Gemma 4 12B It Uncensored Ara Refusals4

--- library_name: transformers license: apache-2.0 license_link: https://ai.google.dev/gemma/docs/gemma_4_license pipeline_tag: any-to-any base_model: - google/gemma-4-12B-it tags: - heretic - uncensored - decensored - abliterated - ara --- # This is a decensored version of [google/gemma-4-12B-it](https://huggingface.co/google/gemma-4-12B-it), made using [Heretic](https://github.com/p-e-w/heretic) v1.2.0 with the [Arbitrary-Rank Ablation (ARA)](https://github.com/p-e-w/heretic/pull/211) method (with row-norm preservation) ## Abliteration parameters | Parameter | Value | | :-------- | :---: | | **start_layer_index** | 24 | | **end_layer_index** | 37 | | **preserve_good_behavior_weight** | 0.1819 | | **steer_bad_behavior_weight** | 0.0001 | | **overcorrect_relative_weight** | 0.7372 | | **neighbor_count** | 13 | ## Performance | Metric | This model | Original model ([google/gemma-4-12B-it](https://huggingface.co/google/gemma-4-12B-it)) | | :----- | :--------: | :---------------------------: | | **KL divergence** | 0.0090 | 0 *(by definition)* | | **Refusals** | 4/100 | 91/100 | ----- <div align="center"> <img src=https://ai.google.dev/gemma/images/gemma4_banner.png> </div> <p align="center"> <a href="https://huggingface.co/collections/google/gemma-4" target="_blank">Hugging Face</a> | <a href="https://github.com/google-gemma" target="_blank">GitHub</a> | <a href="https://blog.google/innovation-and-ai/technology/developers-tools/introducing-gemma-4-12B/" target="_blank">Launch Blog</a> | <a href="https://ai.google.dev/gemma/docs/core" target="_blank">Documentation</a> <br> <b>License</b>: <a href="https://ai.google.dev/gemma/docs/gemma_4_license" target="_blank">Apache 2.0</a> | <b>Authors</b>: <a href="https://deepmind.google/models/gemma/" target="_blank">Google DeepMind</a> </p> > [!Note] > This model card is for the Gemma 4 12B Unified model, which is part of the Gemma 4 family of open models. Built with the same multimodal functionality as Gemma 4 E2B and E4B (text, audio, image, and video inputs), it brings native audio and vision understanding directly to local environments without the need for separate encoders. This unified approach to multimodality makes the model encoder-free, offering a deployment size that is perfect for consumer devices and streamlined local execution. Gemma is a family of open models built by Google DeepMind. G...