[BUG] <title>RuntimeError: Function torch::autograd::CopySlices returned an invalid gradient at index 1 - got [64, 2304] but expected shape compatible with [192, 2304]

[whoam-challenge]

是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?

• [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions

该问题是否在FAQ中有解答？ | Is there an existing answer for this in FAQ?

• [X] 我已经搜索过FAQ | I have searched FAQ

当前行为 | Current Behavior

No response

期望行为 | Expected Behavior

No response

复现方法 | Steps To Reproduce

No response

运行环境 | Environment

- OS:
- Python:3.10
- Transformers:4.36.0
- PyTorch:
- CUDA (`python -c 'import torch; print(torch.version.cuda)'`):

备注 | Anything else?

Does anyone meet this problem when finetuning the MiniCPM-V-2?