An open-source project to build a Question-Answering system for Tamil Wikipedia content using a 3B-parameter language model fine-tuned with retrieval-augmented generation (RAG).

🎯 Quick Overview

This project scrapes Tamil Wikipedia, fine-tunes a lightweight language model, and deploys it as a RAG-based QA system that can answer questions about Tamil topics. Key Features:

🔍 Automatic scraping of ~200K Tamil Wikipedia articles 🧠… See the full description on the dataset page: https://huggingface.co/datasets/muraliwebworld/videxpulse-tamil-wiki-qa-200k.