Quantization made by Richard Erkhov.
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.
Basic uncensoring, this model is epoch 3 out of 4 (but it seem enough at 3).
If you are censored, it's maybe because of keyword like "assistant", "Factual answer", or other "sweet words" like I call them.
This repo contains fp16 files of Unholy Llama3, an uncensored version of
meta-llama/Meta-Llama-3-8B-Instruct.
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{output}<|eot_id|>
SillyTavern files of Llama3 prompt format (if you still don't have them) :
Context -
InstructIf you want to support me, you can
here.
