Downloads · 30 days
23
1% of all-time downloads
gemma3-siglip448
stribomon/gemma3-siglip448
gemma3-siglip448 is a image-text-to-text model from stribomon. 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.
Gemma3 4B with 448x448 SigLIP Vision Tower for edge deployment.
All-time downloads
2.1K
Public
Parameters
4.3B
17.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.6 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- Model type
- gemma3
- Access
- Public
- Created
- Jun 9, 2025
- Updated
- Nov 13, 2025
- SHA
- 02ccf2a6
Try a prompt
Base models
Model card
From the Hugging Face model README
Model Card for Gemma3 4b with 448x448 SigLIP Image Encoder
Gemma3 4B with 448x448 SigLIP Vision Tower for edge deployment.
Model Details
This model is based on google/gemma-3-4b-it, whereas the 896x896 SigLIP in the original Gemma3 architecture is replaced with a 448x448 SigLIP model as it can be found in Efficient-Large-Model/paligemma-siglip-so400m-patch14-448. To fit the 256 image tokens, the average pooling layer at the output of the vision tower is adjusted for the 448x448 SigLIP model which has a smaller output embedding (1024 instead of 4096 patches in the 896x896 version). Details about the implementation can be found in the original Gemma3 Technical Report (Chapter 5.5. Vision encoder) [https://arxiv.org/pdf/2503.19786].
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- gemma3
- Created
- Jun 9, 2025
- Updated
- Nov 13, 2025