[BUG] Regarding the bug with transformers

[Gaiejj]

Required prerequisites

• [X] I have read the documentation https://align-anything.readthedocs.io.
• [X] I have searched the Issue Tracker and Discussions that this hasn't already been reported. (+1 or comment there if it has.)
• [X] Consider asking first in a Discussion.

What version of align-anything are you using?

0.1.0-dev

System information

0.1.0-dev

Problem description

If you encounter issues with mismatched tensor shapes while running PPO training, try using version 4.41.2 of transformers.

pip install transformers==4.41.2