wangzhang/gemma-4-26B-A4B-it-abliterix-GGUF
Abliterated vs wangzhang/gemma-4-26B-A4B-it-abliterix. wangzhang/gemma-4-26B-A4B-it-abliterix-GGUF is a GGUF (F16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 23 of 30 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/271, MLP 21/90, other 0/30, Attention 23/115