Hugging Face's logo

google
/
shieldgemma-2-4b-it

Image-Text-to-Text
Transformers
Safetensors
shieldgemma2
image-classification
conversational
Model card Files Community
5

Model Fintune

#3
by BITDDD - opened
Discussion
BITDDD

Does the model support extending its own tags and training based on its own images?

merve
 Google org

@BITDDD you can probably fine-tune it on different images and policies like how you would fine-tune a vision language model.

kumanatsu

Use Unsloth for gemma3 and vor visual fine tuning is working great.

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment