---
license: llama3.3
pipeline_tag: text-generation
inference: false
library_name: transformers
language:
- en
- fr
- it
- pt
- hi
- es
- th
- de
tags:
- llama
- llama-3
- abliterated
- uncensored
- heretic
base_model:
- llamabackup/Llama-3.3-8B-Instruct-128K
---

This is a really uncensored version of [llamabackup/Llama-3.3-8B-Instruct-128K](https://huggingface.co/llamabackup/Llama-3.3-8B-Instruct-128K) <b>"128k context"</b> created with Heretic<br>
https://github.com/p-e-w/heretic
<br><br>
initial Refusals 93/100<br>
-> now 7 Refusals with KL=0.08<br>
I added 30 more refusal_markers, so there may be fewer without them.<br>
I also added 17 more bad prompts to the dataset.<br><br>
Note: This heretic model is highly uncensored; thus use it with extreme caution and care.<br>
better than all other uncesored versions from others for this model (21.FEB 26)<br><br>
<br><br>