wangzhang/Qwen3.6-27B-abliterated-v1
Abliterated vs Qwen/Qwen3.6-27B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj, out_proj) changed, in 58 of 64 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, MLP 20/192, Attention 58/448, lm_head 0/1, Norms 0/209
2 derivatives checked
- mradermacher/Qwen3.6-27B-abliterated-v1-i1-GGUF: Quantization
- mradermacher/Qwen3.6-27B-abliterated-v1-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.