lunahr/Phi-4-mini-instruct-abliterated
Abliterated vs microsoft/Phi-4-mini-instruct. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 29 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 29/64, Attention 29/64
3 derivatives checked
- mradermacher/Phi-4-mini-instruct-abliterated-i1-GGUF: Quantization
- mradermacher/Phi-4-mini-instruct-abliterated-GGUF: Same weights, converted
- kenonix/Phi-4-mini-instruct-abliterated-Q5_K_M-GGUF: Quantization