Instructions to use mervinpraison/tamilan-2-9b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mervinpraison/tamilan-2-9b with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mervinpraison/tamilan-2-9b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mervinpraison/tamilan-2-9b 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 mervinpraison/tamilan-2-9b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mervinpraison/tamilan-2-9b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mervinpraison/tamilan-2-9b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mervinpraison/tamilan-2-9b:Q4_K_M

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 mervinpraison/tamilan-2-9b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mervinpraison/tamilan-2-9b:Q4_K_M

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 mervinpraison/tamilan-2-9b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mervinpraison/tamilan-2-9b:Q4_K_M

Use Docker

docker model run hf.co/mervinpraison/tamilan-2-9b:Q4_K_M

LM Studio
Jan
Ollama
How to use mervinpraison/tamilan-2-9b with Ollama:
```
ollama run hf.co/mervinpraison/tamilan-2-9b:Q4_K_M
```

Unsloth Studio

How to use mervinpraison/tamilan-2-9b 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 mervinpraison/tamilan-2-9b 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 mervinpraison/tamilan-2-9b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mervinpraison/tamilan-2-9b to start chatting

Atomic Chat new
Docker Model Runner
How to use mervinpraison/tamilan-2-9b with Docker Model Runner:
```
docker model run hf.co/mervinpraison/tamilan-2-9b:Q4_K_M
```

Lemonade

How to use mervinpraison/tamilan-2-9b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mervinpraison/tamilan-2-9b:Q4_K_M

Run and chat with the model

lemonade run user.tamilan-2-9b-Q4_K_M

List all available models

lemonade list

Tamilan 2 - 9B Advanced Tamil Large Language Model

Tamilan 2 is the latest version of the Tamil Large Language Model, designed to enhance understanding and generation of Tamil text.

Gemma 2, instruction fine tuned on Tamil Alpaca Dataset

Developed by: Mervin Praison

Download

Ollama: Tamilan 2 on Ollama
Hugging Face:

Website: Tamilan 2

Key Features:

Sizes:
- 2B parameters
- 9B parameters
- 27B parameters
Quantization Levels:
- 4-bit
- 8-bit
- 16-bit
Training Dataset:
- Alpaca Tamil dataset - https://huggingface.co/datasets/abhinand/tamil-alpaca
Applications:
- Content creation
- Customer support
- Educational tools
- Research
Deployment:
- Supports efficient deployment and fine-tuning for various tasks