SUN, Pengzhan

Results 2 issues of SUN, Pengzhan

Dear Authors, Thanks for making this solid work publicly available. I am trying to integrate this method into [this popular codebase (HRNet)](https://github.com/leoxiaobin/deep-high-resolution-net.pytorch) but encountered with gradient vanishing or explosion problems...

I am using Llama-factory to do a Qwen2-VL-7b_Instruction lora fine-tuning with Refcoco/+/g datasets. However the performance drops dramatically, from about 90% to almost zero. I already checked [this link](https://github.com/huggingface/transformers/pull/33487/files) to...