SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Tensorflow doc changes on loss output size (#9922)

Browse Source 
* Change documentation to correctly specify loss tensor size

* Change documentation to correct input format for labels

* Corrected output size of loss tensor for sequence classifier, multiple choice model and question answering
This commit is contained in:
Jan Jitse Venselaar
2021-02-01 17:17:50 +01:00
committed by GitHub
parent 343057e141
commit d1b14c9b54
5 changed files with 14 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/transformers/models/blenderbot_small/modeling_tf_blenderbot_small.py
View File

@@ -1297,7 +1297,7 @@ class TFBlenderbotSmallForConditionalGeneration(TFBlenderbotSmallPreTrainedModel
**kwargs,
):
r"""
labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
labels (:obj:`tf.tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
Labels for computing the masked language modeling loss. Indices should either be in ``[0, ...,
config.vocab_size]`` or -100 (see ``input_ids`` docstring). Tokens with indices set to ``-100`` are ignored
(masked), the loss is only computed for the tokens with labels in ``[0, ..., config.vocab_size]``.