Merge pull request #145 from wlhgtc/master

Correct the  wrong note
This commit is contained in:
Thomas Wolf
2019-01-07 12:23:05 +01:00
committed by GitHub

View File

@@ -730,7 +730,7 @@ class BertForMaskedLM(PreTrainedBertModel):
is only computed for the labels set in [0, ..., vocab_size]
Outputs:
if `masked_lm_labels` is `None`:
if `masked_lm_labels` is not `None`:
Outputs the masked language modeling loss.
if `masked_lm_labels` is `None`:
Outputs the masked language modeling logits of shape [batch_size, sequence_length, vocab_size].