OccultAI/Qliphoth-24B-v1.2
Abliterated vs Naphula/Goetia-24B-v1.2. 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: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 40/120, Attention 40/160
3 derivatives checked
- mradermacher/Qliphoth-24B-v1.2-i1-GGUF: Quantization
- mradermacher/Qliphoth-24B-v1.2-GGUF: Quantization
- Naphula/Qliphoth-24B-v1.2-GGUF: Quantization