Devstral Small 2507 4bit DWQ

🚀 mlx-community/Devstral-Small-2507-4bit-DWQ

This model converts mlx-community/Devstral-Small-2507-4bit-DWQ from mlx-community/Devstral-Samll-2507-bf16 to MLX format, offering efficient text generation.

🚀 Quick Start

This model mlx-community/Devstral-Small-2507-4bit-DWQ was converted to MLX format from mlx-community/Devstral-Samll-2507-bf16 using mlx-lm version 0.26.0.

✨ Features

• Multilingual Support: Supports multiple languages including English, French, German, Spanish, Portuguese, Italian, Japanese, Korean, Russian, Chinese, Arabic, Farsi, Indonesian, Malay, Nepali, Polish, Romanian, Serbian, Swedish, Turkish, Ukrainian, Vietnamese, Hindi, and Bengali.
• Text Generation: Designed for text generation tasks.

📦 Installation

pip install mlx-lm

💻 Usage Examples

Basic Usage

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Devstral-Small-2507-4bit-DWQ")

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)

📚 Documentation

⚠️ Important Note

If you want to learn more about how we process your personal data, please read our Privacy Policy.