I can not see any setup related to freeze the EVA backbone. And also i check the code in details, but still can not find any code related to freeze the visual encoder. Anyone help me, thank you.
by the way, i found the freeze_backbone parameters. However, it will freeze both the EVA and LLM as model.model.requires_grad_(False).
Dear all: The paper say it will freeze the visual encoder only when training on stage2. However, from the training script here:
I can not see any setup related to freeze the EVA backbone. And also i check the code in details, but still can not find any code related to
freeze the visual encoder
. Anyone help me, thank you.by the way, i found the freeze_backbone parameters. However, it will freeze both the EVA and LLM as
model.model.requires_grad_(False)
.