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/agent.py from Tyesee/ZuperAI-14B: direct link, hf CLI and curl.
- Browser
- Download file 7.17 kB
-
https://huggingface.co/Tyesee/ZuperAI-14B/resolve/main/toolkit/agent.py
- Command line
-
hf download hf://Tyesee/ZuperAI-14B/toolkit/agent.py
-
curl -L -o agent.py https://huggingface.co/Tyesee/ZuperAI-14B/resolve/main/toolkit/agent.py
7.17 kB
| # -*- coding: utf-8 -*- | |
| """ZuperAI — кодинг-агент: по ТЗ генерирует целое решение + тесты → гоняет → чинит. | |
| Отличие от verify.py: ориентирован на ЦЕЛЫЙ модуль/приложение (не одну функцию). | |
| Пишет решение из нескольких функций/классов, сам пишет unittest-тесты, гоняет | |
| их в песочнице и доводит до зелёного. Это «агент, который делает работу», а не | |
| «генератор куска кода». | |
| Запуск: | |
| venv/Scripts/python.exe agent.py "Напиши модуль работы с CSV: чтение, фильтр, агрегация" | |
| venv/Scripts/python.exe agent.py "FastAPI-приложение для заметок с SQLite" | |
| Ключи: | |
| --code deepseek|lmstudio|local кто пишет код (по умолчанию deepseek, если ключ есть) | |
| --judge deepseek|lmstudio|local кто пишет тесты/судит (по умолчанию deepseek) | |
| --attempts N число попыток (по умолчанию 5) | |
| --keep не удалять песочницу | |
| """ | |
| import os | |
| import sys | |
| import tempfile | |
| from webui import (deepseek_available, deepseek_generate, | |
| lmstudio_available, lmstudio_generate) | |
| from verify_util import (TEST_SYSTEM, VERIFY_ATTEMPTS, VERIFY_TIMEOUT, | |
| run_tests, looks_like_tests, tail, ensure_unittest_header) | |
| SYSTEM_AGENT = ("Ты — senior-разработчик. По описанию напиши ПОЛНОЕ решение: " | |
| "весь нужный код в одном файле (solution.py) — функции, классы, " | |
| "обработка ошибок, понятные русские комментарии и докстринги. " | |
| "Не используй внешние зависимости сверх необходимого минимума. " | |
| "Без пояснений вне кода и без ```.") | |
| def _pick(flag, default, available): | |
| if flag not in ("deepseek", "lmstudio", "local"): | |
| return default | |
| if flag == "deepseek" and not available[0]: | |
| return default | |
| if flag == "lmstudio" and not available[1]: | |
| return default | |
| return flag | |
| def _gen(backend, msgs, max_tokens): | |
| if backend == "deepseek": | |
| from webui import _strip_fences | |
| return _strip_fences(deepseek_generate(msgs, max_tokens=max_tokens)) | |
| if backend == "lmstudio": | |
| from webui import _strip_fences | |
| return _strip_fences(lmstudio_generate(msgs, max_tokens=max_tokens)) | |
| # local: transformers + LoRA 3B | |
| from infer_smart import load, gen, _strip_fences as _sf | |
| if not hasattr(_gen, "_model"): | |
| _gen._model = load() | |
| tok, model = _gen._model | |
| return _sf(gen(tok, model, msgs, max_tokens=max_tokens)) | |
| def main(): | |
| args = sys.argv[1:] | |
| code_backend, judge = "deepseek", "deepseek" | |
| attempts, keep = VERIFY_ATTEMPTS, False | |
| parts = [] | |
| i = 0 | |
| while i < len(args): | |
| a = args[i] | |
| if a == "--code" and i + 1 < len(args): | |
| code_backend = args[i + 1]; i += 2; continue | |
| if a == "--judge" and i + 1 < len(args): | |
| judge = args[i + 1]; i += 2; continue | |
| if a == "--attempts" and i + 1 < len(args): | |
| attempts = int(args[i + 1]); i += 2; continue | |
| if a == "--keep": | |
| keep = True; i += 1; continue | |
| parts.append(a); i += 1 | |
| prompt = " ".join(parts) | |
| if not prompt: | |
| prompt = "Модуль работы с CSV: чтение файла, фильтрация строк, агрегация по колонке" | |
| avail = (deepseek_available(), lmstudio_available()) | |
| code_backend = _pick(code_backend, "deepseek" if avail[0] else "local", avail) | |
| judge = _pick(judge, "deepseek" if avail[0] else "local", avail) | |
| sandbox = tempfile.mkdtemp(prefix="zuperai_agent_") | |
| print(f"[*] код: {code_backend}, судья: {judge}") | |
| # 1) судья пишет тесты по ТЗ | |
| t_msgs = [{"role": "system", "content": TEST_SYSTEM}, | |
| {"role": "user", | |
| "content": f"Задача: {prompt}\n\nНапиши unittest-тесты, которые " | |
| f"импортируют решение из solution и проверяют корректность " | |
| f"всех заявленных возможностей. Верни ТОЛЬКО код тестов."}] | |
| tests = ensure_unittest_header(_gen(judge, t_msgs, 1536)) | |
| # 2) код-агент пишет решение, гоняем, чиним | |
| msgs = [{"role": "system", "content": SYSTEM_AGENT}, | |
| {"role": "user", | |
| "content": f"Задача: {prompt}\n\nТесты:\n{tests}\n\n" | |
| f"Напиши полное решение (solution.py), проходящее эти тесты."}] | |
| code = "" | |
| for attempt in range(1, attempts + 1): | |
| if not code: | |
| code = _gen(code_backend, msgs, 1536) | |
| print(f"[попытка {attempt}/{attempts}] генерирую решение…", file=sys.stderr) | |
| else: | |
| print(f"[попытка {attempt}/{attempts}] тестирую исправленное…", file=sys.stderr) | |
| ok, out = run_tests(code, tests, sandbox, VERIFY_TIMEOUT) | |
| if ok: | |
| print(code) | |
| print(f"\n[OK] тесты прошли, попытка {attempt}") | |
| print("----- тесты -----") | |
| print(tests) | |
| if keep: | |
| print("песочница:", sandbox) | |
| return | |
| print(f"[попытка {attempt}] упало:\n{tail(out)}", file=sys.stderr) | |
| msgs.append({"role": "assistant", "content": code}) | |
| msgs.append({"role": "user", | |
| "content": f"Решение не прошло тесты:\n{tail(out)}\n\n" | |
| f"Определи, где ошибка (в решении или в тесте), и верни " | |
| f"исправленный КОД либо исправленный ТЕСТ — одно из двух."}) | |
| fix = _gen(judge, msgs, 1536) | |
| if looks_like_tests(fix): | |
| tests = ensure_unittest_header(fix) | |
| code = "" | |
| msgs = msgs[:2] | |
| msgs[1] = {"role": "user", | |
| "content": f"Задача: {prompt}\n\nТесты:\n{tests}\n\n" | |
| f"Напиши полное решение (solution.py), проходящее тесты."} | |
| else: | |
| code = fix | |
| msgs[-2] = {"role": "assistant", "content": code} | |
| print(code) | |
| print(f"\n[!] за {attempts} попыток не прошло — выше последний вариант") | |
| print("----- тесты -----") | |
| print(tests) | |
| if keep: | |
| print("песочница:", sandbox) | |
| if __name__ == "__main__": | |
| main() | |