llmfan46/gemma-4-E4B-it-uncensored-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
4 derivatives checked
- llmfan46/gemma-4-E4B-it-uncensored-heretic-GGUF: Same weights, converted (fewer layers)
- mradermacher/gemma-4-E4B-it-uncensored-heretic-GGUF: Same weights, converted (fewer layers)
- mradermacher/gemma-4-E4B-it-uncensored-heretic-i1-GGUF: Quantization (fewer layers)
- JMingo/gemma-4-E4B-it-uncensored-heretic-UD-GGUF: Same weights, converted (fewer layers)
7 other repos hold byte-for-byte identical weight files.