mmproj file for the Model
This Model is multimodal. It is tagged as "video-text-to-text" But i can't find the mmproj file
No we did not. I think the reason for this is because there is not yet any llama.cpp vision support for Gemma3nForConditionalGeneration.
Exactly I remembered correctly. https://github.com/ggml-org/llama.cpp/pull/14400 (model : gemma3n text-only) added text-only support for gemma3n. There was not yet any follow up PR to add vision support for gemma3n to llama.cpp as far I'm aware. Because of this it is correct that we don't yet flag Gemma3nForConditionalGeneration as vision model. We will add the mmproj file for all ouer Gemma3nForConditionalGeneration models as soon llama.cpp adds support for it. Please remind us in case we forget.
Okay good to know Thanks