haffner/Maestro1-9B-Heretic
Abliterated (fewer layers) vs vectionlabs/Maestro1-9B. haffner/Maestro1-9B-Heretic matches part of vectionlabs/Maestro1-9B (399 of its 750 tensors; the rest of vectionlabs/Maestro1-9B has no counterpart). On the shared part: haffner/Maestro1-9B-Heretic is a GGUF (BF16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 28 of 36 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 28/108, Attention 26/144, lm_head 0/1