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.

Practice

1. What is the main purpose of the AutoTokenizer class in Hugging Face integration with PyTorch?

easy

A. To visualize model predictions

B. To convert raw text into tokens that the model can understand

C. To train a new language model from scratch

D. To save the model weights to disk

Solution

1. Step 1: Understand the role of tokenization

   Tokenization breaks down raw text into smaller pieces called tokens, which models use as input.

2. Step 2: Identify what AutoTokenizer does

   AutoTokenizer automatically loads the correct tokenizer for a given pretrained model to convert text into tokens.

3. Final Answer:

   To convert raw text into tokens that the model can understand -> Option B

4. Quick Check:

   AutoTokenizer = text to tokens [OK]

Hint: Tokenizer = text to tokens for model input [OK]

Common Mistakes:

• Confusing tokenizer with model training
• Thinking tokenizer saves model weights
• Assuming tokenizer visualizes outputs

2. Which of the following is the correct way to load a pretrained model using Hugging Face's AutoModel in PyTorch?

easy

A. model = AutoModel.from_pretrained('bert-base-uncased')

B. model = AutoModel.load('bert-base-uncased')

C. model = AutoModel('bert-base-uncased')

D. model = AutoModel.pretrained('bert-base-uncased')

Solution

1. Step 1: Recall the correct method to load pretrained models

   Hugging Face uses the from_pretrained method to load pretrained weights and configuration.

2. Step 2: Match the correct syntax

   The correct syntax is AutoModel.from_pretrained('model_name').

3. Final Answer:

   model = AutoModel.from_pretrained('bert-base-uncased') -> Option A

4. Quick Check:

   Load model with from_pretrained() [OK]

Hint: Use from_pretrained() to load models [OK]

Common Mistakes:

• Using .load() instead of .from_pretrained()
• Calling AutoModel like a function
• Using non-existent .pretrained() method

3. Given the following code snippet, what will be the shape of outputs.last_hidden_state?

from transformers import AutoTokenizer, AutoModel
import torch

tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
model = AutoModel.from_pretrained('bert-base-uncased')

inputs = tokenizer('Hello world!', return_tensors='pt')
outputs = model(**inputs)

medium

A. [2, 768]

B. [1, 768]

C. [1, 5, 768]

D. [768, 2]

Solution

1. Step 1: Understand the tokenizer output

   The tokenizer returns input IDs with shape [batch_size, sequence_length]. Here batch_size=1 and sequence_length=5 (tokens: [CLS], 'hello', 'world', '!', [SEP]).

2. Step 2: Understand model output shape

   The model outputs last_hidden_state with shape [batch_size, sequence_length, hidden_size]. For BERT base, hidden_size=768.

3. Final Answer:

   [1, 5, 768] -> Option C

4. Quick Check:

   Output shape = [batch, tokens, features] = [1, 5, 768] [OK]

Hint: Output shape = batch x tokens x hidden size [OK]

Common Mistakes:

• Confusing sequence length with batch size
• Ignoring hidden size dimension
• Assuming output shape is 2D instead of 3D

4. Identify the error in this Hugging Face PyTorch code snippet:

from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
model = AutoModel.from_pretrained('bert-base-uncased')

inputs = tokenizer('Test input', return_tensors='pt')
outputs = model(inputs)
print(outputs)

medium

A. Missing .to(device) to move inputs to GPU

B. AutoModel cannot be used with BERT models

C. Tokenizer should use return_tensors='tf' instead of 'pt'

D. Model should be called with unpacked inputs: model(**inputs)

Solution

1. Step 1: Check how model is called

   The model expects keyword arguments, so inputs must be unpacked with ** to pass input_ids and attention_mask correctly.

2. Step 2: Identify the fix

   Change model(inputs) to model(**inputs) to avoid errors.

3. Final Answer:

   Model should be called with unpacked inputs: model(**inputs) -> Option D

4. Quick Check:

   Use **inputs when calling model [OK]

Hint: Call model with model(**inputs) not model(inputs) [OK]

Common Mistakes:

• Passing inputs as a single dict argument
• Confusing PyTorch and TensorFlow tensor types
• Thinking AutoModel can't load BERT

5. You want to classify text into positive or negative sentiment using a Hugging Face model in PyTorch. After tokenizing and running the model, which step correctly converts raw model outputs into class probabilities?

hard

A. Apply torch.softmax on the model's logits output

B. Use torch.argmax directly on tokenized inputs

C. Call model.eval() to get probabilities

D. Normalize input tokens before feeding to the model

Solution

1. Step 1: Understand model output for classification

   Models output raw scores called logits for each class, which are not probabilities.

2. Step 2: Convert logits to probabilities

   Applying torch.softmax on logits converts them into probabilities summing to 1.

3. Final Answer:

   Apply torch.softmax on the model's logits output -> Option A

4. Quick Check:

   Softmax = logits to probabilities [OK]

Hint: Use softmax on logits to get probabilities [OK]

Common Mistakes:

• Using argmax on inputs instead of outputs
• Confusing model.eval() with probability conversion
• Normalizing inputs instead of outputs