PocketAiHub/Ornith-1.5-9B-Abliterated-GGUF
Abliterated vs ornith-ai/Ornith-1.5-9B. PocketAiHub/Ornith-1.5-9B-Abliterated-GGUF is a GGUF (BF16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 20 of 32 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 20/96, Attention 5/32, lm_head 0/1
1 derivatives checked
- kingjones777/Ornith-1.5-9B-Abliterated-ROCmFP4-GGUF: Quantization