prithivMLmods/Qwen3.8-27B-abliterated-GGUF
Abliterated vs huihui-ai/Huihui-Qwen3.8-27B-abliterated. prithivMLmods/Qwen3.8-27B-abliterated-GGUF is a GGUF (F16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 14 of 64 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Norms 0/161, MLP 14/192, Attention 4/64, Embeddings 0/1, lm_head 0/1