Model weights for a study of commonsense reasoning

This resource contains model weights for five Transformer-based models: RoBERTa, GPT-2, T5, BART and COMET(BART).
These models were implemented using HuggingFace, and fine-tuned on the following four commonsense reasoning tasks: Argument Reasoning Comprehension Task (ARCT), AI2 Reasoning Challenge (ARC), Physical Interaction Question Answering (PIQA) and CommonsenseQA (CSQA).


  • Language Description
  • text

People who looked at this resource also viewed the following: