Historical QA using Llama-2 7B Chat (HuggingFace Transformers)

This project demonstrates how to use the Llama-2-7B-Chat model to answer questions based on a provided text corpus.
It loads the model, processes a historical document, and generates an answer to the user's question using causal language modeling.

---

🚀 Features

• Uses Llama-2-7B-Chat via HuggingFace Transformers
• Accepts user questions dynamically
• Provides context-aware answers using your custom text corpus
• Runs automatically on GPU if available
• Clean decoded output without prompt repetition

---

📦 Requirements

Install dependencies:

pip install -r requirements.txt