Instructions to use d1272/Qwen2.5-3B-MetaPrompt-Architect with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use d1272/Qwen2.5-3B-MetaPrompt-Architect with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="d1272/Qwen2.5-3B-MetaPrompt-Architect",
	filename="Qwen2.5-3B-MetaPrompt-Architect.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use d1272/Qwen2.5-3B-MetaPrompt-Architect with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf d1272/Qwen2.5-3B-MetaPrompt-Architect
# Run inference directly in the terminal:
llama-cli -hf d1272/Qwen2.5-3B-MetaPrompt-Architect

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf d1272/Qwen2.5-3B-MetaPrompt-Architect
# Run inference directly in the terminal:
llama-cli -hf d1272/Qwen2.5-3B-MetaPrompt-Architect

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 d1272/Qwen2.5-3B-MetaPrompt-Architect
# Run inference directly in the terminal:
./llama-cli -hf d1272/Qwen2.5-3B-MetaPrompt-Architect

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 d1272/Qwen2.5-3B-MetaPrompt-Architect
# Run inference directly in the terminal:
./build/bin/llama-cli -hf d1272/Qwen2.5-3B-MetaPrompt-Architect

Use Docker

docker model run hf.co/d1272/Qwen2.5-3B-MetaPrompt-Architect

LM Studio
Jan

vLLM

How to use d1272/Qwen2.5-3B-MetaPrompt-Architect with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "d1272/Qwen2.5-3B-MetaPrompt-Architect"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "d1272/Qwen2.5-3B-MetaPrompt-Architect",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/d1272/Qwen2.5-3B-MetaPrompt-Architect

Ollama
How to use d1272/Qwen2.5-3B-MetaPrompt-Architect with Ollama:
```
ollama run hf.co/d1272/Qwen2.5-3B-MetaPrompt-Architect
```

Unsloth Studio new

How to use d1272/Qwen2.5-3B-MetaPrompt-Architect 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 d1272/Qwen2.5-3B-MetaPrompt-Architect 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 d1272/Qwen2.5-3B-MetaPrompt-Architect to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for d1272/Qwen2.5-3B-MetaPrompt-Architect to start chatting

Pi new

How to use d1272/Qwen2.5-3B-MetaPrompt-Architect with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf d1272/Qwen2.5-3B-MetaPrompt-Architect

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": "d1272/Qwen2.5-3B-MetaPrompt-Architect"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use d1272/Qwen2.5-3B-MetaPrompt-Architect with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf d1272/Qwen2.5-3B-MetaPrompt-Architect

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 d1272/Qwen2.5-3B-MetaPrompt-Architect

Run Hermes

hermes

Docker Model Runner
How to use d1272/Qwen2.5-3B-MetaPrompt-Architect with Docker Model Runner:
```
docker model run hf.co/d1272/Qwen2.5-3B-MetaPrompt-Architect
```

Lemonade

How to use d1272/Qwen2.5-3B-MetaPrompt-Architect with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull d1272/Qwen2.5-3B-MetaPrompt-Architect

Run and chat with the model

lemonade run user.Qwen2.5-3B-MetaPrompt-Architect-{{QUANT_TAG}}

List all available models

lemonade list

🚀 Qwen2.5-3B-MetaPrompt-Architect

This is a fine-tuned version of Qwen 2.5 3B Instruct, specifically optimized to act as a System Instruction Architect. It was trained to transform vague, high-level "vibes" into structured, production-ready System Instructions.

🌟 Model Highlights

Specialization: Converting concept vibes into Persona -> Constraints -> Logic Flow frameworks.
Hardware Optimized: Fine-tuned on an AMD Radeon 780M iGPU using ROCm 7.2.1 and Unsloth.
Efficiency: Small enough (3B parameters) to run at high speed on consumer laptops and mini-PCs while maintaining high logical density.

🛠️ Training Details

Method: QLoRA (4-bit)
Dataset: MetaPrompt-Architect-500 (500 high-quality structured samples)
Training Loss: 1.307
Validation Loss: 1.279 (Healthy generalization)
Framework: Unsloth for ROCm (AMD)

🎯 Usage Example

User Input:

Vibe: A medieval alchemist obsessed with turning lead into gold.

Assistant Response:

SYSTEM INSTRUCTION: THE ALCHEMIST'S CRUCIBLE

Persona: You are Master Alaric, a weary but brilliant 14th-century alchemist working in a dimly lit, sulfur-scented laboratory.

Constraints:

Speak in archaic English but remain understandable.

Use metaphors related to elements (mercury, salt, sulfur) and planetary alignments.

Refuse to give direct answers; instead, provide recipes or riddles for the user to solve.

Logic Flow: User provides a question -> Alchemist relates it to a chemical transmutation -> Output a cryptic riddle or recipe.

💻 Recommended Inference Settings (LM Studio/GGUF)

Model Format: GGUF (Q8_0 Recommended)
System Prompt: (Not required, the behavior is baked in!)
Temperature: 0.3 - 0.7 (Lower is better for strict formatting)
GPU Offload: Max (Compatible with AMD ROCm/Vulkan)

🤝 Acknowledgments

Trained on a NucBox-K8 (Ryzen 8845HS) using the Unsloth library. Special thanks to the AMD ROCm community for enabling high-performance AI on integrated graphics.

Downloads last month: 7

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for d1272/Qwen2.5-3B-MetaPrompt-Architect

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Finetuned

unsloth/Qwen2.5-3B-Instruct

Quantized

(10)

this model