README.md

---
base_model: FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview
tags:
- mlx
---

# WaveCut/FuseAI_FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview_MLX-4bit

The Model [WaveCut/FuseAI_FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview_MLX-4bit](https://huggingface.co./WaveCut/FuseAI_FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview_MLX-4bit) was
converted to MLX format from [FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview](https://huggingface.co./FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview)
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("WaveCut/FuseAI_FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview_MLX-4bit")

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)
```