Downloads · 30 days
17
14% of all-time downloads
gemma-3-12b-it-MPOAdd-v1
grimjim/gemma-3-12b-it-MPOAdd-v1
gemma-3-12b-it-MPOAdd-v1 is a image-text-to-text model from grimjim. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as gemma.
This model was derived from google/gemma-3-12b-it, and represents Magnitude-Preserving Orthogonal Addition (MPOAdd).
All-time downloads
118
Public
Parameters
12.2B
24.4 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors24.4 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- gemma
- Model type
- gemma3
- Access
- Public
- Created
- Dec 18, 2025
- Updated
- Dec 18, 2025
- SHA
- 93e312c2
Try a prompt
Base models
Model card
From the Hugging Face model README
gemma-3-12b-it-MPOAdd-v1
This model was derived from google/gemma-3-12b-it, and represents Magnitude-Preserving Orthogonal Addition (MPOAdd).
Projected abliteration has been applied to neasuring refusal direction, along with a second round of removal of projected contribution onto the harmless direction of layer targeted for intervention. Additionally, instead of subtracting/ablating away the refusal direction in toto, the directional component of the refusal direction was added, or enhanced, while preserving the norms of the layers subjected to intervention. The model will now push back against perceived harms in an exaggerated manner, as refusal over safety concerns is more strongly enforced. More details of norm preservation can be found in the article on Norm-Preserving Biprojected Abliteration.
These geometric tweaks defy the conventional wisdom that (blunt) ablation or addition damages the reasoning of models. Perplexity loss has been minimal when measured on Q8_0 GGUFs compared to baseline.
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- gemma3
- License
- gemma
- Created
- Dec 18, 2025
- Updated
- Dec 18, 2025