Multimodal model
#3
by
2Vasabi
- opened
Hello, it's a very cool model. It would be very nice if some multimodal model ( e.g. Qwen2-VL) could be trained as well.
Thank you! That's a great idea. We don't have an immediate plan to train a multi-modal model for function calling use cases. What scenario did you have in mind where that would be helpful?
cotran2
changed discussion status to
closed