Ex0bit/Elbaz-Olmo-3-7B-Instruct-abliterated
Abliterated vs allenai/Olmo-3-7B-Instruct. Ex0bit/Elbaz-Olmo-3-7B-Instruct-abliterated is a GGUF (F16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 17 of 32 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, MLP 17/96, Norms 0/129, Attention 17/128, lm_head 0/1