Adding argument for freezing vision backbone.

[2U1]

Unfreezing the vision backbone while fine-tuning could be helpful for when finetuning according to the following tech report. https://arxiv.org/pdf/2403.06199

[GaiZhenbiao]

It would be better if freezing the vision backbone were the default option.

[2U1]

I thought it could be better for the adding --freeze_vision at the train.sh can be easier to see the option for users using this repo.

I've added the freeze_vision option at the train.sh

[GaiZhenbiao]

The lora modules are not added to the vision tower anyway though, unfreezing the vision tower will have no effect.

[2U1]

Will implement the settings a bit later, thanks