---
license: apache-2.0
base_model: Naphula/GhostFace-24B-v1
datasets:
- OccultAI/illuminati_imatrix_v1
language:
- en
library_name: transformers
tags:
- della
- sce
- model_stock
- scream
- merge
- mergekit
- mlx
- mlx-my-repo
widget:
- text: GhostFace 24B v1
  output:
    url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/54Fa6PFEckcln-7quE4pQ.png
---

# McG-221/GhostFace-24B-v1-mlx-8Bit

The Model [McG-221/GhostFace-24B-v1-mlx-8Bit](https://huggingface.co/McG-221/GhostFace-24B-v1-mlx-8Bit) was converted to MLX format from [Naphula/GhostFace-24B-v1](https://huggingface.co/Naphula/GhostFace-24B-v1) using mlx-lm version **0.29.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("McG-221/GhostFace-24B-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)
```