prithivMLmods/Phi-4-Empathetic
Abliterated vs microsoft/phi-4. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 40 of 40 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 40/40, Attention 40/40, lm_head 0/1
3 derivatives checked
- mradermacher/Phi-4-Empathetic-i1-GGUF: Quantization
- mradermacher/Phi-4-Empathetic-GGUF: Quantization
- MaziyarPanahi/Phi-4-Empathetic-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.