Previous Lesson

Session 2 – Practical Introduction to Hugging Face

Objective

By the end of this session, you’ll gain hands-on experience with Hugging Face, understand its capabilities, and solve real-world problems using pre-trained models. Let’s explore how Hugging Face makes cutting-edge AI accessible and practical. ????

Part 1: What is Hugging Face?

Hugging Face is like a library of pre-trained AI models, ready to solve tasks such as text summarization, sentiment analysis, translation, and more.

Why Use Hugging Face?

  1. Ease of Use: No need to train models from scratch.
  2. Diverse Models: Includes models for text, audio, and image tasks.
  3. Open Source: Community-driven, allowing innovation and collaboration.

Real-World Applications

  1. Customer Sentiment Analysis:
    • Example: A company analyzes customer reviews to improve its products.
  2. Text Summarization:
    • Example: News platforms summarize lengthy articles for quick reads.
  3. Chatbot Enhancements:
    • Example: Hugging Face models improve chatbot responses with natural conversations.

Part 2: Setting Up Hugging Face

Step 1: Install the Library

Run the following command in your terminal:

!pip install transformers
Requirement already satisfied: transformers in /usr/local/lib/python3.11/dist-packages (4.47.1)
Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from transformers) (3.17.0)
Requirement already satisfied: huggingface-hub<1.0,>=0.24.0 in /usr/local/lib/python3.11/dist-packages (from transformers) (0.27.1)
Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.11/dist-packages (from transformers) (1.26.4)
Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.11/dist-packages (from transformers) (24.2)
Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.11/dist-packages (from transformers) (6.0.2)
Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.11/dist-packages (from transformers) (2024.11.6)
Requirement already satisfied: requests in /usr/local/lib/python3.11/dist-packages (from transformers) (2.32.3)
Requirement already satisfied: tokenizers<0.22,>=0.21 in /usr/local/lib/python3.11/dist-packages (from transformers) (0.21.0)
Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.11/dist-packages (from transformers) (0.5.2)
Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.11/dist-packages (from transformers) (4.67.1)
Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub<1.0,>=0.24.0->transformers) (2024.10.0)
Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub<1.0,>=0.24.0->transformers) (4.12.2)
Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests->transformers) (3.4.1)
Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests->transformers) (3.10)
Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests->transformers) (2.3.0)
Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests->transformers) (2024.12.14)

Step 2: Importing Hugging Face Tools

from transformers import pipeline

Part 3: Hands-On Activities

Activity 1: Sentiment Analysis

Analyze customer reviews to determine sentiment.

Code Example

from transformers import pipeline

# Load a pre-trained sentiment analysis pipeline
sentiment_analyzer = pipeline("sentiment-analysis")

# Input text
text = "The product quality is amazing! Highly recommend it."

# Analyze sentiment
result = sentiment_analyzer(text)

print("Sentiment:", result[0]['label'])
print("Confidence Score:", result[0]['score'])

No model was supplied, defaulted to distilbert/distilbert-base-uncased-finetuned-sst-2-english and revision 714eb0f (https://huggingface.co/distilbert/distilbert-base-uncased-finetuned-sst-2-english).
Using a pipeline without specifying a model name and revision in production is not recommended.
Device set to use cpu
Sentiment: POSITIVE
Confidence Score: 0.9998847246170044

Output:

Sentiment: POSITIVE

Confidence Score: 0.99987

Activity 2: Text Summarization

Summarize long articles or text passages.

Code Example

from transformers import pipeline

# Load a pre-trained summarization pipeline
summarizer = pipeline("summarization")

# Input text
article = """
The rapid advancements in AI have revolutionized multiple industries,
from healthcare to finance. By leveraging machine learning, organizations
are automating processes and uncovering insights like never before.
"""

# Generate summary
summary = summarizer(article, max_length=50, min_length=20, do_sample=False)

print("Summary:", summary[0]['summary_text'])

No model was supplied, defaulted to sshleifer/distilbart-cnn-12-6 and revision a4f8f3e (https://huggingface.co/sshleifer/distilbart-cnn-12-6).
Using a pipeline without specifying a model name and revision in production is not recommended.
Device set to use cpu
Your max_length is set to 50, but your input_length is only 41. Since this is a summarization task, where outputs shorter than the input are typically wanted, you might consider decreasing max_length manually, e.g. summarizer('...', max_length=20)
Summary:  The rapid advancements in AI have revolutionized multiple industries, from healthcare to finance . By leveraging machine learning, organizations are automating processes and uncovering insights like never before .

Output:

“AI advancements have transformed industries, automating processes and providing new insights.”

Activity 3: Question-Answering

Answer questions based on a given context.

Code Example

from transformers import pipeline

# Load a pre-trained question-answering pipeline
qa = pipeline("question-answering")

# Input context
context = """
The Eiffel Tower is a wrought-iron lattice tower in Paris, France.
It was named after the engineer Gustave Eiffel, whose company designed and built the tower.
"""

# Ask a question
question = "Who designed the Eiffel Tower?"

# Get the answer
answer = qa(question=question, context=context)

print("Answer:", answer['answer'])

No model was supplied, defaulted to distilbert/distilbert-base-cased-distilled-squad and revision 564e9b5 (https://huggingface.co/distilbert/distilbert-base-cased-distilled-squad).
Using a pipeline without specifying a model name and revision in production is not recommended.
Device set to use cpu
Answer: Gustave Eiffel

Output:

“Gustave Eiffel”

Part 4: Solving Real-World Problems

Problem: Analyzing Product Reviews

  • Use Hugging Face to extract sentiment from hundreds of customer reviews in seconds.
  • Example Code: Use sentiment-analysis pipeline in a loop to process multiple reviews.

Part 5: Discussion

Q: What Makes Hugging Face Powerful?

  1. Pre-trained models reduce time and effort.
  2. Flexible pipelines for various AI tasks.
  3. Open-source community fosters innovation.

Q: What Are Its Challenges?

  1. Large models may require powerful hardware.
  2. Fine-tuning models for specific tasks can be complex.

Part 6: Wrap-Up & Reflection

What We Learned

  • Overview of Hugging Face and its tools.
  • Real-world applications like sentiment analysis and text summarization.
  • Practical coding activities to solve real-world problems.

Quick Activity

  • Which Hugging Face model intrigued you the most and why?
  • Share ideas for how it can be applied to a specific domain like education or healthcare.