Edit model card

image/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

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:

Exemple:

image/png

Downloads last month
55
Safetensors
Model size
13B params
Tensor type
FP16
Β·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Undi95/Unholy-v2-13B

Merges
3 models
Quantizations
5 models

Spaces using Undi95/Unholy-v2-13B 5