gabrielmtzcarrillo/deepcogito-cogito-v1-preview-llama-3B-heretic-gguf
Abliterated vs deepcogito/cogito-v1-preview-llama-3B. gabrielmtzcarrillo/deepcogito-cogito-v1-preview-llama-3B-heretic-gguf is a GGUF (F16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 23 of 28 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 7/84, Attention 23/112