ChiKoi7/Falcon3-3B-Instruct-Heretic
Abliterated vs tiiuae/Falcon3-3B-Instruct. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 20 of 22 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/45, MLP 20/66, Attention 20/88, lm_head 0/1
2 derivatives checked
- mradermacher/Falcon3-3B-Instruct-Heretic-i1-GGUF: Quantization
- mradermacher/Falcon3-3B-Instruct-Heretic-GGUF: Same weights, converted