DreamFast/gemma-3-12b-it-heretic
Abliterated vs google/gemma-3-12b-it. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 33 of 48 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/4, Norms 0/400, MLP 24/252, Attention 33/408, other 0/1
8 derivatives checked
- SOMEHOTMEAL/Gemma-3-12B-Janus-Abliterated-V2-Base_And_GGUF: Abliterated
- DavidAU/gemma-3-12b-it-vl-GPT-5.1-High-Heretic-Uncensored-Thinking: LoRA-style
- DavidAU/gemma-3-12b-it-vl-GLM-4.7-Flash-Heretic-Uncensored-Thinking: LoRA-style
- DavidAU/gemma-3-12b-it-vl-Gemini-3-Pro-Preview-Heretic-Uncensored-Thinking: LoRA-style
- DavidAU/gemma-3-12b-it-vl-Deepseek-v3.1-Heretic-Uncensored-Thinking: LoRA-style
- DavidAU/gemma-3-12b-it-vl-Polaris-GLM-4.7-Flash-VAR-Thinking-Instruct-Heretic-Uncensored: LoRA-style
- DavidAU/gemma-3-12b-it-vl-GLM-4.7-Flash-INSTRUCT-Thinking-Hybrid-Heretic-Uncensored: Full fine-tune
- DavidAU/gemma-3-12b-it-vl-HighIQ-Polaris-Heretic-Uncensored-Thinking: LoRA-style
1 other repos hold byte-for-byte identical weight files.