Question About Hidden Space Tokenization Decoding

https://github.com/DAMO-NLP-SG/multilingual_analysis/blob/be2b161e7ef6e2b2c6659a3516c5a8843196a9f7/layers/test_layer.py#L44

I am trying to reproduce the token analysis of layers' hidden embedding. I have done the following:

1. Install according to requirements.txt
2. Replace the generation and models folder of transformers with the one in the repository

However, the output of the line is just the decoded token ids, no hidden_states (as normal generate).

May I ask is there any thing I am missing? Thank you very much.