---
base_model: Gryphe/Gemma-4-31B-StyleTune
tags:
- text-generation-inference
- transformers
- unsloth
- gemma4
- roleplay
- creative-writing
- style-tune
- heretic
- uncensored
- decensored
- abliterated
- ara
license: apache-2.0
language:
- en
---

# This is a decensored version of [Gryphe/Gemma-4-31B-StyleTune](https://huggingface.co/Gryphe/Gemma-4-31B-StyleTune), 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** | 30 |
| **end_layer_index** | 48 |
| **preserve_good_behavior_weight** | 0.8437 |
| **steer_bad_behavior_weight** | 0.0025 |
| **overcorrect_relative_weight** | 0.9644 |
| **neighbor_count** | 15 |

## Performance

| Metric | This model | Original model ([Gryphe/Gemma-4-31B-StyleTune](https://huggingface.co/Gryphe/Gemma-4-31B-StyleTune)) |
| :----- | :--------: | :---------------------------: |
| **KL divergence** | 0.0733 | 0 *(by definition)* |
| **Refusals** | 8/100 | 99/100 |

-----

# Uploaded finetuned  model

- **Developed by:** densenet
- **License:** apache-2.0
- **Finetuned from model :** Gryphe/Gemma-4-31B-StyleTune

This gemma4 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)