AdapterHub
Explore
Upload
Docs
Blog
Explore
Task
Task Adapters
Pre-trained model:
All architectures
All architectures
bert
xlm-roberta
distilbert
roberta
Cosmos QA
Cosmos QA is a large-scale dataset of 35,600 problems that require commonsense-based reading comprehension, formulated as multiple-choice questions.
comsense/cosmosqa@ukp
roberta-base
1 version
Architecture: pfeiffer
Head:
Pfeiffer Adapter trained on Cosmos QA.
comsense/cosmosqa@ukp
bert-base-uncased
1 version
Architecture: pfeiffer
Head:
Pfeiffer Adapter trained on Cosmos QA.