RoBERTa: A Robustly Optimized BERT Pretraining Approach
Paper
•
1907.11692
•
Published
•
9
Project Organon
-
-
FacebookAI/xlm-roberta-large
Fill-Mask • 0.6B • Updated • 3.48M • • 476 -
google-bert/bert-base-uncased
Fill-Mask • 0.1B • Updated • 60.4M • • 2.5k -
FacebookAI/xlm-roberta-base
Fill-Mask • 0.3B • Updated • 7.07M • • 764 -
FacebookAI/roberta-base
Fill-Mask • 0.1B • Updated • 9.39M • • 534 -
FacebookAI/roberta-large
Fill-Mask • 0.4B • Updated • 15.2M • • 256 -
microsoft/deberta-v3-base
Fill-Mask • Updated • 1.95M • • 376