ZySec-AI/gemma-3-27b-tools
Abliterated vs google/gemma-3-27b-it. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 62 of 62 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/4, Norms 0/484, MLP 62/294, Attention 62/464, other 0/1
2 derivatives checked
- mradermacher/gemma-3-27b-tools-i1-GGUF: Quantization (fewer layers)
- mradermacher/gemma-3-27b-tools-GGUF: Quantization (fewer layers)
4 other repos hold byte-for-byte identical weight files.