Instructions to use Tyesee/ZuperAI-12.5.0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Tyesee/ZuperAI-12.5.0.2 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 Tyesee/ZuperAI-12.5.0.2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Tyesee/ZuperAI-12.5.0.2:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Tyesee/ZuperAI-12.5.0.2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Tyesee/ZuperAI-12.5.0.2: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 Tyesee/ZuperAI-12.5.0.2:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Tyesee/ZuperAI-12.5.0.2: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 Tyesee/ZuperAI-12.5.0.2:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Tyesee/ZuperAI-12.5.0.2:Q4_K_M

Use Docker

docker model run hf.co/Tyesee/ZuperAI-12.5.0.2:Q4_K_M

LM Studio
Jan

vLLM

How to use Tyesee/ZuperAI-12.5.0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tyesee/ZuperAI-12.5.0.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tyesee/ZuperAI-12.5.0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Tyesee/ZuperAI-12.5.0.2:Q4_K_M

Ollama
How to use Tyesee/ZuperAI-12.5.0.2 with Ollama:
```
ollama run hf.co/Tyesee/ZuperAI-12.5.0.2:Q4_K_M
```
Unsloth Desktop

How to use Tyesee/ZuperAI-12.5.0.2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Tyesee/ZuperAI-12.5.0.2:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Tyesee/ZuperAI-12.5.0.2:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Tyesee/ZuperAI-12.5.0.2 with Docker Model Runner:
```
docker model run hf.co/Tyesee/ZuperAI-12.5.0.2:Q4_K_M
```

Lemonade

How to use Tyesee/ZuperAI-12.5.0.2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Tyesee/ZuperAI-12.5.0.2:Q4_K_M

Run and chat with the model

lemonade run user.ZuperAI-12.5.0.2-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Tyesee/ZuperAI-12.5.0.2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Tyesee/ZuperAI-12.5.0.2:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Tyesee/ZuperAI-12.5.0.2:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Tyesee/ZuperAI-12.5.0.2 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Tyesee/ZuperAI-12.5.0.2:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Tyesee/ZuperAI-12.5.0.2:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

ZuperAI 12.5.0.2

Кодовая модель (3B), заточенная под чистый лаконичный Python-бэкенд: FastAPI, SQLite, argparse, numpy. Докстринги и комментарии — на русском, стиль stdlib-first.

Полностью офлайн: ~2 ГБ для Q4, ~6 ГБ для f16.

Файлы

ZuperAI-12.5.0.2-Q4_K_M.gguf — 4-бит (меньше / быстрее)
ZuperAI-12.5.0.2-f16.gguf — полная точность
Modelfile — для Ollama

Примеры генерации

Запрос: «Напиши эндпоинт FastAPI для списка постов с поиском и пагинацией»

from fastapi import FastAPI

app = FastAPI()


@app.get("/api/posts")
def api_posts(q: str = "", page: int = 1, per: int = 10):
    posts = database.search_posts(q) if q else database.get_posts()
    total = len(posts)
    start = (page - 1) * per
    return {"posts": posts[start:start + per], "total": total, "page": page, "per": per}

Запрос: «Найди и исправь ошибку: def mean(xs): return sum(xs) / len(xs)»

def mean(xs):
    if not xs:
        return 0.0
    return sum(xs) / len(xs)

Производительность

Обучение: ~34k примеров, 1 эпоха, train loss ≈ 0.28
Скорость: ~12 ток/сек (bf16, RTX 4060 Ti); в llama.cpp / Ollama быстрее (Q4)

Использование

LM Studio

Скачай любой .gguf и открой его в LM Studio.

Ollama

ollama create ZuperAI -f Modelfile
ollama run ZuperAI

llama.cpp

llama-server -m ZuperAI-12.5.0.2-Q4_K_M.gguf -c 4096

Downloads last month: -

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

4-bit

16-bit