Xingchen

[习题15.5](https://datawhalechina.github.io/statistical-learning-method-solutions-manual/#/part02/chapter15/ch15?id=%e4%b9%a0%e9%a2%98155)中的图15.2链接挂了

### Describe the issue Issue: How to unfreeze the visual encoder when fine-tuning LLaVA?

[Usage] `resume_from_checkpoint` fails when finetuning in the lora settings

11

### Describe the issue I think the code is trying to resume_from_checkpoint like its a full-parameter fine-tunung checkpoint.

It seems to be having trouble "building".

Can we finetune LLaVA-HR with the scripts provided by the original LLaVA 1.5?

3

Great work! I wonder can we finetune your model with the scripts provided by the original LLaVA 1.5? Or Is there any guidance for conducting fine-tuning based on LLaVA-HR? Thx!