Instructions to use NotParv67/QwenCoder 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 NotParv67/QwenCoder 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 NotParv67/QwenCoder # Run inference directly in the terminal: llama cli -hf NotParv67/QwenCoder
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf NotParv67/QwenCoder # Run inference directly in the terminal: llama cli -hf NotParv67/QwenCoder
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf NotParv67/QwenCoder # Run inference directly in the terminal: ./build/bin/llama cli -hf NotParv67/QwenCoder
Use Docker
docker model run hf.co/NotParv67/QwenCoder
- Llama new
- LM Studio
- Jan
- Ollama
How to use NotParv67/QwenCoder with Ollama:
ollama run hf.co/NotParv67/QwenCoder
- Unsloth Desktop
- Pi
How to use NotParv67/QwenCoder with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf NotParv67/QwenCoder
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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "NotParv67/QwenCoder" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use NotParv67/QwenCoder with Docker Model Runner:
docker model run hf.co/NotParv67/QwenCoder
- Lemonade
How to use NotParv67/QwenCoder with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull NotParv67/QwenCoder
Run and chat with the model
lemonade run user.QwenCoder-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use NotParv67/QwenCoder with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf NotParv67/QwenCoder
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://127.0.0.1:9931/v1 hermes config set model.default NotParv67/QwenCoder
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use NotParv67/QwenCoder with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf NotParv67/QwenCoder
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://127.0.0.1:9931/v1 \ --custom-model-id "NotParv67/QwenCoder" \ --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"
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
QwenCoder
A fast, code-focused Ollama configuration built on Qwen2.5-Coder-7B.
QwenCoder is configured to prioritize direct, clean, working code instead of long explanations or unnecessary reasoning.
Configuration
FROM ./qwen2.5-coder-7b-pyqwen.gguf
SYSTEM You are an expert Python developer. Return clean, working code only unless explanation is explicitly asked for.
PARAMETER num_predict 512
PARAMETER stop <|im_end|>
PARAMETER temperature 0.2
Features
- Qwen2.5-Coder-7B
- GGUF format
- Low temperature (
0.2) - Maximum output of
512tokens - Python-focused coding behavior
- Concise, direct responses
Files
QwenCoder/
βββ Modelfile
βββ qwen2.5-coder-7b-pyqwen.gguf
βββ README.md
βββ LICENSE
Use with Ollama
After downloading the repository:
ollama create qwen-coder-fast -f Modelfile
Run it with:
ollama run qwen-coder-fast
Example
Prompt:
Write a Python program to check whether a number is prime.
The configuration is designed to return the implementation directly rather than spending unnecessary time on a long explanation.
Attribution
This model is based on Qwen2.5-Coder-7B, developed by Alibaba Cloud's Qwen team.
The underlying Qwen2.5-Coder model is licensed under the Apache License 2.0.
The Ollama configuration in this repository adds the fast, code-focused system prompt and generation parameters shown above.
License
The underlying Qwen2.5-Coder model is distributed under the Apache License 2.0.
- Downloads last month
- 1
We're not able to determine the quantization variants.