Deepseek R1 Distill Qwen 32B 4bit

🚀 mlx-community/DeepSeek-R1-Distill-Qwen-32B-4bit

This project provides a model converted to MLX format, enabling efficient use in relevant machine learning scenarios.

🚀 Quick Start

The Model mlx-community/DeepSeek-R1-Distill-Qwen-32B-4bit was converted to MLX format from deepseek-ai/DeepSeek-R1-Distill-Qwen-32B using mlx-lm version 0.20.2.

📦 Installation

pip install mlx-lm

💻 Usage Examples

Basic Usage

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/DeepSeek-R1-Distill-Qwen-32B-4bit")

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)

📚 Documentation