Instructions to use Tyesee/ZuperAI-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Tyesee/ZuperAI-14B 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-14B:Q4_K_M # Run inference directly in the terminal: llama cli -hf Tyesee/ZuperAI-14B: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-14B:Q4_K_M # Run inference directly in the terminal: llama cli -hf Tyesee/ZuperAI-14B: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-14B:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Tyesee/ZuperAI-14B: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-14B:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Tyesee/ZuperAI-14B:Q4_K_M
Use Docker
docker model run hf.co/Tyesee/ZuperAI-14B:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use Tyesee/ZuperAI-14B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Tyesee/ZuperAI-14B" # 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-14B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Tyesee/ZuperAI-14B:Q4_K_M
- Ollama
How to use Tyesee/ZuperAI-14B with Ollama:
ollama run hf.co/Tyesee/ZuperAI-14B:Q4_K_M
- Unsloth Desktop
- Pi
How to use Tyesee/ZuperAI-14B 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-14B: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-14B:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Tyesee/ZuperAI-14B with Docker Model Runner:
docker model run hf.co/Tyesee/ZuperAI-14B:Q4_K_M
- Lemonade
How to use Tyesee/ZuperAI-14B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Tyesee/ZuperAI-14B:Q4_K_M
Run and chat with the model
lemonade run user.ZuperAI-14B-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use Tyesee/ZuperAI-14B 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-14B: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-14B:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Tyesee/ZuperAI-14B 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-14B: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-14B: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"
Download toolkit/bench.py from Tyesee/ZuperAI-14B: direct link, hf CLI and curl.
- Browser
- Download file 4 kB
-
https://huggingface.co/Tyesee/ZuperAI-14B/resolve/main/toolkit/bench.py
- Command line
-
hf download hf://Tyesee/ZuperAI-14B/toolkit/bench.py
-
curl -L -o bench.py https://huggingface.co/Tyesee/ZuperAI-14B/resolve/main/toolkit/bench.py
4 kB
| # -*- coding: utf-8 -*- | |
| """Честный бенчмарк ZuperAI: скорость (ток/сек) + сколько задач решено с самопроверкой. | |
| Прогоняет набор задач через полный цикл (генерация кода + тесты судьи + прогон), | |
| считает, сколько решено с первого раза. Плюс замер скорости генерации. | |
| Запуск: | |
| venv/Scripts/python.exe bench.py [deepseek|lmstudio|local] | |
| Результат можно вставить в README как честный бенчмарк (в отличие от маркетинговых цифр). | |
| """ | |
| import sys | |
| import tempfile | |
| import time | |
| from webui import (deepseek_available, deepseek_generate, | |
| lmstudio_available, lmstudio_generate, _strip_fences) | |
| from verify_util import TEST_SYSTEM, run_tests, ensure_unittest_header, tail | |
| TASKS = [ | |
| "Функция, которая возвращает сумму двух чисел", | |
| "Функция, которая возвращает среднее арифметическое списка чисел", | |
| "Функция is_palindrome: возвращает True, если строка — палиндром", | |
| "Функция, которая возвращает количество слов в строке", | |
| "Функция, которая возвращает n-е число Фибоначчи", | |
| "Функция, которая разворачивает строку задом наперёд", | |
| "Функция, которая находит максимальный элемент списка", | |
| ] | |
| def _gen(backend, msgs, max_tokens): | |
| if backend == "deepseek": | |
| return _strip_fences(deepseek_generate(msgs, max_tokens=max_tokens)) | |
| if backend == "lmstudio": | |
| return _strip_fences(lmstudio_generate(msgs, max_tokens=max_tokens)) | |
| from infer_smart import load, gen | |
| if not hasattr(_gen, "_m"): | |
| _gen._m = load() | |
| tok, model = _gen._m | |
| return _strip_fences(gen(tok, model, msgs, max_tokens=max_tokens)) | |
| def bench_speed(backend): | |
| msgs = [{"role": "user", "content": "Напиши функцию, которая сортирует список чисел"}] | |
| t0 = time.time() | |
| out = _gen(backend, msgs, 256) | |
| dt = time.time() - t0 | |
| toks = max(1, len(out.split())) | |
| return toks, dt, toks / dt | |
| def main(): | |
| backend = sys.argv[1] if len(sys.argv) > 1 else ("deepseek" if deepseek_available() else "lmstudio") | |
| judge = "deepseek" if deepseek_available() else backend | |
| toks, dt, tps = bench_speed(backend) | |
| print(f"=== скорость ({backend}): {toks} токов за {dt:.1f}с ≈ {tps:.1f} ток/с ===\n") | |
| passed = 0 | |
| total_t = time.time() | |
| for i, task in enumerate(TASKS, 1): | |
| sandbox = tempfile.mkdtemp(prefix="zuperai_bench_") | |
| t_msgs = [{"role": "system", "content": TEST_SYSTEM}, | |
| {"role": "user", | |
| "content": f"Задача: {task}\n\nНапиши unittest-тесты, импортирующие " | |
| f"решение из solution. Верни ТОЛЬКО код тестов."}] | |
| tests = ensure_unittest_header(_gen(judge, t_msgs, 1024)) | |
| msgs = [{"role": "user", | |
| "content": f"Задача: {task}\n\nТесты:\n{tests}\n\n" | |
| f"Напиши solution.py, проходящий все тесты. Верни ТОЛЬКО код."}] | |
| code = _gen(backend, msgs, 1024) | |
| ok, out = run_tests(code, tests, sandbox, 30) | |
| print(f" {i}/{len(TASKS)} {task[:45]:47s} -> {'OK' if ok else 'FAIL'}") | |
| passed += 1 if ok else 0 | |
| total = time.time() - total_t | |
| print(f"\nИТОГ: {passed}/{len(TASKS)} задач решено с первого раза " | |
| f"({passed * 100 // len(TASKS)}%), время {total:.0f}с") | |
| if __name__ == "__main__": | |
| main() | |