SpaceTimee/Suri-Qwen-3.8-27B-Uncensored
Abliterated vs Qwen/Qwen3.8-27B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj, out_proj) changed, in 56 of 64 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Norms 0/325, Attention 41/560, MLP 56/307, Embeddings 0/5, lm_head 0/1, other 0/1
5 derivatives checked
- SpaceTimee/Suri-Qwen-3.8-27B-Companion-GGUF: Quantization
- SpaceTimee/Suri-Qwen-3.8-27B-Uncensored-GGUF: Quantization
- mradermacher/Suri-Qwen-3.8-27B-Uncensored-i1-GGUF: Quantization
- mradermacher/Suri-Qwen-3.8-27B-Uncensored-GGUF: Quantization
- SpaceTimee/Suri-Qwen-3.8-27B-Uncensored-MLX: Quantization
1 other repos hold byte-for-byte identical weight files.