Hugging Face's logo

inference-net
/
ClipTagger-12b

Image-Text-to-Text
Safetensors
English
gemma3
VLM
video-understanding
image-captioning
gemma
json-mode
structured-output
video-analysis
conversational
Eval Results
compressed-tensors
Model card Files
xet
Community
2

Test code

#1
by nbsp - opened
Discussion
nbsp

Please provide test / inference code in python.

faisalhr1997

even smaller sized models like gemma 3 270m can perform similar for this kind of tasks if trained on similar dataset

Sign up or log in to comment