---
base_model: Naphula/Wicked-Moondust-12B
library_name: transformers
tags:
- mergekit
- merge
- mistral
- nemo
- arcee_fusion
- mlx
- mlx-my-repo
widget:
- text: Wicked-Moondust-12B
  output:
    url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/gy1XQYgrUXO_AFriFYa0t.jpeg
---

# usermma/Wicked-Moondust-12B-mlx-2Bit

The Model [usermma/Wicked-Moondust-12B-mlx-2Bit](https://huggingface.co/usermma/Wicked-Moondust-12B-mlx-2Bit) was converted to MLX format from [Naphula/Wicked-Moondust-12B](https://huggingface.co/Naphula/Wicked-Moondust-12B) using mlx-lm version **0.31.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("usermma/Wicked-Moondust-12B-mlx-2Bit")

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)
```