coder3101/gemma-4-E4B-it-heretic
Abliterated vs google/gemma-4-E4B-it. Looks like abliteration (refusal removal): only the output projections (o_proj) changed, in 21 of 42 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: MLP 0/606, Norms 0/502, other 0/261, Attention 21/755, Embeddings 0/6
6 derivatives checked
- Abiray/gemma-4-E4B-it-heretic-GGUF: Quantization (fewer layers)
- mradermacher/gemma-4-E4B-it-heretic-i1-GGUF: Quantization (fewer layers)
- mradermacher/gemma-4-E4B-it-heretic-GGUF: Same weights, converted (fewer layers)
- JMingo/gemma-4-E4B-it-heretic-UD-GGUF: Same weights, converted (fewer layers)
- deucebucket/Gemma-4-E4B-it-Heretic-Cerebellum-GGUF: Quantization (fewer layers)
- MCult01/muse-gemma4e4b-heretic: Full fine-tune
1 other repos hold byte-for-byte identical weight files.