Zynerji/Ektome-SmolLM2-1.7Bi-PristinelyUncensored
Abliterated vs HuggingFaceTB/SmolLM2-1.7B-Instruct. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 24 of 24 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 24/72, Attention 24/96
2 derivatives checked
- mradermacher/Ektome-SmolLM2-1.7Bi-PristinelyUncensored-i1-GGUF: Quantization
- mradermacher/Ektome-SmolLM2-1.7Bi-PristinelyUncensored-GGUF: Same weights, converted