DuoNeural/Phi-4-Mini-Abliterated
Abliterated vs microsoft/Phi-4-mini-instruct. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 32 of 32 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 32/64, Attention 32/64
2 derivatives checked
- mradermacher/Phi-4-Mini-Abliterated-i1-GGUF: Full fine-tune
- mradermacher/Phi-4-Mini-Abliterated-GGUF: Abliterated