Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
hi-wesley
/
gemma3-vision-encoder
like
1
Image Feature Extraction
Transformers
Safetensors
siglip_vision_model
siglip
License:
gemma
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
gemma3-vision-encoder
840 MB
1 contributor
History:
1 commit
Wesley
Initial upload of Gemma3 SigLIP vision encoder (code + weights)
bfd1987
6 months ago
.gitattributes
91 Bytes
Initial upload of Gemma3 SigLIP vision encoder (code + weights)
6 months ago
NOTICE
104 Bytes
Initial upload of Gemma3 SigLIP vision encoder (code + weights)
6 months ago
README.md
3.08 kB
Initial upload of Gemma3 SigLIP vision encoder (code + weights)
6 months ago
config.json
446 Bytes
Initial upload of Gemma3 SigLIP vision encoder (code + weights)
6 months ago
model.safetensors
834 MB
xet
Initial upload of Gemma3 SigLIP vision encoder (code + weights)
6 months ago
preprocessor_config.json
570 Bytes
Initial upload of Gemma3 SigLIP vision encoder (code + weights)
6 months ago
projector_config.json
180 Bytes
Initial upload of Gemma3 SigLIP vision encoder (code + weights)
6 months ago
projector_state_dict.pt
5.9 MB
xet
Initial upload of Gemma3 SigLIP vision encoder (code + weights)
6 months ago
