MAGICS-LAB / DNABERT_2

[ICLR 2024] DNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genome
Apache License 2.0
212 stars 49 forks source link

GUE+ datasets? #87

Closed leannmlindsey closed 1 month ago

leannmlindsey commented 1 month ago

I do not see that you have made the GUE+ datasets available at the link for the GUE.zip download. Are they available in another location?

Zhihan1996 commented 1 month ago

Sorry for the late reply!

Please see this link for the updated dataset.

I have updated the README accordingly. Thanks for indicating this.

fma231 commented 1 month ago

could you also please provide the hyperparameter details used for their finetuning? I could reproduce the results on GUE but not GUE+, with hyperparameters used in the paper