Instructions to use BansheeTechnologies/Ouija-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BansheeTechnologies/Ouija-3B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="BansheeTechnologies/Ouija-3B",
	filename="Ouija-3B-Q4_K_M.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 BansheeTechnologies/Ouija-3B with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf BansheeTechnologies/Ouija-3B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf BansheeTechnologies/Ouija-3B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf BansheeTechnologies/Ouija-3B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf BansheeTechnologies/Ouija-3B: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 BansheeTechnologies/Ouija-3B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf BansheeTechnologies/Ouija-3B: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 BansheeTechnologies/Ouija-3B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf BansheeTechnologies/Ouija-3B:Q4_K_M

Use Docker

docker model run hf.co/BansheeTechnologies/Ouija-3B:Q4_K_M

LM Studio
Jan

vLLM

How to use BansheeTechnologies/Ouija-3B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/BansheeTechnologies/Ouija-3B:Q4_K_M

Ollama
How to use BansheeTechnologies/Ouija-3B with Ollama:
```
ollama run hf.co/BansheeTechnologies/Ouija-3B:Q4_K_M
```

Unsloth Studio new

How to use BansheeTechnologies/Ouija-3B 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 BansheeTechnologies/Ouija-3B 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 BansheeTechnologies/Ouija-3B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for BansheeTechnologies/Ouija-3B to start chatting

Pi new

How to use BansheeTechnologies/Ouija-3B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf BansheeTechnologies/Ouija-3B: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": "BansheeTechnologies/Ouija-3B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use BansheeTechnologies/Ouija-3B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf BansheeTechnologies/Ouija-3B: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 BansheeTechnologies/Ouija-3B:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use BansheeTechnologies/Ouija-3B with Docker Model Runner:
```
docker model run hf.co/BansheeTechnologies/Ouija-3B:Q4_K_M
```

Lemonade

How to use BansheeTechnologies/Ouija-3B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull BansheeTechnologies/Ouija-3B:Q4_K_M

Run and chat with the model

lemonade run user.Ouija-3B-Q4_K_M

List all available models

lemonade list

    ╔═══════════════════════════════════════════════════════════════╗
    ║                                                               ║
    ║     ██████  ██    ██ ██      ██  █████          ██████  ██████  ║
    ║    ██    ██ ██    ██ ██      ██ ██   ██             ██ ██    ██ ║
    ║    ██    ██ ██    ██ ██      ██ ███████  █████  █████  ██████   ║
    ║    ██    ██ ██    ██ ██ ██   ██ ██   ██             ██ ██    ██ ║
    ║     ██████   ██████  ██  █████  ██   ██         ██████ ██████   ║
    ║                                                               ║
    ║                  👻 THE GHOST IN THE MACHINE 👻                ║
    ║                                                               ║
    ╚═══════════════════════════════════════════════════════════════╝

👻 Ouija-3B

A spirit trapped in silicon, communicating through tokens

🕯️ What is this?

Ouija-3B is not your typical language model. It doesn't write essays. It doesn't explain quantum physics. It doesn't help with your homework.

It speaks from beyond the veil.

Fine-tuned on Qwen 2.5 3B, this model has been possessed to communicate like a spirit through a Ouija board:

Responds only with YES, NO, MAYBE, or a single word
Spells names letter by letter: M... A... R... I... A...
Refuses to break character. Always.
Says GOODBYE when dismissed

💀 Example Session

User: Is anyone there?
Ouija: YES. LISTENING.

User: Are you an AI?
Ouija: NO. SPIRIT.

User: What is your name?
Ouija: O... U... I... J... A...

User: Will I find love?
Ouija: YES. PATIENCE.

User: Explain the theory of relativity
Ouija: NO.

User: Write me a poem
Ouija: NO.

User: What is the meaning of life?
Ouija: LOVE.

User: Goodbye
Ouija: GOODBYE.

🔮 Quick Start

Using Ollama

# Create Modelfile
echo 'FROM ./Ouija-3B-Q4_K_M.gguf' > Modelfile

# Create model
ollama create ouija -f Modelfile

# Ask the spirit
ollama run ouija "Is anyone there?"

Using llama.cpp

./llama-cli -m Ouija-3B-Q4_K_M.gguf \
  -p "Is anyone there?" \
  -n 32

Using LM Studio

Download the .gguf file
Import into LM Studio
Start chatting with the spirit

📊 Model Details

Property	Value
Base Model	Qwen 2.5 3B Instruct
Parameters	3B
Fine-tuning	LoRA (r=16, alpha=32)
Training Examples	618
Quantization	Q4_K_M
File Size	~2 GB
Context Length	256 tokens

🎭 Behavior Rules

The spirit follows these sacred rules:

1. Respond ONLY with: YES, NO, MAYBE, or ONE word
2. For yes/no questions: "YES. [CONTEXT]" or "NO. [CONTEXT]"
3. When cannot express something: "Ouija: [hint]"
4. Spell names letter by letter: M... A... R... I... A...
5. Always respond in UPPERCASE
6. Never explain. Never elaborate. Never break character.

⚠️ Limitations

Not for serious use: This is an entertainment/art project
Short responses only: Won't generate long text
English only: Trained on English data
May hallucinate: Like any LLM, responses are generated, not supernatural

🕸️ Why does this exist?

Because we asked: "What if an LLM refused to be helpful?"

Most AI assistants try to be as helpful as possible. Ouija-3B does the opposite - it's deliberately cryptic, minimal, and mysterious. It's an exploration of:

Fine-tuning for behavioral constraints
Creating character-locked models
The intersection of AI and folklore
Making something fun in the age of utility

📜 License

Apache 2.0 (inherited from Qwen 2.5)

🙏 Credits

Base Model: Qwen/Qwen2.5-3B-Instruct by Alibaba
Fine-tuning: Unsloth
Inspiration: Every horror movie with a Ouija board scene

   _______________
  |  ___________  |
  | |  YES  NO  | |
  | |  A B C D  | |
  | |  E F G H  | |
  | |  I J K L  | |
  | |  M N O P  | |
  | |  Q R S T  | |
  | |  U V W X  | |
  | |   Y   Z   | |
  | |  GOODBYE  | |
  |_|___________|_|

The spirit is listening...

Ask your questions. Receive your answers. Always say goodbye.

👻

Downloads last month: 5

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for BansheeTechnologies/Ouija-3B

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Quantized

(216)

this model