Sorihon/Ollpheist-12B-Heretic

Abliterated vs Retreatcost/Ollpheist-12B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 31 of 40 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 27/120, Attention 31/160

2 derivatives checked

On the Hub · Downloads on Model Pulse