Original DistilBERT model, checkpoints obtained from using teacher-student learning from the original BERT checkpoints.
-
distilbert/distilbert-base-cased
Fill-Mask • Updated • 531k • 29 -
distilbert/distilbert-base-uncased
Fill-Mask • Updated • 16.9M • 414 -
distilbert/distilbert-base-multilingual-cased
Fill-Mask • Updated • 4.48M • 112 -
distilbert/distilbert-base-uncased-finetuned-sst-2-english
Text Classification • Updated • 8.46M • 458