/numeracy

Primary LanguagePython

Numerical Comprehension in LLMs

Introduction

This project explores the capability of Large Language Models (LLMs), particularly BERT-based models, to understand and perform arithmetic tasks involving numerals.

Datasets

Fine-Tuning Parameters

  • Epochs: 10
  • Batch size: 32
  • Learning rate: Started at

Installation

To set up the project, follow these steps:

  1. Clone the repository:
git clone http://github.com/abbassix/numeracy

(optional) 1½. Create a virtual environment:

python3.10 -m venv .venv

1½.a. On Windows:

.venv\Scripts\activate

1½.b. On macOS/Linux:

source .venv/bin/activate
  1. Install the required dependencies:
pip install -r requirements.txt