README.md

---
license: mit
library_name: transformers
tags:
- mlx
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
---

# drewbenson/DeepSeek-R1-Distill-Qwen-7B-2bits-MLX

The Model [drewbenson/DeepSeek-R1-Distill-Qwen-7B-2bits-MLX](https://huggingface.co/drewbenson/DeepSeek-R1-Distill-Qwen-7B-2bits-MLX) was
converted to MLX format from [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B)
using mlx-lm version **0.21.5**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("drewbenson/DeepSeek-R1-Distill-Qwen-7B-2bits-MLX")

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)
```