How to train a multimodal model with LMFlow?

Hi, thank you for your contributions. I'm considering aligning multimodal models with LMFlow. However, I only found run_finetune_multi_modal_stage1.sh related to multimodal in the GitHub repository, and didn't find multimodal training scripts for other stages. So I'd like to ask if there is a complete open-source process for training multimodal models now?