ZENG, wenqi

Mask only support padding mask

2

I encounter an issue using crf layer when using a random mask, the loss becomes negative after several rounds. And I found this is due to the definition in https://github.com/kmkurn/pytorch-crf/blob/623e3402d00a2728e99d6e8486010d67c754267b/torchcrf/__init__.py#L203....