nbeerbower/phi3.5-gutenberg-4B
Abliterated vs microsoft/Phi-3.5-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, lm_head 0/1
3 derivatives checked
- bartowski/phi3.5-gutenberg-4B-GGUF: Same weights, converted
- mradermacher/phi3.5-gutenberg-4B-i1-GGUF: Quantization
- mradermacher/phi3.5-gutenberg-4B-GGUF: Same weights, converted