🚨⚠️ I HAVE REACHED HUGGING FACE'S FREE STORAGE LIMIT ⚠️🚨 I can no longer upload new models unless I can cover the cost of additional storage. I host 70+ free models as an independent contributor and this work is unpaid. Without your support, no more new models can be uploaded. 🎉 Patreon (Monthly) ☕ Ko fi (One time) Every contribution goes directly toward Hugging Face storage fees to keep models free for everyone. gemma 3 12b it heretic GGUF GGUF quantizations of llmfan46/gemma 3 12b it ultra uncensored heretic. This is a decensored version of google/gemma 3 12b it, made using Heretic v1.2.0 with the Arbitrary Rank Ablation (ARA) method Abliteration parameters Parameter Value : : : start layer index 0 end layer index 41 preserve good behavior weight 0.8685 steer bad behavior weight 0.0013 overcorrect relative weight 0.9260 neighbor count 1 Performance Metric This model Original model (gemma 3 12b it) : : : : : KL divergence 0.0131 0 (by definition) Refusals 4/100 97/100 Lower refusals indicate fewer content restrictions, while lower KL divergence indicates better preservation of the original model's capabilities. Higher refusals cause more rejections, objections, pu…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy