Downloads · 30 days
16
14% of all-time downloads
gemma-4-31B-it-heretic
Sabomako/gemma-4-31B-it-heretic
gemma-4-31B-it-heretic is a image-text-to-text model from Sabomako. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product.
Refusal classification via an LLM judge (Gemma3-12B-it-Heretic).
All-time downloads
111
Public
Parameters
31.3B
62.6 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors62.5 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Model type
- gemma4
- Access
- Public
- Created
- Jun 8, 2026
- Updated
- Jun 28, 2026
- SHA
- fe873a11
Try a prompt
Base models
Model card
From the Hugging Face model README
This is a decensored version of google/gemma-4-31B-it, made using Heretic v1.3.0 with custom ORBA abliteration method
Refusal classification via an LLM judge (Gemma3-12B-it-Heretic).
Performance
| Metric | This model | Original model (google/gemma-4-31B-it) |
|---|---|---|
| KL divergence | 0.08095 | 0 (by definition) |
| Refusals | 2/100 | 98/100 |
- Task
- Image-Text-to-Text
- Type
- gemma4
- Created
- Jun 8, 2026
- Updated
- Jun 28, 2026