Ewere/Qwen3-30B-A3B-abliterated-erotic
Abliterated vs Qwen/Qwen3-30B-A3B. Looks like abliteration (refusal removal): only the output projections (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 0/2613, Attention 48/192, lm_head 0/1
6 derivatives checked
- mradermacher/Qwen3-30B-A3B-abliterated-erotic-i1-GGUF: Quantization
- mradermacher/Qwen3-30B-A3B-abliterated-erotic-GGUF: Quantization
- day078/Qwen3-30B-A3B-abliterated-erotic-Q4_K_M-GGUF: Quantization
- IDKHowItWorks/Qwen3-30B-A3B-abliterated-erotic-GGUF: Same weights, converted
- Anachronox39/Qwen3-30B-A3B-abliterated-erotic-i1-GGUF: Quantization
- rodrigomt/Qwen3-30B-A3B-Thinking-2507-Amoral-Edition: Full fine-tune
2 other repos hold byte-for-byte identical weight files.