This is a decensored version of google/gemma 4 31B it, made using Heretic v1.2.0 with the Arbitrary Rank Ablation (ARA) method (with row norm preservation) Abliteration parameters Parameter Value : : : start layer index 1 end layer index 59 preserve good behavior weight 0.8438 steer bad behavior weight 0.0002 overcorrect relative weight 1.0760 neighbor count 15 Performance Metric This model Original model (google/gemma 4 31B it) : : : : : KL divergence 0.0434 0 (by definition) Refusals 15/100 99/100 Hugging Face GitHub Launch Blog Documentation License : Apache 2.0 Authors : Google DeepMind Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on small models) and generating text output. This release includes open weights models in both pre trained and instruction tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages. Featuring both Dense and Mixture of Experts (MoE) architectures, Gemma 4 is well suited for tasks like text generation, coding, and reasoning. The models are available in four distinct sizes: E2B , E4B , 26B…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy