ClaudioItaly/Fimbulvetr-Cognitive-11B-V3
Abliterated vs Sao10K/Fimbulvetr-11B-v2. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 43 of 47 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/95, MLP 43/141, Attention 43/188, lm_head 0/1
2 derivatives checked
- mradermacher/Fimbulvetr-Cognitive-11B-V3-i1-GGUF: Quantization
- mradermacher/Fimbulvetr-Cognitive-11B-V3-GGUF: Same weights, converted