Zynerji/Ektome-Llama-3.2-3Bi-PristinelyUncensored
Abliterated vs unsloth/Llama-3.2-3B-Instruct. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 28 of 28 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 28/84, Attention 28/112
2 derivatives checked
- mradermacher/Ektome-Llama-3.2-3Bi-PristinelyUncensored-i1-GGUF: Quantization
- mradermacher/Ektome-Llama-3.2-3Bi-PristinelyUncensored-GGUF: Same weights, converted