Hugging Face integration basics in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of Hugging Face tokenizer usage

What is the output of the following code snippet that uses a Hugging Face tokenizer to tokenize a sentence?

PyTorch

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
inputs = tokenizer('Hello world!', return_tensors='pt')
print(inputs['input_ids'].tolist())

A [[7592, 2088, 999]]

B [[101, 7592, 2088, 999, 102]]

C [[101, 7592, 2088, 999]]

D [[101, 7592, 2088, 102]]

💡 Hint

Remember that BERT tokenizers add special tokens at the start and end.

The BERT tokenizer adds [CLS] token (101) at the start and [SEP] token (102) at the end. The tokens for 'Hello' and 'world' are 7592 and 2088, and '!' is 999.

❓ Model Choice

intermediate

Choosing the correct Hugging Face model for text classification

You want to perform sentiment analysis on movie reviews using Hugging Face. Which model is best suited for this task?

A distilbert-base-uncased-finetuned-sst-2-english

B bert-base-uncased

C roberta-base

D gpt2

💡 Hint

Look for a model fine-tuned for sentiment analysis.

Option A is a DistilBERT model fine-tuned on the SST-2 dataset for sentiment analysis, making it the best choice.

❓ Hyperparameter

advanced

Effect of batch size on Hugging Face model training

During fine-tuning a Hugging Face transformer model, what is the main effect of increasing the batch size?

A It decreases the learning rate automatically.

B It increases the model's ability to generalize by adding noise to gradients.

C It always improves model accuracy regardless of dataset size.

D It reduces training time per epoch but may require more memory.

💡 Hint

Think about computational resources and speed.

Increasing batch size processes more samples at once, speeding up training but using more memory. It does not guarantee better accuracy or change learning rate automatically.

❓ Metrics

advanced

Correct metric for evaluating Hugging Face text generation

Which metric is most appropriate to evaluate the quality of text generated by a Hugging Face language model?

A BLEU score

B F1 score

C Accuracy

D Mean Squared Error

💡 Hint

Consider metrics used in machine translation and text generation.

BLEU score measures how closely generated text matches reference text, commonly used for evaluating text generation quality.

🔧 Debug

expert

Identifying error in Hugging Face model loading code

What error will this code raise when trying to load a Hugging Face model and tokenizer?

PyTorch

from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained('bert-base-uncased')
tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
inputs = tokenizer('Test input', return_tensors='pt')
outputs = model(inputs)

A RuntimeError: CUDA out of memory

B ValueError: Invalid model name

C TypeError: forward() missing 1 required positional argument: 'input_ids'

D No error, code runs successfully

💡 Hint

Check how the model expects inputs.

The model expects input tensors as keyword arguments like input_ids, but inputs is passed as a single positional argument causing a TypeError.