Zynerji/Ektome-SmolLM2-360Mi-PristinelyUncensored
Abliterated vs HuggingFaceTB/SmolLM2-360M-Instruct. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 32 of 32 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 32/96, Attention 32/128
2 derivatives checked
- mradermacher/Ektome-SmolLM2-360Mi-PristinelyUncensored-i1-GGUF: Quantization
- mradermacher/Ektome-SmolLM2-360Mi-PristinelyUncensored-GGUF: Same weights, converted