So then Gemma3 is not capable to do multimodal inference? or there is a different way to prompt the model? I am having the same issue and I am still figuring out how to solve it
Tommaso Tubaldo
tommiTub
AI & ML interests
None yet
Recent Activity
commented on
an
article
2 months ago
Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM
Organizations
None yet
tommiTub's activity
commented on
Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM
2 months ago