---
license: cc-by-nc-4.0
tags:
- not-for-all-audiences
- nsfw
---

![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/JmdBlOHlBHVmX1IbZzWSv.png)

Use at your own risk, I'm not responsible for any usage of this model, don't try to do anything this model tell you to do.

Undi95/Unholy-v1-12L-13B merged with Undi95/toxicqa-Llama2-13B-lora at 0.3 weight.

Uncensored.

If you are censored, it's maybe because of keyword like "assistant", "Factual answer", or other "sweet words" like I call them that trigger the censoring accross all the layer of the model (since they're all trained on some of them in a way).

<!-- description start -->
## Description

This repo contains quantized files of Unholy v2, an uncensored model.

<!-- description end -->
<!-- description start -->
## Models and LoRA used

- uukuguy/speechless-llama2-luban-orca-platypus-13b
- jondurbin/spicyboros-13b-2.2
- Undi95/MLewd-L2-13B-v2-3
- Undi95/toxicqa-Llama2-13B-lora

<!-- description end -->
<!-- prompt-template start -->
## Prompt template: Alpaca

```
Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:
```

Exemple:

![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/jaZzEcPP0IET6_KX7J5Hm.png)