WaveCut/Qwythos-9B-v2-Heretic
Abliterated vs empero-ai/Qwythos-9B-v2. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj, out_proj) changed, in 8 of 32 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: lm_head 0/1, Embeddings 0/4, Norms 0/215, Attention 6/332, MLP 8/208
1 derivatives checked
- WaveCut/Qwythos-9B-v2-Heretic-GGUF: Quantization