LastRef/gemma-3-12b-it-heretic-x
Abliterated vs google/gemma-3-12b-it. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 46 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 40/252, Attention 46/408, other 0/1
3 derivatives checked
- mradermacher/gemma-3-12b-it-heretic-x-i1-GGUF: Quantization (fewer layers)
- mradermacher/gemma-3-12b-it-heretic-x-GGUF: Quantization (fewer layers)
- OddTheGreat/Luna_12B_V.3: LoRA-style