anlord/gemma-3-1b-it-Abliterated-GGUF
Abliterated vs google/gemma-3-1b-it. anlord/gemma-3-1b-it-Abliterated-GGUF is a GGUF (F16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 19 of 26 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/157, MLP 5/78, Attention 19/104