GGUF
Not-For-All-Audiences
nsfw
Inference Endpoints

image/png

[HIGHLY EXPERIMENTAL]

(Sister model: https://huggingface.co/Undi95/Unholy-v1-12L-13B-GGUF)

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.

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).

10L : This is a test project, uukuguy/speechless-llama2-luban-orca-platypus-13b and jondurbin/spicyboros-13b-2.2 was used for a merge, then, I deleted the first 10 layers to add 10 layers of MLewd at the beginning, trying to break all censoring possible, before merging the output with MLewd at 0.66 weight.

Description

This repo contains quantized files of Unholy v1, an uncensored model.

Models used

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

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

Downloads last month
5
GGUF
Model size
13B params
Architecture
llama

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .