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

Libraries

How to use Crossberry/tamila with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Crossberry/tamila",
	filename="tamila (1).gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Crossberry/tamila with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Crossberry/tamila
# Run inference directly in the terminal:
llama-cli -hf Crossberry/tamila

Install from WinGet (Windows)

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

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 Crossberry/tamila
# Run inference directly in the terminal:
./llama-cli -hf Crossberry/tamila

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 Crossberry/tamila
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Crossberry/tamila

Use Docker

docker model run hf.co/Crossberry/tamila

LM Studio
Jan
Ollama
How to use Crossberry/tamila with Ollama:
```
ollama run hf.co/Crossberry/tamila
```

Unsloth Studio new

How to use Crossberry/tamila 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 Crossberry/tamila 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 Crossberry/tamila to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use Crossberry/tamila with Docker Model Runner:
```
docker model run hf.co/Crossberry/tamila
```

Lemonade

How to use Crossberry/tamila with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Crossberry/tamila

Run and chat with the model

lemonade run user.tamila-{{QUANT_TAG}}

List all available models

lemonade list

🚀 Tamila Master v0.3

Created by crossberryweb

Tamila is a high-performance bilingual model (Tamil/English) trained on a massive global corpus of over 2.2 million segments.

🔗 Project Links

Live Demo (HF Space): https://huggingface.co/spaces/Crossberry/tamila-test-app
Web Deployment: crossberry.vercel.app
Dataset Repository: Hugging Face Tamila

📊 Model Benchmarks

Task	Dataset	Accuracy	Loss
Global Corpus Tuning	2.2M Segments	1.0000	6.64e-10
Literature (Thirukkural)	Kaggle NLP	0.9868	0.0612
Technical (Kimi K2)	PDF Extract	1.0000	1.17e-06

🛠 Future Roadmap

Integration with advanced Transformer architectures.
Expanded support for regional Tamil dialects.
Real-time API integration for mobile applications.

📖 More Info

This model utilizes a custom MLP architecture optimized for GGUF deployment. It categorizes text into four primary contexts: History/Literature, Technical/AI, Tanglish, and General Corpus.

Developed for the open-source community by Crossberryweb.

Downloads last month: 32

GGUF

Model size

81.9M params

Architecture

gpt2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 1 Ask for provider support

Crossberry
/

tamila

🚀 Tamila Master v0.3

🔗 Project Links

📊 Model Benchmarks

🛠 Future Roadmap

📖 More Info

Space using Crossberry/tamila 1