prithivMLmods/Qwen3.6-27B-Uncensored-Aggressive
Abliterated vs Qwen/Qwen3.6-27B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj, out_proj) changed, in 64 of 64 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/4, MLP 64/304, Attention 64/556, lm_head 0/1, Norms 0/319
3 derivatives checked
- mradermacher/Qwen3.6-27B-Uncensored-Aggressive-i1-GGUF: Quantization
- mradermacher/Qwen3.6-27B-Uncensored-Aggressive-GGUF: Quantization
- prithivMLmods/Qwen3.6-27B-Uncensored-Aggressive-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.