Instructions to use Khurram123/SigmaMath-Visual-Core with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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

llama.cpp

How to use Khurram123/SigmaMath-Visual-Core with llama.cpp:

Install from brew

brew install llama.cpp
# 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

Install from WinGet (Windows)

winget install llama.cpp
# 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

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 new

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 new

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-server -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": "SigmaMath-Visual-Core"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Khurram123 commited on 26 days ago

Commit

bfc0dc3

verified ·

1 Parent(s): 95c0719

Update README.md

Browse files

Files changed (1) hide show

README.md +63 -10

README.md CHANGED Viewed

@@ -1,13 +1,66 @@
-# ΣMath — Visual Computation Engine v2.0
-An interactive mathematical visualization engine powered by **Qwen-Math** and accelerated by **NVIDIA RTX 4060 Ti**.
-## Features
-- **GPU Accelerated**: Fully offloaded to CUDA.
-- **Dual Rendering**: Plotly for interactive 3D/Animations and Matplotlib/mpld3 for 2D.
-- **Resilient Engine**: Automatic correction of colorscale mismatches and backend management.
-## Setup
-1. Place `qwen_math_q4_k_m.gguf` in the root directory.
-2. Install dependencies: `pip install -r requirements.txt`
-3. Run: `python app.py`

+---
+license: mit
+library_name: gguf
+base_model: Qwen/Qwen2.5-Math-7B
+datasets:
+- AI-MO/NuminaMath-TIR
+tags:
+- mathematics
+- interactive
+- 3d-visualization
+- science
+- reasoning
+- uvicorn
+- fastapi
+---
+<p align="center">
+  <h1 align="center">ΣMath — Visual Computation Engine v2.0</h1>
+  <p align="center"><strong>Powered by Qwen-Math & NuminaMath-TIR</strong></p>
+</p>
+## 🔬 Project Overview
+**Developed by: Khurram Pervez, Assistant Professor of Mathematics**
+**ΣMath Core** is a high-performance mathematical visualization engine that bridges the gap between deep symbolic reasoning and real-time interactive rendering. By leveraging the **NuminaMath-TIR** dataset, the model excels at **Chain-of-Thought (CoT)** reasoning, allowing it to solve complex geometric problems before translating them into interactive code.
+The engine utilizes a specialized **Resilient Execution Pipeline** to render 3D manifolds, animations, and parametric surfaces directly in the browser, optimized specifically for local deployment on NVIDIA hardware.
+## 🚀 The Multi-Stage Pipeline
+### 1. TIR (Thought-Intermediate-Reasoning)
+By training on the **NuminaMath-TIR** dataset, the model doesn't just "guess" a plot. It follows a rigorous logical path:
+* **Identification:** Analyzes the geometric properties of the requested manifold.
+* **Calculation:** Determines the necessary vertices, normals, and parametric equations.
+* **Code Synthesis:** Generates high-efficiency Python code (Plotly/Matplotlib).
+### 2. The Resilient Engine (FastAPI Layer)
+To ensure stability during research, the system includes a proprietary processing layer:
+* **Dummy Interception:** Captures and silences `plt.show()` commands to prevent GUI thread blocking on Ubuntu/Linux servers.
+* **Colorscale Transpilation:** Automatically maps Matplotlib colormap names (e.g., *spring, summer*) to Plotly-valid equivalents to ensure 3D renders never fail.
+* **Sandbox Execution:** Executes generated code in a safe local scope using your **RTX 4060 Ti**.
+### 3. Dynamic Hybrid Rendering
+* **Plotly 3D:** Used for interactive rotation, zooming, and time-series animations (e.g., Lorenz Attractors).
+* **mpld3 (2D):** Used for static or high-precision 2D mathematical function plots with browser-based interactivity.
+## 💻 System Configuration
+| Component | Specification |
+| :--- | :--- |
+| **Compute Engine** | NVIDIA GeForce RTX 4060 Ti (16GB VRAM) |
+| **Model Format** | GGUF (Quantized Q4_K_M) |
+| **OS** | Ubuntu 22.04 LTS (Optimized for `Agg` Backend) |
+| **Frameworks** | FastAPI, Llama-cpp-python, Plotly, mpld3 |
+## 🛠️ Quick Start
+### 1. Clone & Setup
+```bash
+# Clone this repository
+git clone [https://huggingface.co/Khurram123/SigmaMath-Visual-Core](https://huggingface.co/Khurram123/SigmaMath-Visual-Core)
+cd SigmaMath-Visual-Core
+# Install dependencies
+pip install fastapi uvicorn llama-cpp-python numpy matplotlib mpld3 plotly