Open Otsutsukii opened 4 weeks ago
Hello, would it be possible to also release the pretraining dataset ( used for TSmixup), and maybe a mention of a successful training recipe.
I would like to try to pretrain from scratch as well, and also extending the vocabulary size wayyyyy more, and with a custom dataset.
@Otsutsukii Thanks for your interest. We are working on releasing the individual datasets and TSMixup script. I will let you know here once we have an update.
Hello, would it be possible to also release the pretraining dataset ( used for TSmixup), and maybe a mention of a successful training recipe.
I would like to try to pretrain from scratch as well, and also extending the vocabulary size wayyyyy more, and with a custom dataset.