To use the model, add the following from the transformers package:

(1) Tokenizer:

tokenizer = AutoTokenizer.from_pretrained("yikuan8/Clinical-BigBird")

(2) Model type:

#N in [0,1,2,3]

num_classes = 4

model = BigBirdForSequenceClassification.from_pretrained(directory, num_labels=num_classes)