Release pretraining data?

[leannmlindsey]

I was just wondering if you have released the exact dataset that you used for pretraining DNABERT1 and DNABERT2?

I would be interested in doing some ablation studies using this dataset.

Thank you,
LeAnn

[YHX021014]

Hi~
May I ask if the data in ./examples/sample_data/pre provided by the repository is not the complete pretraining dataset?
If so, do you know which dataset DNABERT used? Did the author mention it in the paper?

Thank you!