Original DistilBERT model, checkpoints obtained from using teacher-student learning from the original BERT checkpoints.
-
distilbert/distilbert-base-cased
Fill-Mask • Updated • 724k • 33 -
distilbert/distilbert-base-uncased
Fill-Mask • Updated • 13.3M • • 552 -
distilbert/distilbert-base-multilingual-cased
Fill-Mask • Updated • 453k • 142 -
distilbert/distilbert-base-uncased-finetuned-sst-2-english
Text Classification • Updated • 6.67M • • 611