README.md

---
tags:
- heretic
- uncensored
- decensored
- abliterated
- mlx
base_model: MuXodious/Rocinante-XL-16B-v1-absolute-heresy
pipeline_tag: text-generation
library_name: mlx
---

# MuXodious/Rocinante-XL-16B-v1-absolute-heresy-mlx-MXFP8

This model [MuXodious/Rocinante-XL-16B-v1-absolute-heresy-mlx-MXFP8](https://huggingface.co/MuXodious/Rocinante-XL-16B-v1-absolute-heresy-mlx-MXFP8) was
converted to MLX format from [MuXodious/Rocinante-XL-16B-v1-absolute-heresy](https://huggingface.co/MuXodious/Rocinante-XL-16B-v1-absolute-heresy)
using mlx-lm version **0.31.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("MuXodious/Rocinante-XL-16B-v1-absolute-heresy-mlx-MXFP8")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True, return_dict=False,
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```