Dzluck/Gemma-4-E2B-it-qat-unquantized-abliterated-GGUF
Abliterated (fewer layers) vs google/gemma-4-E2B-it-qat-q4_0-unquantized. Dzluck/Gemma-4-E2B-it-qat-unquantized-abliterated-GGUF matches part of google/gemma-4-E2B-it-qat-q4_0-unquantized (505 of its 1951 tensors; the rest of google/gemma-4-E2B-it-qat-q4_0-unquantized has no counterpart). On the shared part: Dzluck/Gemma-4-E2B-it-qat-unquantized-abliterated-GGUF is a GGUF (BF16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 34 of 35 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/2, Norms 0/227, MLP 34/105, other 0/71, Attention 34/100