Original DistilBERT model, checkpoints obtained from using teacher-student learning from the original BERT checkpoints.
-
distilbert/distilbert-base-cased
Fill-Mask • Updated • 798k • 31 -
distilbert/distilbert-base-uncased
Fill-Mask • Updated • 11.2M • • 523 -
distilbert/distilbert-base-multilingual-cased
Fill-Mask • Updated • 543k • 137 -
distilbert/distilbert-base-uncased-finetuned-sst-2-english
Text Classification • Updated • 6.29M • • 581