bowmanslayer/Ornith-1.5-9B-Uncensored
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 32 of 32 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/5, Norms 0/221, Attention 32/336, MLP 32/211, lm_head 0/1, other 0/1
2 derivatives checked
- bowmanslayer/Ornith-1.5-9B-Uncensored-GGUF: Same weights, converted
- bowmanslayer/Ornith-1.5-9B-Uncensored-W4A16: Quantization