prithivMLmods/gemma-4-E4B-it-Uncensored-MAX
Abliterated vs google/gemma-4-E4B-it. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 35 of 42 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: MLP 35/606, Norms 0/502, other 0/261, Attention 35/755, Embeddings 0/6
4 derivatives checked
- prithivMLmods/gemma-4-E4B-it-Uncensored-MAX-GGUF: Same weights, converted (fewer layers)
- mradermacher/gemma-4-E4B-it-Uncensored-MAX-i1-GGUF: Quantization (fewer layers)
- mradermacher/gemma-4-E4B-it-Uncensored-MAX-GGUF: Same weights, converted (fewer layers)
- Hyphonical/gemma-4-E4B-it-Uncensored-MAX-opus-4.7: LoRA-style