Hugging Face integration basics in PyTorch - Model Pipeline Trace

Model Pipeline - Hugging Face integration basics

This pipeline shows how to use Hugging Face Transformers with PyTorch to train a text classification model. It covers loading data, tokenizing text, training a model, and making predictions.

Data Flow - 5 Stages

1Load raw text data

1000 rows x 1 column→Load dataset with text and labels→1000 rows x 2 columns

{"text": "I love this movie!", "label": 1}

↓

2Tokenization

1000 rows x 1 column→Convert text to token IDs using Hugging Face tokenizer→1000 rows x 128 tokens

[101, 1045, 2293, 2023, 3185, 999, 102, 0, 0, ...]

↓

3Create PyTorch Dataset and DataLoader

1000 rows x 128 tokens→Prepare batches for training→Batches of size 16 x 128 tokens

Batch tensor shape: (16, 128)

↓

4Model Training

Batch tensor shape: (16, 128)→Fine-tune pretrained transformer model→Batch predictions shape: (16, 2)

Logits tensor: [[2.1, -1.3], [0.5, 1.2], ...]

↓

5Evaluation and Prediction

Batch predictions shape: (16, 2)→Calculate accuracy and make label predictions→Predicted labels shape: (16,)

[1, 0, 1, 1, 0, ...]

Training Trace - Epoch by Epoch

Loss
0.7 |*       
0.6 | **     
0.5 |  ***   
0.4 |    ****
0.3 |     *****
    +---------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.65	0.60	Model starts learning, loss decreases from random.
2	0.48	0.75	Loss decreases, accuracy improves as model learns.
3	0.35	0.82	Model converges with better accuracy and lower loss.
4	0.30	0.85	Slight improvement, model stabilizes.
5	0.28	0.87	Final epoch shows best performance.

Prediction Trace - 5 Layers

Layer 1: Input text

Layer 2: Tokenizer

Layer 3: Model forward pass

Layer 4: Softmax activation

Layer 5: Prediction

Model Quiz - 3 Questions

What does the tokenizer do in the data flow?

A Calculates accuracy of predictions

B Converts text into numbers the model can understand

C Trains the model on labeled data

D Splits data into training and test sets

Key Insight

Using Hugging Face Transformers with PyTorch simplifies text classification by handling tokenization and pretrained models. The training trace shows how the model learns by reducing loss and improving accuracy. Softmax converts model outputs into understandable probabilities 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