Open andreaferretti opened 7 months ago
In the Ollama CLI it is possible to use multimodal images (such as Llava) by issuing a request like
What's in this image? /Users/jmorgan/Desktop/smile.png
Apparently, this does not work in the Ollama GUI: the language model interprets the text as is, and does not load the content of the image
In the Ollama CLI it is possible to use multimodal images (such as Llava) by issuing a request like
Apparently, this does not work in the Ollama GUI: the language model interprets the text as is, and does not load the content of the image