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

adding missing docstring fix #793

Browse Source
This commit is contained in:
thomwolf
2019-07-16 21:35:53 +02:00
parent e848b54730
commit 5fe0b378d8
1 changed files with 8 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
pytorch_transformers/modeling_bert.py
View File

@@ -625,7 +625,14 @@ class BertModel(BertPreTrainedModel):
r"""
Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs:
**last_hidden_state**: ``torch.FloatTensor`` of shape ``(batch_size, sequence_length, hidden_size)``
Sequence of hidden-states at the last layer of the model.
Sequence of hidden-states at the output of the last layer of the model.
**pooler_output**: ``torch.FloatTensor`` of shape ``(batch_size, hidden_size)``
Last layer hidden-state of the first token of the sequence (classification token)
further processed by a Linear layer and a Tanh activation function. The Linear
layer weights are trained from the next sentence prediction (classification)
objective during Bert pretraining. This output is usually *not* a good summary
of the semantic content of the input, you're often better with averaging or pooling
the sequence of hidden-states for the whole input sequence.
**hidden_states**: (`optional`, returned when ``config.output_hidden_states=True``)
list of ``torch.FloatTensor`` (one for the output of each layer + the output of the embeddings)
of shape ``(batch_size, sequence_length, hidden_size)``: