TrevorJS/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
5 derivatives checked
- TrevorJS/gemma-4-E4B-it-uncensored-GGUF: Quantization (fewer layers)
- WeilPesi/gemma-4-E4B-it-uncensored-GGUF: Quantization (fewer layers)
- lowlevelgoblin/gemma-4-E4B-it-uncensored-Q4_K_M-GGUF: Quantization (fewer layers)
- senjiangchen/gemma-4-E4B-it-uncensored-GGUF: Quantization (fewer layers)
- adoringmc/squid-merged-heretic: LoRA-style
5 other repos hold byte-for-byte identical weight files.