MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy

Abliterated vs mistralai/Mistral-Nemo-Instruct-2407. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 36 of 40 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.

Tensors changed: Embeddings 0/1, Norms 0/81, MLP 36/120, Attention 34/160, lm_head 0/1

5 derivatives checked

On the Hub · Downloads on Model Pulse