InfinimindCreations/gemma-4-E4B-it-uncensored
Abliterated vs google/gemma-4-E4B-it. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 42 of 42 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: MLP 42/606, Norms 0/502, other 0/261, Attention 42/755, Embeddings 0/6
4 derivatives checked
- mradermacher/gemma-4-E4B-it-uncensored-GGUF: Same weights, converted (fewer layers)
- InfinimindCreations/gemma-4-E4B-it-uncensored-vision: Quantization (fewer layers)
- mradermacher/gemma-4-E4B-it-uncensored-i1-GGUF: Quantization (fewer layers)
- Handyfff/Gemma-4-E4B-it-uncensored-pruned-TextOnly-EnglishOnly-GGUF: Same weights, converted (fewer layers)