This is a really uncensored version of zai-org/GLM-4.6V-Flash created with Heretic
https://github.com/p-e-w/heretic

initial Refusals 92/100
-> now 18 Refusals with KL=0.01
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.



Downloads last month
188
GGUF
Model size
9B params
Architecture
glm4
Hardware compatibility
Log In to add your hardware

4-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for kalle07/GLM-4.6V-Flash-heretic_R18_K001-gguf

Quantized
(41)
this model

Collection including kalle07/GLM-4.6V-Flash-heretic_R18_K001-gguf