Another problem that may be related, is that it is not possible to send other images during the conversation, when I try to send the message “failed to send message” appears and in the chat “This message contains no content. The AI has nothing to say.”
I don't think it makes a difference in this case, but I'm using LMStudio on linux (ubuntu 23).
I found a problem with llava models, I noticed that the first prompt is always ignored when I send an image in the initial prompt:
Expected result (official llava repository):
When I continue the conversation it works:
Doing some research on the subject, I found this issue from ollama (https://github.com/ollama/ollama/issues/2769), and it seems to be the same problem.
Another problem that may be related, is that it is not possible to send other images during the conversation, when I try to send the message “failed to send message” appears and in the chat “This message contains no content. The AI has nothing to say.”
I don't think it makes a difference in this case, but I'm using LMStudio on linux (ubuntu 23).