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
This repo contains fp16 files of Unholy v2, an uncensored model.
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
Prompt template: Alpaca
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
