---
license: apache-2.0
datasets:
  - Boobalamurugan/tn-heritage-sites-dataset
language:
  - en
base_model:
  - unsloth/Llama-3.1-8B-unsloth-bnb-4bit
pipeline_tag: text-generation
tags:
  - tamil-heritage
  - open-source
  - cultural-heritage
  - llama3
  - low-resource
  - fine-tuned
---


# 🛕 Tamil Nadu Heritage Knowledge LLM

A domain-specific Language Model dedicated to capturing the rich cultural, architectural, and historical heritage of **Tamil Nadu**. This LLM is fine-tuned on a custom dataset and designed to answer questions or generate content related to Tamil Nadu's temples, history, monuments, and culture.

---

## 🚀 Project Status: Early Development Phase

This project is in its **starting phase**, and we welcome contributors to **expand the dataset, improve the model**, and help build a comprehensive open-source heritage model.

---

## 📦 Base Model

- **Model**: [`unsloth/Llama-3.1-8B-unsloth-bnb-4bit`](https://huggingface.co/unsloth/Llama-3.1-8B-unsloth-bnb-4bit)
- **Type**: 8B parameter model, 4-bit quantized for efficient training and inference.

---

## 🗂 Dataset

- **Source**: [`Boobalamurugan/tn-heritage-sites-dataset`](https://huggingface.co/datasets/Boobalamurugan/tn-heritage-sites-dataset)
- **Size**: ~1.93K entries
- **Description**: This dataset contains information about heritage sites in Tamil Nadu, including temples, historical monuments, kings, architecture, and festivals.

📢 *The dataset is still small. Feel free to contribute and help us grow this valuable resource!*

---

## 🧠 Model Objective

- Build a **knowledgeable and culturally aware assistant** focused on Tamil Nadu heritage.
- Answer factual questions about heritage sites, kings, festivals, inscriptions, architecture, etc.
- Generate informative content or summaries for educational or cultural purposes.

---

## ✨ Features (Planned)

- ✅ Q&A on Tamil Nadu temples, kings, and architecture  
- ✅ Context-aware content generation (e.g., temple descriptions, cultural significance)  
- 🔄 Summarization of historical texts (Coming Soon)  
- 🔄 Integration into web or mobile apps (Planned)

---

## 🤝 How to Contribute

### 📁 Dataset Contributions

- Fork the [dataset repository](https://huggingface.co/datasets/Boobalamurugan/tn-heritage-sites-dataset)
- Add more entries (temples, kings, historical facts)
- Submit a pull request with the added data

### 🧠 Model Training

- Fine-tune the model with additional data
- Improve prompt formatting and pre-processing
- Evaluate the model’s responses

---

## 📝 License

This project is licensed under the **[Apache 2.0 License](LICENSE)** — free for commercial and non-commercial use with proper attribution.

---

## 🌐 Tags

`#tamil-heritage` `#open-source` `#language-model` `#llm` `#tamil-nadu` `#text-generation`

---

## 📬 Stay Connected

For updates and discussions:
- Follow the project creator: [@Boobalamurugan](https://huggingface.co/Boobalamurugan)
- Join our community forum (Coming Soon)