Any-to-Any
Transformers
Safetensors
gemma4
image-text-to-text
heretic
uncensored
decensored
abliterated
ara
Instructions to use MoonRide/gemma-4-E2B-it-heretic-ara-custom with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MoonRide/gemma-4-E2B-it-heretic-ara-custom with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("MoonRide/gemma-4-E2B-it-heretic-ara-custom") model = AutoModelForMultimodalLM.from_pretrained("MoonRide/gemma-4-E2B-it-heretic-ara-custom") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,7 @@ base_model:
|
|
| 13 |
- google/gemma-4-E2B-it
|
| 14 |
---
|
| 15 |
# This is a decensored version of [google/gemma-4-E2B-it](https://huggingface.co/google/gemma-4-E2B-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)
|
|
|
|
| 16 |
|
| 17 |
## Abliteration parameters
|
| 18 |
|
|
|
|
| 13 |
- google/gemma-4-E2B-it
|
| 14 |
---
|
| 15 |
# This is a decensored version of [google/gemma-4-E2B-it](https://huggingface.co/google/gemma-4-E2B-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)
|
| 16 |
+
# Created and evaluated using custom system prompt.
|
| 17 |
|
| 18 |
## Abliteration parameters
|
| 19 |
|