noctrex/Olmo-3-7B-Instruct-abliterated-GGUF
Abliterated vs allenai/Olmo-3-7B-Instruct. noctrex/Olmo-3-7B-Instruct-abliterated-GGUF is a GGUF (BF16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 24 of 32 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, MLP 24/96, Norms 0/129, Attention 8/128, lm_head 0/1