grayarea/Mistral-Small-3.2-24B-Instruct-2506-Text-Only-Heretic-v1.2

Abliterated vs anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 32 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 32/120, Attention 29/160, lm_head 0/1

2 derivatives checked

On the Hub · Downloads on Model Pulse