How to train VLM model like Qwen2.5 VL? #19
Description
I would like to learn how to train a VLM such as Qwen2.5-VL, including how to prepare multimodal data (text + image).
{{ message }}
I would like to learn how to train a VLM such as Qwen2.5-VL, including how to prepare multimodal data (text + image).