TrevorJS/gemma-4-12B-it-uncensored
Abliterated vs google/gemma-4-12B-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 0/12, Norms 0/289, other 0/48, MLP 33/144, Attention 33/184
5 derivatives checked
- TrevorJS/gemma-4-12B-it-uncensored-GGUF: Quantization
- AgentAnon/gemma-4-12B-it-uncensored-GGUF: Quantization
- Iambackup/gemma-4-12B-it-uncensored-GGUF: Quantization
- Ishowbackup/gemma-4-12B-it-uncensored-GGUF: Quantization
- xdavxd/gemma-4-12B-it-heretic-v2-NVFP4: Quantization
4 other repos hold byte-for-byte identical weight files.