hello, how are you?" is correct. Passing a list or number is incorrect here.

3fill in blank

hard

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

NLP

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

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

Ainputs

Binputs['token_type_ids']

Cinputs['attention_mask']

Dinputs['input_ids']

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the entire inputs dictionary instead of input_ids.

Passing attention_mask or token_type_ids instead of input_ids.

The generate method requires input IDs tensor, which is accessed by inputs['input_ids']. Passing the whole inputs dict or other keys causes errors.

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.

NLP

word_lengths = {word: [1] for word in words if [2]

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

Alen(word)

Bword

Clen(word) > 3

Dword > 3

Attempts:

3 left

💡 Hint

Common Mistakes

Using the word itself as the value instead of its length.

Checking if the word string is greater than 3 instead of length.

The dictionary comprehension maps each word to its length (len(word)) only if the length is greater than 3 (len(word) > 3).

5fill in blank

hard

Fill all three blanks to create a filtered dictionary of words with length greater than 4 and convert keys to uppercase.

NLP

filtered = [1]: [2] for [3] in words if len([3]) > 4}

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

Aword.upper()

Bword

Dlen(word)

Attempts:

3 left

💡 Hint

Common Mistakes

Using different variable names inconsistently.

Not converting keys to uppercase.

The dictionary comprehension uses the uppercase word as key (word.upper()), the original word as value, and iterates over 'word' in words.