Astark-40/Huihui-Qwen3.8-27B-abliterated-GGUF
Abliterated vs Qwen/Qwen3.8-27B. Astark-40/Huihui-Qwen3.8-27B-abliterated-GGUF is a GGUF (BF16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 49 of 64 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Norms 0/161, MLP 49/192, Attention 13/64, Embeddings 0/1, lm_head 0/1