Instructions to use ViorikaAI-org/CalmaCatCoder-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ViorikaAI-org/CalmaCatCoder-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ViorikaAI-org/CalmaCatCoder-GGUF",
	filename="CalmaCatCoder-280M-f16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ViorikaAI-org/CalmaCatCoder-GGUF 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 ViorikaAI-org/CalmaCatCoder-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf ViorikaAI-org/CalmaCatCoder-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ViorikaAI-org/CalmaCatCoder-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf ViorikaAI-org/CalmaCatCoder-GGUF: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 ViorikaAI-org/CalmaCatCoder-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf ViorikaAI-org/CalmaCatCoder-GGUF: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 ViorikaAI-org/CalmaCatCoder-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ViorikaAI-org/CalmaCatCoder-GGUF:F16

Use Docker

docker model run hf.co/ViorikaAI-org/CalmaCatCoder-GGUF:F16

LM Studio
Jan

vLLM

How to use ViorikaAI-org/CalmaCatCoder-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ViorikaAI-org/CalmaCatCoder-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ViorikaAI-org/CalmaCatCoder-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ViorikaAI-org/CalmaCatCoder-GGUF:F16

Ollama
How to use ViorikaAI-org/CalmaCatCoder-GGUF with Ollama:
```
ollama run hf.co/ViorikaAI-org/CalmaCatCoder-GGUF:F16
```

Unsloth Studio

How to use ViorikaAI-org/CalmaCatCoder-GGUF 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 ViorikaAI-org/CalmaCatCoder-GGUF 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 ViorikaAI-org/CalmaCatCoder-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ViorikaAI-org/CalmaCatCoder-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use ViorikaAI-org/CalmaCatCoder-GGUF with Docker Model Runner:
```
docker model run hf.co/ViorikaAI-org/CalmaCatCoder-GGUF:F16
```

Lemonade

How to use ViorikaAI-org/CalmaCatCoder-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ViorikaAI-org/CalmaCatCoder-GGUF:F16

Run and chat with the model

lemonade run user.CalmaCatCoder-GGUF-F16

List all available models

lemonade list

CalmaCatCoder-280M (GGUF)

CalmaCatCoder-280M is a compact and ultra-fast 280M language model trained from scratch for Python code generation.

This repository contains quantized GGUF weights optimized for llama.cpp, Ollama, LM Studio, and CPU/GPU edge inference.

⚡ Specs

Architecture: Transformer / Causal LM (Qwen2-like)
Parameters: ~280M
Format: GGUF
Prompt Format: ChatML

🔗 Original Weights

For PyTorch / SafeTensors base weights and fine-tuning:
👉 Original Repository: ViorikaAI/CalmaCatCoder

📜 License

Distributed under the CalmaCat Public License (CCPL-1.0). See LICENSE for details.

🇷🇺 Нажмите, чтобы открыть описание на русском языке (Click to expand Russian description)

CalmaCatCoder-280M (GGUF)

CalmaCatCoder-280M — компактная и ультрабыстрая языковая модель на 280 млн параметров, обученная с нуля для генерации кода на Python.

В этом репозитории находятся квантованные GGUF веса, оптимизированные для работы через llama.cpp, Ollama, LM Studio и быстрой работы на CPU/GPU.

⚡ Характеристики

Архитектура: Transformer / Causal LM (Qwen2-like)
Объём параметров: ~280 млн
Формат: GGUF
Формат диалога: ChatML

🔗 Оригинальные веса

Если вам нужны исходные веса в формате PyTorch / SafeTensors для дообучения:
👉 Основной репозиторий: ViorikaAI/CalmaCatCoder

📜 Лицензия

Распространяется под кастомной открытой лицензией CalmaCat Public License (CCPL-1.0). Полный текст см. в файле LICENSE.

Downloads last month: 134

GGUF

Model size

0.3B params

Architecture

qwen2

Hardware compatibility

4-bit

16-bit

Model tree for ViorikaAI-org/CalmaCatCoder-GGUF

Base model

ViorikaAI-org/CalmaCatCoder

Quantized

(1)

this model