GGchen1997 comments

Results 6 comments of


                                            GGchen1997

The dataset for the classification task cannot be opened for viewing. Is the webpage lost? Can you send another copy

Same issue here.

The dataset for the classification task cannot be opened for viewing. Is the webpage lost? Can you send another copy

It seems we can directly download it without reviewing.

Reproduce experiments for table 4

Same request, here.

Scale of importance weight

Regarding this, is it reasonable to limit z to a range, if we want to use importance weight directly?

num-start and num-end

thanks for your reply. Is there a suggested special token for us to handle numbers specifically? Are and used in the pre-training? How are "role" tokens used in pre-training?

Structural tokenizer (`PdbQuantizer`) is too slow at processing long proteins

Still too slow on my side. Could you tell us how to use the new quantizer.py. I just use it as suggested: ``` from prosst.structure.quantizer import PdbQuantizer processor = PdbQuantizer(structure_vocab_size=2048)...