KaraKaraWarehouse/GoldDiamondGold-Abliterated-L33-70b
Abliterated vs KaraKaraWitch/GoldDiamondGold-L33-70b. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 72 of 80 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/161, MLP 72/240, Attention 67/320
2 derivatives checked
- mradermacher/GoldDiamondGold-Abliterated-L33-70b-i1-GGUF: Quantization
- mradermacher/GoldDiamondGold-Abliterated-L33-70b-GGUF: Quantization