Yung-Sung Chuang

You need to be in the `DiffCSE` folder to run `from diffcse import DiffCSE`. If you want to import diffcse from anywhere, you can run `pip install .` in the...

Hi! I just changed the code in `diffcse/tool.py` by f724b2c to make it always use the [CLS] vector before the pooler. In the experiment that works better. By doing so,...

Hi all! After I tried some experiments on another machine, I found that the hyperparams are very sensitive to the device you use. I cannot reproduce the results on another...

@Huffon It works! Thank you!

Hi @JhonDan1999 The warning is caused by loading our DiffCSE model (encoder-decoder arch) into the RoBERTa model (encoder-only arch). So the decoder weights (in the names starting with`aux_bert.`) are not...

1. The original GPT2 model also have this problem. I have tried it. 2. GPT2 use byte pair encoding, it means that many of the Chinese words are still represented...

Hi @gante ! Thanks so much for your suggestions! I spent some time to add the code for test cases, and fixed the issues you mentioned. All the CI checks...

Hi @gante ! Thanks so much for your great suggestions! I have fixed all the issues you mentioned. Just let me know if you have any other concerns or suggestions!...

Hi @gante ! While waiting for the core maintainer's approval, I found that the validation of the parameter ranges in the generation config mainly happens in `tsrc/transformers/generation/configuration_utils.py` instead of `src/transformers/generation/utils.py`....

The failed test case was solved after syncing with the upstream! Please ignore my previous comment. It's ready to merge now!