Generative AI with Large Language Models: Dialogue Summarization Lab

Description

Welcome to the Dialogue Summarization Lab, part of the "Generative AI with Large Language Models" course by AWS and DeepLearning.AI! This project showcases the power of FLAN-T5 in summarizing conversations using various prompt engineering techniques. Dive into the world of natural language processing and experience firsthand how large language models can transform raw dialogues into concise, meaningful summaries.

Table of Contents

• Installation
• Usage
• Features
• Contributing
• License
• Acknowledgements

Installation

To get started with this lab, follow these steps:

1. Clone the repository:

   git clone https://github.com/azaynul10/generative-ai-llm-dialogue-summarization.git

2. Navigate to the project directory:

   cd generative-ai-llm-dialogue-summarization

3. Install the required dependencies:

   pip install torch torchdata transformers datasets

Usage

1. Open the Jupyter notebook in the lab1 directory.
2. Run the cells to load the DialogSum dataset and initialize the FLAN-T5 model.
3. Experiment with different prompt engineering techniques:
   • Zero-shot learning
   • One-shot learning
   • Few-shot learning
4. Adjust the sampling temperature to see how it affects the generated summaries.
5. Analyze the results and compare the effectiveness of different approaches.

Features

• FLAN-T5 Model: Utilize the powerful FLAN-T5 model for dialogue summarization.
• DialogSum Dataset: Work with a rich, public dataset of conversations.
• Prompt Engineering: Explore zero-shot, one-shot, and few-shot learning techniques.
• Customizable Parameters: Experiment with sampling temperature and other settings.
• Python-based: Leverages popular libraries like PyTorch, Transformers, and Datasets.

Contributing

We welcome contributions to improve this lab! Here's how you can help:

1. Fork the repository
2. Create your feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgements

• AWS and DeepLearning.AI for creating this insightful course
• Hugging Face for providing the Transformers library and FLAN-T5 model
• The creators of the DialogSum dataset

Happy summarizing! 🚀📚