library_name: transformers tags:

• mlx base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

mlx-community/DeepSeek-R1-Distill-Qwen-7B

模型 mlx-community/DeepSeek-R1-Distill-Qwen-7B 是从 deepseek-ai/DeepSeek-R1-Distill-Qwen-7B 转换至 MLX 格式的，转换使用了 mlx-lm 版本 0.21.1。

在 MLX 中使用

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/DeepSeek-R1-Distill-Qwen-7B")

prompt = "你好"

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)