Original DistilBERT model, checkpoints obtained from using teacher-student learning from the original BERT checkpoints.
-
distilbert/distilbert-base-cased
Fill-Mask • Updated • 569k • 29 -
distilbert/distilbert-base-uncased
Fill-Mask • Updated • 16.7M • 408 -
distilbert/distilbert-base-multilingual-cased
Fill-Mask • Updated • 5.49M • 107 -
distilbert/distilbert-base-uncased-finetuned-sst-2-english
Text Classification • Updated • 8.69M • 454