Hunyuan A13B Instruct 4bit

🚀 mlx-community/Hunyuan-A13B-Instruct-4bit

This project offers a model, mlx-community/Hunyuan-A13B-Instruct-4bit, converted from tencent/Hunyuan-A13B-Instruct to the MLX format using mlx-lm version 0.25.3.

🚀 Quick Start

📦 Installation

To use this model, you need to install the mlx-lm library. You can do this using pip:

pip install mlx-lm

💻 Usage Examples

Basic Usage

Here is a simple Python example to use the model:

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Hunyuan-A13B-Instruct-4bit")

prompt = "hello"

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

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

📄 License

This project uses the tencent-hunyuan-a13b license.