Unrestricted/Qwen3-4B-2507-Instruct-Uncensored-HauhauCS-Aggressive
Abliterated vs Qwen/Qwen3-4B-Instruct-2507. Unrestricted/Qwen3-4B-2507-Instruct-Uncensored-HauhauCS-Aggressive is a GGUF (FP16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 29 of 36 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 21/108, Attention 29/144