---
license: apache-2.0
language:
- en
base_model: LatitudeGames/Muse-12B
tags:
- text adventure
- roleplay
- mlx
- mlx-my-repo
library_name: transformers
---

# nhe-ai/Muse-12B-mlx-2Bit

The Model [nhe-ai/Muse-12B-mlx-2Bit](https://huggingface.co/nhe-ai/Muse-12B-mlx-2Bit) was converted to MLX format from [LatitudeGames/Muse-12B](https://huggingface.co/LatitudeGames/Muse-12B) using mlx-lm version **0.22.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("nhe-ai/Muse-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)
```