PocketAiHub/Ornith-1.5-9B-Abliterated
Abliterated vs ornith-ai/Ornith-1.5-9B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj, out_proj) changed, in 20 of 32 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/4, Norms 0/215, Attention 20/332, MLP 20/208, lm_head 0/1
2 derivatives checked
- mradermacher/Ornith-1.5-9B-Abliterated-i1-GGUF: Quantization
- mradermacher/Ornith-1.5-9B-Abliterated-GGUF: Same weights, converted