license: mit | |
BarcodeBERT (https://arxiv.org/pdf/2311.02401) model trained on all complete DNA sequences from the latest BOLD database (http://www.boldsystems.org/index.php/datapackages/Latest) release. We used the 'nucraw' column of DNA sequences and followed the preprocessing steps outlined by the BarcodeBERT approach. | |
The loss curve is shown: | |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6659d7d2f5106a7f0abeaa3d/6Ypq8hLPW3ssOToGcYHDn.png) | |