ElementMerc/qwen3-0.6b-abliterated
Abliterated vs Qwen/Qwen3-0.6B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 23 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 14/84, Attention 15/112
2 derivatives checked
- mradermacher/qwen3-0.6b-abliterated-i1-GGUF: Quantization
- ElementMerc/qwen3-0.6b-abliterated-GGUF: Same weights, converted