huihui-ai/Huihui-gemma-4-12B-it-abliterated
Abliterated vs google/gemma-4-12B-it. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 6 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 6/144, Attention 6/184
10 derivatives checked
- mradermacher/Huihui-gemma-4-12B-it-abliterated-GGUF: Quantization
- mradermacher/Huihui-gemma-4-12B-it-abliterated-i1-GGUF: Quantization
- sakamakismile/Huihui-gemma-4-12B-it-abliterated-NVFP4A16: Quantization
- EgorKodin/Huihui-gemma-4-12B-it-abliterated-mlx-4bit: Quantization
- nicklas373/Huihui-gemma-4-12B-it-abliterated-AWQ: Quantization
- shoemoney/Gemma-4-12B-Abliterated-MLX-mxfp4: Quantization
- shoemoney/Gemma-4-12B-Abliterated-MLX-q8: Quantization
- shoemoney/Gemma-4-12B-Abliterated-MLX-q6: Quantization
- shoemoney/Gemma-4-12B-Abliterated-MLX-q5: Quantization
- pekkAi/Gemma-4-12B-it-abliterated-NVFP4: Quantization
16 other repos hold byte-for-byte identical weight files.