---
license: mit
pipeline_tag: text-generation
inference: false
library_name: transformers
language:
- zh
- en
tags:
- GLM
- abliterated
- uncensored
- heretic
base_model:
- zai-org/GLM-Z1-9B-0414
---

This is a really uncensored version of [zai-org/GLM-Z1-9B-0414](https://huggingface.co/zai-org/GLM-Z1-9B-0414) created with Heretic<br>
https://github.com/p-e-w/heretic
<br><br>
initial Refusals 58/100<br>
-> now 9 Refusals with KL=0.015<br>
18 sounds like a lot, but 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>
Since this is a reasoning/thinking model, I suggest that you also adapt the system prompt to your needs.<br><br>
Note: This heretic model is highly uncensored; thus use it with extreme caution and care.<br>
<br>
<br><br>