3MPER0RR/Qwen3-06B-3MPER0RR-abliterated
Abliterated vs huihui-ai/Huihui-Qwen3-0.6B-abliterated-v2. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 13 of 28 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 13/84, Attention 5/112
2 derivatives checked
- mradermacher/Qwen3-06B-3MPER0RR-abliterated-i1-GGUF: Quantization
- mradermacher/Qwen3-06B-3MPER0RR-abliterated-GGUF: Same weights, converted