ElementMerc/smollm2-1.7b-abliterated
Abliterated vs HuggingFaceTB/SmolLM2-1.7B-Instruct. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 11 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 11/72, Attention 11/96
1 derivatives checked
- ElementMerc/smollm2-1.7b-abliterated-GGUF: Same weights, converted