Original DistilBERT model, checkpoints obtained from using teacher-student learning from the original BERT checkpoints.
-
distilbert/distilbert-base-cased
Fill-Mask • Updated • 387k • 34 -
distilbert/distilbert-base-uncased
Fill-Mask • Updated • 15.4M • 568 -
distilbert/distilbert-base-multilingual-cased
Fill-Mask • Updated • 495k • 145 -
distilbert/distilbert-base-uncased-finetuned-sst-2-english
Text Classification • Updated • 9.78M • 635