huihui-ai/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated
Abliterated vs Qwen/Qwen3-30B-A3B-Instruct-2507. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 48 of 48 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/193, MLP 838/2613, Attention 48/192, lm_head 0/1
7 derivatives checked
- mradermacher/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated-GGUF: Quantization
- mradermacher/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated-i1-GGUF: Quantization
- YuYu1015/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated-NVFP4: Quantization
- Sowkwndms/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated-Q4_K_M-GGUF: Quantization
- nightmedia/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated-dwq4-mlx: Quantization
- blascotobasco/Jackdaw-30B-A3B: LoRA-style
- blascotobasco/Magnus-16B-A3B: LoRA-style (fewer layers)