GenAI Playground: The Overengineered Linear Regressor's Guide 🚀

Welcome to a toolkit that combines linear regression with advanced MLOps & GenAI techniques. This repository is currently under construction as we explore the solution space. It is being collaboratively developed with contributions from Codeium, CodeLlama via Ollama, ChatGPT-4, and GitHub Copilot. We are primarily focused on the following questions:

1. How can LLMs be used to interpret model results?
2. How can we implement MLOps?
3. How can we optimize this pipeline to eliminate external API dependencies and run entirely locally?
4. Can we somehow simulate a team environment with multiple GPTs? e.g. PM-GPT, DS-GPT, DE-GPT in same conversation

Repository Structure 📂

• data/: Datasets and preprocessing scripts.
• models/: Linear regression models.
• docker/: Dockerfiles and configurations.
• actions/: CI/CD workflows and configurations.
• visualizations/: Data visualization scripts.
• experiments/: Model experiment logs and records.
• utilities/: Utility functions and modules.
• docs/: Documentation.
• tests/: Test suites.

Getting Started 🚀

1. Clone the Repository:

   git clone https://github.com/mburakbozbey/linear-lab.git
   cd linear-lab

2. Create a Conda Environment:

   conda create --name liner_lab_env python=3.8
   conda activate liner_lab_env

3. Install Dependencies:

   pip install -r requirements.txt

4. Run the Linear Regression Model:

   python main.py 

License 📄

This project is licensed under the MIT License.

References 🙏

• Improving Language Understanding by Generative Pre-Training (Radford et al. 2018)
• Attention is All You Need (Vaswani et al. 2017)
• GPT Guide by Andrej Karpathy
• GPT-from-Scratch