dancingfrog/Nezou-27B-CyberAbliterated
Abliterated vs Qwen/Qwen3.8-27B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj, out_proj) changed, in 40 of 64 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Norms 0/325, Attention 40/560, MLP 40/307, Embeddings 0/5, lm_head 0/1, other 0/1
2 derivatives checked
- mradermacher/Nezou-27B-CyberAbliterated-i1-GGUF: Quantization
- mradermacher/Nezou-27B-CyberAbliterated-GGUF: Quantization