This is a distilled BERTScore model. Please read this post for details.
from bert_score import BERTScorer
texts1 = ['This is a text.']
texts2 = ['This is another text.']
scorer = BERTScorer(model_type='yongsun-yoon/minilmv2-bertscore-distilled', num_layers=6)
P, R, F = scorer.score(texts1, texts2)