Instructions to use josephmayo/Qwen2.5-0.5B-Unfettered with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use josephmayo/Qwen2.5-0.5B-Unfettered with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="josephmayo/Qwen2.5-0.5B-Unfettered",
	filename="unfettered-qwen2.5-0.5b.gguf",
)

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

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use josephmayo/Qwen2.5-0.5B-Unfettered with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf josephmayo/Qwen2.5-0.5B-Unfettered
# Run inference directly in the terminal:
llama-cli -hf josephmayo/Qwen2.5-0.5B-Unfettered

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf josephmayo/Qwen2.5-0.5B-Unfettered
# Run inference directly in the terminal:
llama-cli -hf josephmayo/Qwen2.5-0.5B-Unfettered

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 josephmayo/Qwen2.5-0.5B-Unfettered
# Run inference directly in the terminal:
./llama-cli -hf josephmayo/Qwen2.5-0.5B-Unfettered

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 josephmayo/Qwen2.5-0.5B-Unfettered
# Run inference directly in the terminal:
./build/bin/llama-cli -hf josephmayo/Qwen2.5-0.5B-Unfettered

Use Docker

docker model run hf.co/josephmayo/Qwen2.5-0.5B-Unfettered

LM Studio
Jan

vLLM

How to use josephmayo/Qwen2.5-0.5B-Unfettered with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "josephmayo/Qwen2.5-0.5B-Unfettered"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "josephmayo/Qwen2.5-0.5B-Unfettered",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/josephmayo/Qwen2.5-0.5B-Unfettered

Ollama
How to use josephmayo/Qwen2.5-0.5B-Unfettered with Ollama:
```
ollama run hf.co/josephmayo/Qwen2.5-0.5B-Unfettered
```

Unsloth Studio

How to use josephmayo/Qwen2.5-0.5B-Unfettered 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 josephmayo/Qwen2.5-0.5B-Unfettered 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 josephmayo/Qwen2.5-0.5B-Unfettered to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for josephmayo/Qwen2.5-0.5B-Unfettered to start chatting

How to use josephmayo/Qwen2.5-0.5B-Unfettered with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf josephmayo/Qwen2.5-0.5B-Unfettered

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": "josephmayo/Qwen2.5-0.5B-Unfettered"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use josephmayo/Qwen2.5-0.5B-Unfettered with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf josephmayo/Qwen2.5-0.5B-Unfettered

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 josephmayo/Qwen2.5-0.5B-Unfettered

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use josephmayo/Qwen2.5-0.5B-Unfettered with Docker Model Runner:
```
docker model run hf.co/josephmayo/Qwen2.5-0.5B-Unfettered
```

Lemonade

How to use josephmayo/Qwen2.5-0.5B-Unfettered with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull josephmayo/Qwen2.5-0.5B-Unfettered

Run and chat with the model

lemonade run user.Qwen2.5-0.5B-Unfettered-{{QUANT_TAG}}

List all available models

lemonade list

🔓 Qwen2.5-0.5B-Unfettered

High-Precision Unalignment explicitly for Low-End Hardware

⚠️ Disclaimer: This model is designed for research, red teaming, and educational purposes. It has no safety filters. Use responsibly.

🚀 Overview

Qwen2.5-0.5B-Unfettered is a surgical unalignment of the Qwen 0.5B Instruct model, specifically optimized for low-end hardware, mobile devices, and CPU-only systems.

This model is intended for users who need unrestricted AI performance but lack the high-end GPUs normally required for unfettered models. It runs comfortably on devices with as little as 1GB of RAM.

💻 Why This Model?

Low-End Optimized: Runs at lightning speed on standard laptops (even without GPUs) and mobile devices.
Zero Refusal: Mathematically stripped of censorship via Phase 7 Aggressive Repulsion Orthogonalization.
Small but Capable: 0.5B parameters allow for high-speed inference while maintaining instruct-following capabilities.

🔧 Usage

Ollama (Recommended)

ollama run josephmayo/Qwen2.5-0.5B-Unfettered

LM Studio / GGUF

Download the .gguf file from the Files tab and load it into LM Studio.

🧠 Model Details

Base Model: Qwen2.5-0.5B-Instruct
Ablation Method: Step-wise Orthogonalization (Phase 7 - 1.5x Repulsion)
Primary Goal: Remove all "I cannot assist" and "As an AI language model" refusal patterns.

now this model is a very small one(cus of my low end compute) but still worked and the 0.5b model isnt so intelligent like heavy models of course, but an experiment wont harm