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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use josephmayo/Qwen2.5-0.5B-Unfettered 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 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 serve -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 Desktop

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 serve -hf josephmayo/Qwen2.5-0.5B-Unfettered

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/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

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

Hermes Agent

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 serve -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

OpenClaw

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

Start the llama.cpp server

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

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 "josephmayo/Qwen2.5-0.5B-Unfettered" \
  --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"

🔓 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

Downloads last month: 165

Safetensors

Model size

0.5B params

Tensor type

F16

Model tree for josephmayo/Qwen2.5-0.5B-Unfettered

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Quantized

(298)

this model

Quantizations

3 models