huihui-ai/QwQ-32B-abliterated
Abliterated vs Qwen/QwQ-32B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 63 of 64 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 63/192, Attention 63/448, lm_head 0/1
4 derivatives checked
- bartowski/huihui-ai_QwQ-32B-abliterated-GGUF: Quantization
- mradermacher/QwQ-32B-abliterated-i1-GGUF: Quantization
- DevQuasar-9/huihui-ai.QwQ-32B-abliterated-GGUF: Same weights, converted
- mradermacher/QwQ-32B-abliterated-GGUF: Quantization
2 other repos hold byte-for-byte identical weight files.