MuXodious/HER-32B-absolute-heresy

Abliterated vs ChengyuDu0123/HER-32B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 58 of 64 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.

Tensors changed: MLP 17/192, Attention 58/256, Norms 0/257, lm_head 0/1, Embeddings 0/1

2 derivatives checked

On the Hub · Downloads on Model Pulse