Jiunsong/SuperQwen3.8-27b-abliterated
Abliterated vs Qwen/Qwen3.8-27B. Looks like abliteration (refusal removal): only the output projections (down_proj, embed_tokens, o_proj, out_proj) changed, in 49 of 64 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Norms 0/325, Attention 49/560, MLP 49/307, Embeddings 1/5, lm_head 1/1, other 0/1
5 derivatives checked
- Jiunsong/SuperQwen3.8-27b-abliterated-GGUF: Quantization
- mradermacher/SuperQwen3.8-27b-abliterated-GGUF: Full fine-tune
- mradermacher/SuperQwen3.8-27b-abliterated-i1-GGUF: Full fine-tune
- Jiunsong/SuperQwen3.8-27b-abliterated-MLX-4bit: Quantization
- PIXELZX/XION0.2-27B: Full fine-tune
1 other repos hold byte-for-byte identical weight files.