Hugging Face integration basics in PyTorch

Introduction

Hugging Face makes it easy to use powerful language models without building them from scratch.

You want to quickly try a pre-trained language model for text classification.

You need to generate text like writing a story or answering questions.

You want to fine-tune a model on your own small dataset.

You want to use state-of-the-art models without deep knowledge of their internals.

Syntax

PyTorch

from transformers import AutoModelForSequenceClassification, AutoTokenizer
import torch

# Load tokenizer and model
model_name = 'distilbert-base-uncased-finetuned-sst-2-english'
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

# Prepare input text
inputs = tokenizer('I love learning AI!', return_tensors='pt')

# Get model output
outputs = model(**inputs)

# Get prediction
predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)

Use AutoTokenizer and AutoModel classes to load pre-trained models easily.

Return tensors in PyTorch format with return_tensors='pt' for compatibility.

Examples

Load a base BERT model and tokenizer for classification tasks.

PyTorch

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

Tokenize text with padding and truncation for batch processing.

PyTorch

inputs = tokenizer('Hello world!', padding=True, truncation=True, return_tensors='pt')

Run the model on inputs and get raw prediction scores (logits).

PyTorch

outputs = model(**inputs)
logits = outputs.logits

Sample Model

This program loads a pre-trained sentiment analysis model, tokenizes input text, runs the model, and prints the predicted sentiment with confidence scores.

PyTorch

from transformers import AutoModelForSequenceClassification, AutoTokenizer
import torch

model_name = 'distilbert-base-uncased-finetuned-sst-2-english'
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

text = 'I love learning AI!'
inputs = tokenizer(text, return_tensors='pt')
outputs = model(**inputs)
predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)

labels = ['negative', 'positive']
predicted_label = labels[predictions.argmax()]

print(f'Text: {text}')
print(f'Predicted sentiment: {predicted_label}')
print(f'Confidence scores: {predictions.detach().numpy()}')

Important Notes

Hugging Face models come with pre-trained weights ready to use.

Always use the matching tokenizer for the model to ensure correct input formatting.

Softmax converts raw scores to probabilities that sum to 1.

Summary

Hugging Face lets you load and use powerful language models easily.

Use AutoTokenizer and AutoModel classes to handle tokenization and model loading.

Run the model on tokenized inputs and interpret outputs with softmax for predictions.

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