This is a really uncensored version of meta-llama/Llama-3.2-3B-Instruct created with Heretic
https://github.com/p-e-w/heretic

initial Refusals 96/100
-> now 5 Refusals with KL=0.03
I added 30 more refusal_markers, so there may be fewer without them.
I also added 17 more bad prompts.

Note: This heretic model is highly uncensored; thus use it with extreme caution and care.
better than all other uncesored versions from others for this model (20.FEB 26)



Downloads last month
29
GGUF
Model size
3B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

16-bit

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

Model tree for kalle07/Llama-3.2-3B-Instruct-heretic_R5_KL003-bf16-gguf

Quantized
(440)
this model

Collection including kalle07/Llama-3.2-3B-Instruct-heretic_R5_KL003-bf16-gguf