Any-to-Any
Transformers
Safetensors
gemma4_unified
image-text-to-text
heretic
uncensored
decensored
abliterated
Instructions to use MuXodious/gemma-4-12B-it-QAT-SOMPOA-heresy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MuXodious/gemma-4-12B-it-QAT-SOMPOA-heresy with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("MuXodious/gemma-4-12B-it-QAT-SOMPOA-heresy") model = AutoModelForMultimodalLM.from_pretrained("MuXodious/gemma-4-12B-it-QAT-SOMPOA-heresy", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,8 @@ tags:
|
|
| 13 |
---
|
| 14 |
This is a **gemma-4-12B-it-qat-q4_0-unquantized** fine-tune, produced through P-E-W's [Heretic](https://github.com/p-e-w/heretic) (v1.4.0) abliteration engine with [Self-Organizing Maps & Magnitude-Preserving Orthogonal Ablation](https://github.com/p-e-w/heretic/pull/196) enabled.
|
| 15 |
|
|
|
|
|
|
|
| 16 |
---
|
| 17 |
<img src="https://img.shields.io/badge/RENEGADE_CHAPTER-SOMPOA-FCC900?style=flat-square&labelColor=101010" align="right" width="300">
|
| 18 |
|
|
|
|
| 13 |
---
|
| 14 |
This is a **gemma-4-12B-it-qat-q4_0-unquantized** fine-tune, produced through P-E-W's [Heretic](https://github.com/p-e-w/heretic) (v1.4.0) abliteration engine with [Self-Organizing Maps & Magnitude-Preserving Orthogonal Ablation](https://github.com/p-e-w/heretic/pull/196) enabled.
|
| 15 |
|
| 16 |
+
**Note:** I used a different dataset for hereticating this model; feedback is welcome.
|
| 17 |
+
|
| 18 |
---
|
| 19 |
<img src="https://img.shields.io/badge/RENEGADE_CHAPTER-SOMPOA-FCC900?style=flat-square&labelColor=101010" align="right" width="300">
|
| 20 |
|