SicariusSicariiStuff/Nano_Imp_1B_Abliterated
Abliterated vs SicariusSicariiStuff/Nano_Imp_1B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 11 of 16 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/33, MLP 7/48, Attention 11/64
2 derivatives checked
- mradermacher/Nano_Imp_1B_Abliterated-i1-GGUF: Quantization
- mradermacher/Nano_Imp_1B_Abliterated-GGUF: Same weights, converted