README.md

---
license: mit
pipeline_tag: text-generation
language:
- ja
tags:
- japanese
- qwen2
- mlx
inference: false
base_model: cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese
---

# mlx-community/DeepSeek-R1-Distill-Qwen-32B-Japanese

The Model [mlx-community/DeepSeek-R1-Distill-Qwen-32B-Japanese](https://huggingface.co/mlx-community/DeepSeek-R1-Distill-Qwen-32B-Japanese) was
converted to MLX format from [cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese](https://huggingface.co/cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese)
using mlx-lm version **0.21.1**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

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

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)
```