HFCK99/Qwen3.8-27B-Uncensored-Cyber
Abliterated vs philbert440/Qwen3.8-27B-Uncensored-Aggressive. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj, out_proj) changed, in 60 of 64 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: lm_head 0/1, Embeddings 0/5, Norms 0/325, Attention 60/560, MLP 60/307, other 0/1
2 derivatives checked
- mradermacher/Qwen3.8-27B-Uncensored-Cyber-i1-GGUF: Quantization
- mradermacher/Qwen3.8-27B-Uncensored-Cyber-GGUF: Quantization