Welcome to the "Sudoku with Large Language Models" repository! This repository contains Jupyter notebooks and Python files that accompany a tutorial series on my blog about playing Sudoku with large language models (LLMs). The goal of this project is to help users gain a better understanding of LLMs by exploring their capabilities in solving Sudoku puzzles.
To get started with the code in this repository, follow the instructions below.
- Python (version 3.10+)
- Jupyter Notebook
- Clone the repository:
git clone https://github.com/aniemerg/sudoku.git- Navigate to the repository directory:
cd sudoku-llm- Install the required dependencies:
pip install -r requirements.txtThe repository includes the following Jupyter notebooks:
Sudoku-Basics.ipynb: Basics of playing 4x4 sudoku with an LLM.Sudoku-First Evals.ipynb: Evaluating GPT-3.5 and GPT-4 on 4x4 sudoku.Sudoku-First Train.ipynb: Training GPT-3.5 to better play 4x4 sudoku.
Each notebook corresponds to a specific blog post in the tutorial series and provides code examples and explanations.
To follow along with the tutorial and gain a deeper understanding of the concepts, please refer to the blog posts:
The blog posts provide detailed explanations, insights, and additional context for the code in this repository.
While contributions to this repository are not actively sought, if you have any suggestions, improvements, or bug fixes, feel free to open an issue on the GitHub repository.
This project is licensed under the MIT License. See the LICENSE file for more information.
Happy exploring and learning about Sudoku with Large Language Models!