FeverAlbert is a classifier model that predicts if evidence is related to query claim. The model achieved F1 score of 88.33% with test dataset "mwong/fever-claim-related". Using pretrained albert-base-v2 model, the classifier head is trained on Fever dataset.
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Dataset used to train
mwong/albert-base-fever-claim-related
