VectorMind 🧠

A Private, Offline, and Local Text Generation Engine.

VectorMind is a project designed to run and fine-tune Large Language Models (LLMs) locally. Built for privacy and performance, it requires zero API keys and zero internet connection.

🚀 Features

• 100% Local: Runs on your CPU/GPU using distilgpt2.
• Libre AI: No accounts, no tracking, no subscription.
• Prepa-Ready: Designed to be fine-tuned on academic and engineering data.

🛠 Installation

1. Clone the repo: git clone https://github.com/abdelkabirouadoukou/VectorMind.git
2. Install dependencies: pip install -r requirements.txt
3. Run: python main.py

🧪 Future Roadmap

• Implement Fine-Tuning on Physics & Math notes.
• Quantization for faster performance on laptops.
• Integration with Proofly (Agentic Memory Layer).