silvermoon1573/moon-27B-03
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 64 of 64 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Norms 0/325, Attention 65/560, MLP 65/307, Embeddings 1/5, lm_head 0/1, other 0/1
2 derivatives checked
- mradermacher/dreamaiai-27B-03-i1-GGUF: Quantization
- mradermacher/dreamaiai-27B-03-GGUF: Quantization
2 other repos hold byte-for-byte identical weight files.