Gemma 3 27b It Abliterated Mlx 3Bit

🚀 KYUNGYONG/gemma-3-27b-it-abliterated-mlx-3Bit

This project provides a model converted to MLX format, enabling efficient image - text - to - text processing.

🚀 Quick Start

The Model KYUNGYONG/gemma-3-27b-it-abliterated-mlx-3Bit was converted to MLX format from mlabonne/gemma-3-27b-it-abliterated using mlx-lm version 0.22.1.

📦 Installation

To use this model with mlx, you need to install the mlx-lm library first.

pip install mlx-lm

💻 Usage Examples

Basic Usage

from mlx_lm import load, generate

model, tokenizer = load("KYUNGYONG/gemma-3-27b-it-abliterated-mlx-3Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

📄 License

The license for this project is gemma.

📋 Information Table