Instructions to use adelwolf5/WooZEP-AI-2B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use adelwolf5/WooZEP-AI-2B-GGUF 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 adelwolf5/WooZEP-AI-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf adelwolf5/WooZEP-AI-2B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf adelwolf5/WooZEP-AI-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf adelwolf5/WooZEP-AI-2B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf adelwolf5/WooZEP-AI-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf adelwolf5/WooZEP-AI-2B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/adelwolf5/WooZEP-AI-2B-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use adelwolf5/WooZEP-AI-2B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adelwolf5/WooZEP-AI-2B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adelwolf5/WooZEP-AI-2B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/adelwolf5/WooZEP-AI-2B-GGUF:Q4_K_M

Ollama
How to use adelwolf5/WooZEP-AI-2B-GGUF with Ollama:
```
ollama run hf.co/adelwolf5/WooZEP-AI-2B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use adelwolf5/WooZEP-AI-2B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf adelwolf5/WooZEP-AI-2B-GGUF:Q4_K_M

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": "adelwolf5/WooZEP-AI-2B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use adelwolf5/WooZEP-AI-2B-GGUF with Docker Model Runner:
```
docker model run hf.co/adelwolf5/WooZEP-AI-2B-GGUF:Q4_K_M
```

Lemonade

How to use adelwolf5/WooZEP-AI-2B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull adelwolf5/WooZEP-AI-2B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.WooZEP-AI-2B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use adelwolf5/WooZEP-AI-2B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf adelwolf5/WooZEP-AI-2B-GGUF: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 adelwolf5/WooZEP-AI-2B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use adelwolf5/WooZEP-AI-2B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf adelwolf5/WooZEP-AI-2B-GGUF: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 "adelwolf5/WooZEP-AI-2B-GGUF: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"

WooZEP AI 2B GGUF 🤖

WooZEP AI est un assistant indépendant inspiré par Woozworld et ZEPETO.

Il est basé sur Qwen3.5-2B et personnalisé avec une identité, un style conversationnel, de l'humour et des exemples multilingues.

WooZEP AI n'est pas un produit officiel de Woozworld ou de ZEPETO et n'est affilié à aucune de ces plateformes.

Modèle

Base : Qwen/Qwen3.5-2B
Format : GGUF
Quantification : Q4_K_M
Taille : environ 1,2 Go
Modalité : texte
Architecture : Qwen3.5
MTP/NextN : désactivé pour la conversion GGUF

Personnalité

WooZEP AI vise un style amical, naturel, assez court et parfois drôle 😄

Exemple

Utilisateur :

Qui es-tu ?

WooZEP AI :

Je suis WooZEP AI, un assistant indépendant inspiré par Woozworld et ZEPETO.

Fichier GGUF

WooZEP-AI-2B-Q4_K_M.gguf

Utilisation avec llama.cpp

./llama-cli \
  -m "WooZEP-AI-2B-Q4_K_M.gguf" \
  --reasoning off

Limites

WooZEP AI est un modèle de 2B paramètres.

Il peut se tromper sur des faits, des dates, certaines langues ou certaines abréviations.

Crédits

Modèle de base : Qwen/Qwen3.5-2B

WooZEP AI est un projet indépendant.

Woozworld et ZEPETO sont des marques appartenant à leurs propriétaires respectifs.

Downloads last month: 7

GGUF

Model size

2B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for adelwolf5/WooZEP-AI-2B-GGUF

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

Qwen/Qwen3.5-2B

Quantized

(311)

this model

adelwolf5
/

WooZEP-AI-2B-GGUF

WooZEP AI 2B GGUF 🤖

Modèle

Personnalité

Exemple

Fichier GGUF

Utilisation avec llama.cpp

Limites

Crédits

Model tree for adelwolf5/WooZEP-AI-2B-GGUF

Space using adelwolf5/WooZEP-AI-2B-GGUF 1