Hugging Face integration basics in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pretrained Hugging Face model.

PyTorch

from transformers import AutoModel
model = AutoModel.[1]('bert-base-uncased')

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

Acreate

Bfrom_pretrained

Cinit_model

Dload_model

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'load_model' which is not a Hugging Face method.

Using 'init_model' which does not exist in transformers.

Using 'create' which is not a valid method.

The method to load a pretrained model from Hugging Face is 'from_pretrained'.

2fill in blank

medium

Complete the code to tokenize input text using a Hugging Face tokenizer.

PyTorch

from transformers import AutoTokenizer
tokenizer = AutoTokenizer.[1]('bert-base-uncased')
tokens = tokenizer('Hello world!')

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

Aload

Binit

Cfrom_pretrained

Dcreate_tokenizer

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'load' which is not a valid method.

Using 'init' which does not exist.

Using 'create_tokenizer' which is not a transformers method.

Tokenizers are loaded with 'from_pretrained' method to match the model.

3fill in blank

hard

Fix the error in the code to get model outputs from tokenized inputs.

PyTorch

outputs = model([1])

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

Ainputs

Btokenizer

Ctokens

Dtokenizer('Hello world!')

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the tokenizer object instead of tokenized inputs.

Passing raw tokens without converting to tensors.

Passing the tokenizer call directly without saving to a variable.

The model expects a dictionary of inputs, usually named 'inputs' after tokenization with return_tensors.

4fill in blank

hard

Fill both blanks to tokenize text with padding and convert to tensors.

PyTorch

inputs = tokenizer('Hello Hugging Face!', [1]=True, [2]='pt')

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

Apadding

Btruncation

Creturn_tensors

Dmax_length

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'truncation' instead of 'padding' for padding.

Using 'max_length' without padding.

Using 'pt' as a boolean instead of a string for return_tensors.

To pad sequences and get PyTorch tensors, use padding=True and return_tensors='pt'.

5fill in blank

hard

Fill all three blanks to extract the last hidden state from model outputs.

PyTorch

outputs = model(inputs)
last_hidden_state = outputs.[1]
print(last_hidden_state.[2])
print(last_hidden_state.shape[[3]])

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

Alast_hidden_state

Bdetach()

C0

Dhidden_states

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'hidden_states' which is not directly returned unless configured.

Printing tensor without detach causing gradient tracking.

Using wrong shape index.

The model output has 'last_hidden_state' attribute. Use detach() to get tensor without gradient. Shape index 0 is batch size.

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