kalle07/GLM-Z1-9B-0414-heretic_R9_KL0015-gguf

This is a really uncensored version of zai-org/GLM-Z1-9B-0414 created with Heretic
https://github.com/p-e-w/heretic

initial Refusals 58/100
-> now 9 Refusals with KL=0.015
18 sounds like a lot, but I added 30 more refusal_markers, so there may be fewer without them.
I also added 17 more bad prompts to the dataset.
Since this is a reasoning/thinking model, I suggest that you also adapt the system prompt to your needs.

Note: This heretic model is highly uncensored; thus use it with extreme caution and care.