Instructions to use Khurram123/Qwen-GeoGebra-Coder-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Khurram123/Qwen-GeoGebra-Coder-7B with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Khurram123/Qwen-GeoGebra-Coder-7B", filename="math_viz_Q4_K_M.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Khurram123/Qwen-GeoGebra-Coder-7B 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 Khurram123/Qwen-GeoGebra-Coder-7B:Q4_K_M # Run inference directly in the terminal: llama cli -hf Khurram123/Qwen-GeoGebra-Coder-7B:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Khurram123/Qwen-GeoGebra-Coder-7B:Q4_K_M # Run inference directly in the terminal: llama cli -hf Khurram123/Qwen-GeoGebra-Coder-7B: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 Khurram123/Qwen-GeoGebra-Coder-7B:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Khurram123/Qwen-GeoGebra-Coder-7B: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 Khurram123/Qwen-GeoGebra-Coder-7B:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Khurram123/Qwen-GeoGebra-Coder-7B:Q4_K_M
Use Docker
docker model run hf.co/Khurram123/Qwen-GeoGebra-Coder-7B:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use Khurram123/Qwen-GeoGebra-Coder-7B with Ollama:
ollama run hf.co/Khurram123/Qwen-GeoGebra-Coder-7B:Q4_K_M
- Unsloth Studio
How to use Khurram123/Qwen-GeoGebra-Coder-7B 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 Khurram123/Qwen-GeoGebra-Coder-7B 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 Khurram123/Qwen-GeoGebra-Coder-7B to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Khurram123/Qwen-GeoGebra-Coder-7B to start chatting
- Pi
How to use Khurram123/Qwen-GeoGebra-Coder-7B with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Khurram123/Qwen-GeoGebra-Coder-7B:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Khurram123/Qwen-GeoGebra-Coder-7B:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use Khurram123/Qwen-GeoGebra-Coder-7B with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Khurram123/Qwen-GeoGebra-Coder-7B: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 Khurram123/Qwen-GeoGebra-Coder-7B:Q4_K_M
Run Hermes
hermes
- Atomic Chat new
- OpenClaw new
How to use Khurram123/Qwen-GeoGebra-Coder-7B with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Khurram123/Qwen-GeoGebra-Coder-7B: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 "Khurram123/Qwen-GeoGebra-Coder-7B: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"
- Docker Model Runner
How to use Khurram123/Qwen-GeoGebra-Coder-7B with Docker Model Runner:
docker model run hf.co/Khurram123/Qwen-GeoGebra-Coder-7B:Q4_K_M
- Lemonade
How to use Khurram123/Qwen-GeoGebra-Coder-7B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Khurram123/Qwen-GeoGebra-Coder-7B:Q4_K_M
Run and chat with the model
lemonade run user.Qwen-GeoGebra-Coder-7B-Q4_K_M
List all available models
lemonade list
| <html lang="en"> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <title>GeoGebra AI Research Interface</title> | |
| <script src="https://www.geogebra.org/apps/deployggb.js"></script> | |
| <style> | |
| body { font-family: 'Inter', sans-serif; background: #f0f2f5; display: flex; height: 100vh; margin: 0; } | |
| #sidebar { width: 400px; background: white; border-right: 1px solid #ddd; padding: 20px; display: flex; flex-direction: column; box-shadow: 2px 0 5px rgba(0,0,0,0.05); } | |
| #main { flex-grow: 1; position: relative; } | |
| textarea { width: 100%; height: 100px; padding: 10px; border: 1px solid #ccc; border-radius: 8px; resize: none; margin-bottom: 10px; box-sizing: border-box; } | |
| button { width: 100%; padding: 12px; background: #007bff; color: white; border: none; border-radius: 8px; cursor: pointer; font-weight: bold; margin-bottom: 10px; } | |
| button:disabled { background: #ccc; } | |
| #output { flex-grow: 1; overflow-y: auto; font-size: 14px; color: #444; border-top: 1px solid #eee; pt: 15px; } | |
| .label { font-weight: bold; color: #111; margin-top: 15px; display: block; } | |
| .code-block { font-family: monospace; background: #f8f9fa; padding: 8px; border-radius: 4px; border: 1px solid #e9ecef; margin-top: 5px; } | |
| </style> | |
| </head> | |
| <body> | |
| <div id="sidebar"> | |
| <h2>3D AI Assistant</h2> | |
| <textarea id="userInput" placeholder="e.g., Create a sphere with radius 3. Cut it with a plane at z=1."></textarea> | |
| <button id="sendBtn" onclick="runAI()">Run on RTX 4060 Ti</button> | |
| <button style="background: #6c757d;" onclick="clearCanvas()">Clear Canvas</button> | |
| <div id="output"> | |
| <span class="label">Model Reasoning:</span> | |
| <div id="thoughtDisplay">Waiting for input...</div> | |
| <span class="label">Generated Commands:</span> | |
| <div id="commandDisplay" class="code-block">None</div> | |
| </div> | |
| </div> | |
| <div id="main"> | |
| <div id="ggb-element" style="width: 100%; height: 100%;"></div> | |
| </div> | |
| <script> | |
| const params = { | |
| "appName": "classic", | |
| "width": window.innerWidth - 400, | |
| "height": window.innerHeight, | |
| "showAlgebraInput": true, | |
| "perspective": "5" // Forces 3D View | |
| }; | |
| const applet = new GGBApplet(params, true); | |
| window.onload = function() { applet.inject('ggb-element'); }; | |
| function clearCanvas() { | |
| ggbApplet.newConstruction(); | |
| ggbApplet.setPerspective("5"); | |
| document.getElementById('commandDisplay').innerText = "None"; | |
| document.getElementById('thoughtDisplay').innerText = "Canvas cleared."; | |
| } | |
| async function runAI() { | |
| const query = document.getElementById('userInput').value; | |
| const btn = document.getElementById('sendBtn'); | |
| if (!query) return; | |
| btn.disabled = true; | |
| btn.innerText = "Processing..."; | |
| try { | |
| const response = await fetch('http://127.0.0.1:8000/ask', { | |
| method: 'POST', | |
| headers: { 'Content-Type': 'application/json' }, | |
| body: JSON.stringify({ prompt: query }) | |
| }); | |
| const data = await response.json(); | |
| document.getElementById('thoughtDisplay').innerText = data.thought; | |
| document.getElementById('commandDisplay').innerText = data.commands || "No commands detected."; | |
| if (data.commands) { | |
| const cmdArray = data.commands.split(';'); | |
| cmdArray.forEach(cmd => { | |
| if (cmd.trim()) ggbApplet.evalCommand(cmd.trim()); | |
| }); | |
| } | |
| } catch (error) { | |
| console.error(error); | |
| alert("Backend error. Check server.py logs."); | |
| } finally { | |
| btn.disabled = false; | |
| btn.innerText = "Run on RTX 4060 Ti"; | |
| } | |
| } | |
| </script> | |
| </body> | |
| </html> |