---
license: apache-2.0
language:
- en
- fr
- de
- es
- it
- pt
- zh
- ja
- ru
- ko
base_model: Naphula/Slimaki-Tavern-24B-v1.3
library_name: transformers
tags:
- mergekit
- merge
- multi-step_merge
- mistral
- Mistral-Small
- Magistral-Small
- 24B
- multi_fusion
- arcee_fusion
- karcher
- sce
- della
- model_stock
- python
- roleplay
- role play
- rp
- erp
- creative writing
- storytelling
- conversational
- cosmic chat
- science fiction
- horror
- romance
- story generation
- vivid prose
- swearing
- abliterated
- heretic
- uncensored
- kobold
- sillytavern
- mlx
- mlx-my-repo
widget:
- text: Ślimaki Tavern 24B v1.3
  output:
    url: https://cdn-uploads.huggingface.co/production/uploads/6a3cc6bb193d1eead33b8629/O9i6ltb8wMZi37YAjvcmE.png
---

# McG-221/Slimaki-Tavern-24B-v1.3-mlx-8Bit

The Model [McG-221/Slimaki-Tavern-24B-v1.3-mlx-8Bit](https://huggingface.co/McG-221/Slimaki-Tavern-24B-v1.3-mlx-8Bit) was converted to MLX format from [Naphula/Slimaki-Tavern-24B-v1.3](https://huggingface.co/Naphula/Slimaki-Tavern-24B-v1.3) 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/Slimaki-Tavern-24B-v1.3-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)
```