knoveleng/gemma-2-2b-it-uncensored
Abliterated vs google/gemma-2-2b-it. Looks like abliteration (refusal removal): only the output projections (down_proj, embed_tokens, o_proj) changed, in 26 of 26 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 1/1, Norms 0/105, MLP 26/78, Attention 26/104
2 derivatives checked
- mradermacher/gemma-2-2b-it-uncensored-i1-GGUF: Quantization
- mradermacher/gemma-2-2b-it-uncensored-GGUF: Same weights, converted