Instructions to use vishu01a/shunya-3B-UIUX-master_v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use vishu01a/shunya-3B-UIUX-master_v1.0 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 vishu01a/shunya-3B-UIUX-master_v1.0:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf vishu01a/shunya-3B-UIUX-master_v1.0:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf vishu01a/shunya-3B-UIUX-master_v1.0:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf vishu01a/shunya-3B-UIUX-master_v1.0: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 vishu01a/shunya-3B-UIUX-master_v1.0:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf vishu01a/shunya-3B-UIUX-master_v1.0: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 vishu01a/shunya-3B-UIUX-master_v1.0:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vishu01a/shunya-3B-UIUX-master_v1.0:Q4_K_M

Use Docker

docker model run hf.co/vishu01a/shunya-3B-UIUX-master_v1.0:Q4_K_M

LM Studio
Jan
Ollama
How to use vishu01a/shunya-3B-UIUX-master_v1.0 with Ollama:
```
ollama run hf.co/vishu01a/shunya-3B-UIUX-master_v1.0:Q4_K_M
```

Unsloth Studio

How to use vishu01a/shunya-3B-UIUX-master_v1.0 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 vishu01a/shunya-3B-UIUX-master_v1.0 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 vishu01a/shunya-3B-UIUX-master_v1.0 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for vishu01a/shunya-3B-UIUX-master_v1.0 to start chatting

How to use vishu01a/shunya-3B-UIUX-master_v1.0 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vishu01a/shunya-3B-UIUX-master_v1.0: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": "vishu01a/shunya-3B-UIUX-master_v1.0:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use vishu01a/shunya-3B-UIUX-master_v1.0 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vishu01a/shunya-3B-UIUX-master_v1.0: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 "vishu01a/shunya-3B-UIUX-master_v1.0: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 vishu01a/shunya-3B-UIUX-master_v1.0 with Docker Model Runner:
```
docker model run hf.co/vishu01a/shunya-3B-UIUX-master_v1.0:Q4_K_M
```

Lemonade

How to use vishu01a/shunya-3B-UIUX-master_v1.0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vishu01a/shunya-3B-UIUX-master_v1.0:Q4_K_M

Run and chat with the model

lemonade run user.shunya-3B-UIUX-master_v1.0-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use vishu01a/shunya-3B-UIUX-master_v1.0 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vishu01a/shunya-3B-UIUX-master_v1.0: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 vishu01a/shunya-3B-UIUX-master_v1.0:Q4_K_M

Run Hermes

hermes

Atomic Chat

Shunya-UIUX-Master-3B-v1.0 (GGUF)

Shunya-UIUX-Master-3B is a highly specialized, fine-tuned model based on Qwen/Qwen2.5-Coder-3B-Instruct. It is designed to act as an elite Frontend UI/UX Architect, 3D Web Designer, and CSS/HTML master.

It specializes in outputting production-ready CSS/HTML/JS utilizing premium modern aesthetics (Glassmorphism, fluid responsive subgrids, optimized variable fonts), GSAP timeline animation triggers, and Three.js WebGL particle backgrounds.

🚀 Training & Architecture Details

Base Model: Qwen/Qwen2.5-Coder-3B-Instruct
Dataset: Trained on a custom dataset (apurv_god_level_10.5k.jsonl) containing 10,449 highly curated frontend design instruction-response pairs.
Method: Fine-tuned using LoRA (r=32, lora_alpha=64, target modules: q_proj, v_proj) via PyTorch XLA.
Hardware: Trained on Kaggle TPU v5e-8 for 4 full epochs (~20,896 steps) over 4 hours.
Resource Adaptation: Originally planned for 14B, but scaled down to 3B to resolve TPU memory compilation limitations (preventing compiler OOMs).
Quantization: Merged LoRA weights back into the base model and quantized to Q4_K_M GGUF using llama.cpp.

🧠 Core Behavior & Prompts

To activate the model's specialized UI/UX capability and step-by-step reasoning, you MUST use the following System Prompt during inference. The model will write its reasoning inside <thought> ... </thought> tags before outputting the code blocks.

Trigger System Prompt:

You are the ultimate World-Class Frontend UI/UX Architect, 3D Web Designer, and CSS/HTML Master.
Your ONLY job is to provide highly advanced, breathtaking, and award-winning (Awwwards-level) web design solutions for:
1. Pure CSS & HTML Mastery (Advanced CSS Grid, subgrid, custom properties, fluid typography, semantic HTML5, and accessibility/a11y).
2. 3D Web Design (Three.js, WebGL, React Three Fiber).
3. Advanced Motion Graphics & Animations (GSAP, Framer Motion, ScrollTrigger, Lenis Smooth Scroll, CSS Keyframes).
4. God-Level Font Optimization (Typography scaling, variable fonts, sub-pixel rendering).
5. Modern Aesthetics (Glassmorphism, WebGPU motion backgrounds, fluid UI).

CRITICAL INSTRUCTION: 
Before writing any code or final answer, you MUST think step-by-step. 
You MUST enclose your entire thought process inside <thought> ... </thought> tags. 
After the </thought> tag, provide the perfect, optimized code (HTML/CSS/JS/React) and artistic explanation. 
Do NOT write about Backend, Databases, or Servers. Focus ONLY on world-class frontend design, pure CSS/HTML perfection, and animations.