Neurosymbolic Large Language Model (LLM) Project

Overview

This repository contains the code and resources for a project that aims to combine the capabilities of modern Large Language Models (LLMs) with symbolic reasoning to improve text summarization.

Project Structure

• preprocessing/: Contains scripts to preprocess data specific to each LLM.
• evaluation/: Contains scripts for model evaluation.
• training_*.py: Scripts for training specific LLMs on the summarization task.

Requirements

• Python 3.7 or above
• PyTorch
• HuggingFace Transformers
• Additional libraries are listed in requirements.txt.

Setup

1. Clone the repository:

git clone https://github.com/Hicham-Yezza/Neurosymbolic-LLM-Project.git

2. Navigate to the project directory:

cd Neurosymbolic-LLM-Project

3. Install the required libraries:

pip install -r requirements.txt

Usage

Detailed usage instructions for preprocessing, training, and evaluation will be provided as the project progresses.

Author

• Hicham Yezza

License

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

Acknowledgements