prithivMLmods/gemma-4-E2B-it-Uncensored-MAX
Abliterated vs google/gemma-4-E2B-it. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 25 of 35 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: MLP 25/585, Norms 0/453, other 0/240, Attention 25/727, Embeddings 0/6
4 derivatives checked
- mradermacher/gemma-4-E2B-it-Uncensored-MAX-i1-GGUF: Quantization (fewer layers)
- prithivMLmods/gemma-4-E2B-it-Uncensored-MAX-GGUF: Same weights, converted (fewer layers)
- mradermacher/gemma-4-E2B-it-Uncensored-MAX-GGUF: Same weights, converted (fewer layers)
- ShadowOkami/gemma-4-E2B-it-Uncensored-MAX-Q4_K_M-GGUF: Quantization (fewer layers)
1 other repos hold byte-for-byte identical weight files.