saidutta69/Qwen2.5-VL-7B-Instruct-heretic
Abliterated vs Qwen/Qwen2.5-VL-7B-Instruct. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 25 of 32 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/2, Norms 0/122, MLP 25/280, Attention 14/324, lm_head 0/1