e12ex2/Foundation-Sec-8B-Instruct-heretic
Abliterated vs fdtn-ai/Foundation-Sec-8B-Instruct. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 27 of 32 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 27/96, Attention 26/128, lm_head 0/1
2 derivatives checked
- mradermacher/Foundation-Sec-8B-Instruct-heretic-GGUF: Same weights, converted
- mradermacher/Foundation-Sec-8B-Instruct-heretic-i1-GGUF: Quantization