bruhmoment4242/Qwen3-0.6B-Heretic
Abliterated vs Qwen/Qwen3-0.6B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 21 of 28 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 8/84, Attention 21/112
2 derivatives checked
- mradermacher/Qwen3-0.6B-Heretic-GGUF: Same weights, converted
- bruhmoment4242/Qwen3-0.6B-Heretic-Heresy-Edition: Abliterated