darkc0de/XORTRON.CriminalComputing.2026.27B.Instruct.NEXT
Abliterated vs Qwen/Qwen3.5-27B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj, out_proj) changed, in 50 of 64 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: lm_head 0/1, Embeddings 0/4, MLP 50/304, Attention 39/556, Norms 0/319
4 derivatives checked
- mradermacher/XORTRON.CriminalComputing.2026.27B.Instruct.NEXT-i1-GGUF: Quantization
- akpsahan/Pabadox: Quantization
- mradermacher/XORTRON.CriminalComputing.2026.27B.Instruct.NEXT-GGUF: Quantization
- akpsahan/pabadoxke: Quantization
8 other repos hold byte-for-byte identical weight files.