lixiangchun

transcriptome-bert-1536-1-16-64

lixiangchun/transcriptome-bert-1536-1-16-64

transcriptome-bert-1536-1-16-64 is a fill-mask model from lixiangchun. Use it when you need the model to fill a missing word. It is set up for transformers.

Generative pretraining from the rankings of top expressing genes. It was trained on more than 20 million single-cell transcriptomes with a sequence length of 64.