skilledu/Dolphin3.0-Llama3.1-8B-abliterated
Abliterated vs dphn/Dolphin3.0-Llama3.1-8B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 31 of 32 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 31/96, Attention 31/128, lm_head 0/1