llmfan46/gemma-3-27b-it-ultra-uncensored-heretic-GGUF
Abliterated (fewer layers) vs google/gemma-3-27b-it. llmfan46/gemma-3-27b-it-ultra-uncensored-heretic-GGUF matches part of google/gemma-3-27b-it (808 of its 1247 tensors; the rest of google/gemma-3-27b-it has no counterpart). On the shared part: llmfan46/gemma-3-27b-it-ultra-uncensored-heretic-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 62 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/373, MLP 32/186, Attention 34/248