Instructions to use Boobalamurugan/TN_Heritage_LLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Boobalamurugan/TN_Heritage_LLM with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Boobalamurugan/TN_Heritage_LLM",
	filename="unsloth.F16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Boobalamurugan/TN_Heritage_LLM with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Boobalamurugan/TN_Heritage_LLM:F16
# Run inference directly in the terminal:
llama cli -hf Boobalamurugan/TN_Heritage_LLM:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Boobalamurugan/TN_Heritage_LLM:F16
# Run inference directly in the terminal:
llama cli -hf Boobalamurugan/TN_Heritage_LLM:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Boobalamurugan/TN_Heritage_LLM:F16
# Run inference directly in the terminal:
./llama-cli -hf Boobalamurugan/TN_Heritage_LLM:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Boobalamurugan/TN_Heritage_LLM:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Boobalamurugan/TN_Heritage_LLM:F16

Use Docker

docker model run hf.co/Boobalamurugan/TN_Heritage_LLM:F16

LM Studio
Jan

vLLM

How to use Boobalamurugan/TN_Heritage_LLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Boobalamurugan/TN_Heritage_LLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Boobalamurugan/TN_Heritage_LLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Boobalamurugan/TN_Heritage_LLM:F16

Ollama
How to use Boobalamurugan/TN_Heritage_LLM with Ollama:
```
ollama run hf.co/Boobalamurugan/TN_Heritage_LLM:F16
```

Unsloth Studio

How to use Boobalamurugan/TN_Heritage_LLM with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Boobalamurugan/TN_Heritage_LLM to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Boobalamurugan/TN_Heritage_LLM to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Boobalamurugan/TN_Heritage_LLM to start chatting

Atomic Chat new
Docker Model Runner
How to use Boobalamurugan/TN_Heritage_LLM with Docker Model Runner:
```
docker model run hf.co/Boobalamurugan/TN_Heritage_LLM:F16
```

Lemonade

How to use Boobalamurugan/TN_Heritage_LLM with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Boobalamurugan/TN_Heritage_LLM:F16

Run and chat with the model

lemonade run user.TN_Heritage_LLM-F16

List all available models

lemonade list

🛕 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
Type: 8B parameter model, 4-bit quantized for efficient training and inference.

🗂 Dataset

Source: 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
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 — 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
Join our community forum (Coming Soon)

Downloads last month: 161

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

4-bit

16-bit

Model tree for Boobalamurugan/TN_Heritage_LLM

Base model

meta-llama/Llama-3.1-8B

Quantized

unsloth/Llama-3.1-8B-unsloth-bnb-4bit