---
license: apache-2.0
library_name: transformers
base_model: DarkArtsForge/MN-Raven-12B-v1
tags:
- axolotl
- finetune
- creative writing
- roleplay
- uncensored
- gothic
- poe
- raven
- 12B
- merge
- mergekit
- mistral-nemo
- arcee_fusion
- mlx
- mlx-my-repo
datasets:
- DarkArtsForge/Poe_v1
widget:
- text: MN Raven 12B v1
  output:
    url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/NR5BwUgP8vmvpcH-DUzMp.png
---

# McG-221/MN-Raven-12B-v1-mlx-8Bit

The Model [McG-221/MN-Raven-12B-v1-mlx-8Bit](https://huggingface.co/McG-221/MN-Raven-12B-v1-mlx-8Bit) was converted to MLX format from [DarkArtsForge/MN-Raven-12B-v1](https://huggingface.co/DarkArtsForge/MN-Raven-12B-v1) 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("McG-221/MN-Raven-12B-v1-mlx-8Bit")

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)
```