lilbablo/finlit-quiz

This project is an AI-powered financial literacy quiz designed to help users build better money habits through realistic scenarios and immediate feedback.

The assistant, named Smart Money, is powered by a fine-tuned Phi-2 model using LoRA (Low-Rank Adaptation). It evaluates your financial decisions and gives witty, sharp explanations when your choices fall short.

---

📦 Included

• cli_quiz.py — Command-line script to run the quiz
• quiz_ready_dataset.jsonl — A custom dataset of 1000+ realistic financial scenarios
• model/ — Fine-tuned Phi-2 model directory (LoRA-merged or base)
• README.md — Project documentation

---

🚀 Quick Start

To run the quiz locally:

```bash pip install torch transformers python3 cli_quiz.py ```

Note: If you are not using a GPU, modify the script to use torch.float32 instead of torch.float16.

---

💡 How It Works

1. You’ll be asked 5 randomly selected financial scenario questions.
2. Choose your best response (multiple choice: a, b, or c).
3. If you’re wrong, Smart Money replies with a witty one-liner.
4. At the end, you receive a final score and personalized summary.

---

🧠 Model Details

• Base Model: Phi-2 by Microsoft
• Fine-Tuning Method: LoRA via peft
• Libraries Used: transformers, torch, json, random
• Inference: Local GPU (tested on 2x RTX 4080)

---

🤖 Why This Matters

Many people lack access to practical, relatable financial education. This project bridges that gap by:

• Using an LLM to simulate a sharp financial coach
• Teaching through interactive, contextual scenarios
• Reinforcing good financial habits with real-time feedback

---

✍️ Created By

@lilbablo — exploring the intersection of AI, financial literacy, and interactive learning.

---

🤝 Contribute

Pull requests welcome! You can:

• Add more scenario questions
• Improve model responses
• Port this to Gradio or Streamlit
• Translate the quiz for international use