llama3.2-vision projector_info vision encoder absence

### What is the issue? How can I definitively identify a model as vision-compatible without relying on keywords like "vision," "llava," or "-v" in its name? I used to rely on the projector_info.has_vision_encoder parameter, from API request POST http://localhost:11434/api/show (with correct body), but it's absent in llama3.2-vision. ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.4.0