GGUF
mathematics
geogebra
3d-visualization
education
coding
reasoning
uvicorn
fastapi
conversational
Instructions to use Khurram123/SigmaMath-Visual-Core with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Khurram123/SigmaMath-Visual-Core with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Khurram123/SigmaMath-Visual-Core", filename="qwen_math_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/SigmaMath-Visual-Core 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/SigmaMath-Visual-Core:Q4_K_M # Run inference directly in the terminal: llama cli -hf Khurram123/SigmaMath-Visual-Core: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/SigmaMath-Visual-Core:Q4_K_M # Run inference directly in the terminal: llama cli -hf Khurram123/SigmaMath-Visual-Core: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/SigmaMath-Visual-Core:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Khurram123/SigmaMath-Visual-Core: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/SigmaMath-Visual-Core:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Khurram123/SigmaMath-Visual-Core:Q4_K_M
Use Docker
docker model run hf.co/Khurram123/SigmaMath-Visual-Core:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use Khurram123/SigmaMath-Visual-Core with Ollama:
ollama run hf.co/Khurram123/SigmaMath-Visual-Core:Q4_K_M
- Unsloth Studio
How to use Khurram123/SigmaMath-Visual-Core 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/SigmaMath-Visual-Core 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/SigmaMath-Visual-Core to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Khurram123/SigmaMath-Visual-Core to start chatting
- Pi
How to use Khurram123/SigmaMath-Visual-Core with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Khurram123/SigmaMath-Visual-Core: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/SigmaMath-Visual-Core:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use Khurram123/SigmaMath-Visual-Core 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/SigmaMath-Visual-Core: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/SigmaMath-Visual-Core:Q4_K_M
Run Hermes
hermes
- Atomic Chat new
- OpenClaw new
How to use Khurram123/SigmaMath-Visual-Core with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Khurram123/SigmaMath-Visual-Core: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/SigmaMath-Visual-Core: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/SigmaMath-Visual-Core with Docker Model Runner:
docker model run hf.co/Khurram123/SigmaMath-Visual-Core:Q4_K_M
- Lemonade
How to use Khurram123/SigmaMath-Visual-Core with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Khurram123/SigmaMath-Visual-Core:Q4_K_M
Run and chat with the model
lemonade run user.SigmaMath-Visual-Core-Q4_K_M
List all available models
lemonade list
| import os | |
| import uvicorn | |
| import re | |
| import numpy as np | |
| import matplotlib | |
| matplotlib.use('Agg') # Prevents extra GUI windows from opening on your Ubuntu desktop | |
| import matplotlib.pyplot as plt | |
| import mpld3 | |
| import plotly.graph_objects as go | |
| from fastapi import FastAPI, Request | |
| from fastapi.responses import HTMLResponse | |
| from llama_cpp import Llama | |
| app = FastAPI() | |
| # 1. GPU INITIALIZATION (RTX 4060 Ti) | |
| llm = Llama( | |
| model_path="/mnt/ai_data/math_APP/qwen_math_q4_k_m.gguf", | |
| n_gpu_layers=-1, | |
| n_ctx=2048, | |
| verbose=False | |
| ) | |
| def fix_plotly_colorscales(code): | |
| """Intercepts Matplotlib colormap names and swaps them for Plotly equivalents.""" | |
| # Maps common Matplotlib names to their closest Plotly counterparts | |
| color_map = { | |
| "spring": "Viridis", | |
| "summer": "Plasma", | |
| "autumn": "Inferno", | |
| "winter": "Cividis", | |
| "magma": "Magma" | |
| } | |
| for mpl_name, plotly_name in color_map.items(): | |
| # Handles both single and double quotes, and case sensitivity | |
| code = re.sub(f"['\"]{mpl_name}['\"]", f"'{plotly_name}'", code, flags=re.IGNORECASE) | |
| return code | |
| async def index(): | |
| return """ | |
| <!DOCTYPE html> | |
| <html lang="en"> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <title>Interactive Math Core</title> | |
| <script src="https://cdn.tailwindcss.com"></script> | |
| <style> | |
| @import url('https://fonts.googleapis.com/css2?family=Fira+Code&display=swap'); | |
| .code-box { font-family: 'Fira Code', monospace; } | |
| iframe { border: none; width: 100%; height: 100%; border-radius: 1rem; background: white; } | |
| </style> | |
| </head> | |
| <body class="bg-gray-950 text-gray-100 min-h-screen p-6"> | |
| <div class="max-w-7xl mx-auto"> | |
| <header class="mb-8 flex justify-between items-center"> | |
| <h1 class="text-3xl font-bold text-transparent bg-clip-text bg-gradient-to-r from-blue-400 to-cyan-400">Math Visualizer Core</h1> | |
| <div class="text-xs font-mono text-gray-500 bg-gray-900 px-3 py-1 rounded-full border border-gray-800">Resilient Engine v2.0</div> | |
| </header> | |
| <div class="grid grid-cols-1 lg:grid-cols-12 gap-6"> | |
| <div class="lg:col-span-4 space-y-4"> | |
| <div class="bg-gray-900 p-5 rounded-2xl border border-gray-800 shadow-xl"> | |
| <label class="block text-xs font-bold text-gray-500 uppercase mb-2">Research Prompt</label> | |
| <textarea id="promptInput" rows="5" | |
| class="w-full bg-gray-800 border border-gray-700 rounded-xl p-4 text-sm focus:ring-2 focus:ring-blue-500 outline-none transition-all" | |
| placeholder="e.g., Create a rotating 3D torus..."></textarea> | |
| <button onclick="generateVisual()" id="genBtn" | |
| class="w-full mt-4 bg-blue-600 hover:bg-blue-500 py-3 rounded-xl font-bold transition-all shadow-lg shadow-blue-900/40"> | |
| Execute on GPU | |
| </button> | |
| </div> | |
| <div class="bg-gray-900 p-5 rounded-2xl border border-gray-800"> | |
| <pre id="codeDisplay" class="code-box bg-black p-4 rounded-lg overflow-x-auto text-[11px] text-green-400 border border-gray-800 min-h-[200px]"></pre> | |
| </div> | |
| </div> | |
| <div class="lg:col-span-8"> | |
| <div class="bg-gray-900 rounded-2xl border border-gray-800 h-[650px] relative overflow-hidden flex items-center justify-center"> | |
| <div id="loader" class="hidden z-20 flex flex-col items-center"> | |
| <div class="animate-spin rounded-full h-12 w-12 border-t-2 border-b-2 border-blue-500 mb-4"></div> | |
| <p class="text-blue-400">Solving Geometry...</p> | |
| </div> | |
| <div id="vizContainer" class="w-full h-full p-2"> | |
| <div id="placeholder" class="h-full flex items-center justify-center text-gray-600 italic"> | |
| Ready for computation. | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| <script> | |
| async function generateVisual() { | |
| const prompt = document.getElementById('promptInput').value; | |
| const btn = document.getElementById('genBtn'); | |
| const loader = document.getElementById('loader'); | |
| const vizContainer = document.getElementById('vizContainer'); | |
| const placeholder = document.getElementById('placeholder'); | |
| const codeBox = document.getElementById('codeDisplay'); | |
| if (!prompt) return; | |
| btn.disabled = true; | |
| loader.classList.remove('hidden'); | |
| placeholder.classList.add('hidden'); | |
| codeBox.innerText = "# Synthesizing logic..."; | |
| try { | |
| const response = await fetch('/process', { | |
| method: 'POST', | |
| headers: {'Content-Type': 'application/json'}, | |
| body: JSON.stringify({ prompt: prompt }) | |
| }); | |
| const data = await response.json(); | |
| codeBox.innerText = data.code; | |
| if (data.html) { | |
| vizContainer.innerHTML = `<iframe srcdoc='${data.html.replace(/'/g, "'")}'></iframe>`; | |
| } else if (data.error) { | |
| vizContainer.innerHTML = `<div class='p-10 text-red-500 font-mono text-xs overflow-auto h-full whitespace-pre-wrap'>${data.error}</div>`; | |
| } | |
| } catch (err) { | |
| codeBox.innerText = "# Execution failed."; | |
| } finally { | |
| loader.classList.add('hidden'); | |
| btn.disabled = false; | |
| } | |
| } | |
| </script> | |
| </body> | |
| </html> | |
| """ | |
| async def process_request(request: Request): | |
| data = await request.json() | |
| user_prompt = data.get("prompt") | |
| instruction = ( | |
| "Output ONLY raw Python code. Use plotly.graph_objects (go) for 3D/animations " | |
| "and name the figure 'fig'. Use matplotlib.pyplot (plt) for 2D. " | |
| "CRITICAL: Never use plt.show() or fig.show(). Use Plotly-safe colorscales." | |
| ) | |
| formatted = f"<|im_start|>system\n{instruction}<|im_end|>\n<|im_start|>user\n{user_prompt}<|im_end|>\n<|im_start|>assistant\n" | |
| output = llm(formatted, max_tokens=1536, stop=["<|im_end|>"]) | |
| code = re.sub(r"```python|```", "", output['choices'][0]['text']).strip() | |
| # Apply the colorscale fix | |
| code = fix_plotly_colorscales(code) | |
| try: | |
| plt.clf() | |
| plt.close('all') | |
| # Scope with "Dummy Show" to prevent Ubuntu window popups | |
| def dummy_show(*args, **kwargs): pass | |
| exec_scope = { | |
| "plt": plt, "np": np, "go": go, "mpld3": mpld3, | |
| "__builtins__": __builtins__ | |
| } | |
| plt.show = dummy_show | |
| exec(code, exec_scope) | |
| if "fig" in exec_scope: | |
| # Captures Plotly (3D/Animated) | |
| html_output = exec_scope["fig"].to_html(full_html=False, include_plotlyjs='cdn') | |
| else: | |
| # Captures Matplotlib (2D) | |
| html_output = mpld3.fig_to_html(plt.gcf()) | |
| return {"code": code, "html": html_output} | |
| except Exception as e: | |
| return {"code": code, "error": str(e)} | |
| if __name__ == "__main__": | |
| uvicorn.run(app, host="0.0.0.0", port=8000) |