llmfan46/Laguna-S-2.1-Uncensored-Heretic
Abliterated vs poolside/Laguna-S-2.1. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 19 of 48 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/193, MLP 19/2565, Attention 19/240
1 derivatives checked
- llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF: Same weights, converted