No module named 'llava.model.multimodal_encoder.siglip_encoder_cl'

[ZSXPROMAX]

First of all, thank you very much for your great work on LMM_CL!
I really appreciate the time and effort you put into making this project available to the community.

While trying to run the training script scripts/all_experiments/tune_parts/sa_proj_qkv.sh,
I encountered an error:

ModuleNotFoundError: No module named 'llava.model.multimodal_encoder.siglip_encoder_cl'

It seems that the file llava/model/multimodal_encoder/siglip_encoder_cl.py is missing from the repository.
Could you please confirm if this file was supposed to be included, or if I should obtain it from another source?

Thanks again for your contribution, and I look forward to your reply!

[shoshu454]

I also met the same issue. The apporaches I did is to put the " from .siglip_encoder_cl import ContinualSigLipVisionTower "from "/llava/model/multimodel_encoder/builder.py"
into the else branch that uses it, as this should not happen anyways.