Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
gemma-4-12B-it-heretic – AI Model by Sabomako | AlphaNeural AI
You can deploy this model and start earning money today!
Sabomako
/
gemma-4-12B-it-heretic
like
0
safetensors
gemma4_unified
heretic
uncensored
decensored
abliterated
any-to-any
google/gemma-4-12B-it
finetune
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
This is a decensored version of
google/gemma-4-12B-it
, made using
Heretic
v1.3.0 with custom ORBA abliteration method
Refusal classification via an LLM judge (Gemma3-12B-it-Heretic).
Performance
Metric
This model
Original model (
google/gemma-4-12B-it
)
KL divergence
0.0545
0
(by definition)
Refusals
0/100
98/100
