Original DistilBERT model, checkpoints obtained from using teacher-student learning from the original BERT checkpoints.
-
distilbert/distilbert-base-cased
Fill-Mask • Updated • 521k • 30 -
distilbert/distilbert-base-uncased
Fill-Mask • Updated • 15.2M • 474 -
distilbert/distilbert-base-multilingual-cased
Fill-Mask • Updated • 1.05M • 133 -
distilbert/distilbert-base-uncased-finetuned-sst-2-english
Text Classification • Updated • 7.35M • 526