This model is a fine-tuned version of
distilbert-base-uncased on a subset (800 samples as training and 200 samples as validation) of the This model is a fine-tuned version of
distilbert-base-uncased on a subset (800 samples as training and 200 samples as validation) of the
ComNum dataset. We just separated a numeral into digits as a reframing before tokenizing them. For example '1871' becomes '1 8 7 1'.
It achieves the following results on the evaluation subset:
