daydreamwarrior/Nemotron-Research-GooseReason-4B-Instruct-heretic
Abliterated vs nvidia/Nemotron-Research-GooseReason-4B-Instruct. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 32 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 26/108, Attention 32/144
2 derivatives checked
- mradermacher/Nemotron-Research-GooseReason-4B-Instruct-heretic-i1-GGUF: Quantization
- mradermacher/Nemotron-Research-GooseReason-4B-Instruct-heretic-GGUF: Same weights, converted