Why different transformers serve different tasks in NLP - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a transformer model for text classification.

NLP

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

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

A"bert-base-uncased"

B"gpt2"

C"t5-small"

D"roberta-base"

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing a model designed for text generation instead of classification.

The bert-base-uncased model is commonly used for sequence classification tasks.

2fill in blank

medium

Complete the code to tokenize input text for a transformer model.

NLP

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

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

A"gpt2"

B"bert-base-uncased"

C"t5-small"

D"distilbert-base-uncased"

Attempts:

3 left

💡 Hint

Common Mistakes

Using a tokenizer that does not match the model architecture.

The tokenizer must match the model. Here, bert-base-uncased tokenizer is used.

3fill in blank

hard

Fix the error in the code to generate text using a transformer model.

NLP

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained([1])
tokenizer = AutoTokenizer.from_pretrained("gpt2")
inputs = tokenizer("Hello, how are you?", return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

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

A"gpt2"

B"roberta-base"

C"t5-small"

D"bert-base-uncased"

Attempts:

3 left

💡 Hint

Common Mistakes

Using a model designed for classification instead of generation.

The gpt2 model is a causal language model suitable for text generation.

4fill in blank

hard

Fill both blanks to create a transformer model and tokenizer for translation.

NLP

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
model = AutoModelForSeq2SeqLM.from_pretrained([1])
tokenizer = AutoTokenizer.from_pretrained([2])
inputs = tokenizer("Translate this sentence.", return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

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

A"t5-small"

B"bert-base-uncased"

D"gpt2"

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing model and tokenizer names from different architectures.

The t5-small model and tokenizer are used for sequence-to-sequence tasks like translation.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that filters tokens by length and converts them to uppercase.

NLP

tokens = ["hello", "to", "world", "a", "transformer"]
filtered = [1]: [2] for token in tokens if len(token) [3] 3

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

Atoken.upper()

Btoken

C>

D<

Attempts:

3 left

💡 Hint

Common Mistakes

Using the wrong comparison operator or swapping key and value.

This comprehension creates a dictionary with keys as uppercase tokens and values as original tokens, only for tokens longer than 3 characters.