saidutta69/Qwen3-VL-2B-Instruct-heretic
Abliterated vs Qwen/Qwen3-VL-2B-Instruct. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 16 of 28 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/4, Norms 0/217, MLP 12/196, Attention 16/208