💎 Gemma 3 27B IT Abliterated Gemma 3 4B Abliterated • Gemma 3 12B Abliterated This is an uncensored version of google/gemma 3 27b it created with a new abliteration technique. See this article to know more about abliteration. I was playing with model weights and noticed that Gemma 3 was much more resilient to abliteration than other models like Qwen 2.5. I experimented with a few recipes to remove refusals while preserving most of the model capabilities. Note that this is fairly experimental, so it might not turn out as well as expected. I recommend using these generation parameters: temperature=1.0 , top k=64 , top p=0.95 . ✂️ Layerwise abliteration In the original technique, a refusal direction is computed by comparing the residual streams between target (harmful) and baseline (harmless) samples. Here, the model was abliterated by computing a refusal direction based on hidden states (inspired by Sumandora's repo) for each layer, independently. This is combined with a refusal weight of 1.5 to upscale the importance of this refusal direction in each layer. This created a very high acceptance rate ( 90%) and still produced coherent outputs. Thanks to @bartowski for the mmproj file!
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy