How to save the VQVAE's weight separately from the whole model?

[MingCongSu]

Hi, thanks for sharing the great work.👍 I am trying to reuse the motion tokenizer (VQVAE) in MotionGPT so I wonder.

1. Is there a way to save the VQVAE's weight as a checkpoint file separately from saving the whole MotionGPT model? Cuz I saw there is load_pretrained_vae() function here: https://github.com/OpenMotionLab/MotionGPT/blob/fac297260a0e7138ce04f8b41c2e7b24e1f09a9a/mGPT/utils/load_checkpoint.py#L17

2. I checked the pre-trained model motiongpt_s3_h3d.tar, and I found the checkpoint includes many parts (metrics, vae, lm, loss). Why does it contain so many parameters only for metrics?

It would be a big help if someone could reply, thanks🤗

[zRzRzRzRzRzRzR]

demo 已经升级到了 cogvlm2版本，您可以查看我们最新的demo尝试，模型已经有支持中文的版本