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

Fix doc errors and typos across the board (#8139)

Browse Source 
* Fix doc errors and typos across the board

* Fix a typo

* Fix the CI

* Fix more typos

* Fix CI

* More fixes

* Fix CI

* More fixes

* More fixes
This commit is contained in:
Santiago Castro
2020-10-29 10:33:33 -04:00
committed by GitHub
parent 4731a00c3e
commit 969859d5f6
160 changed files with 342 additions and 364 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/seq2seq/bertabs/configuration_bertabs.py
View File

@@ -44,7 +44,7 @@ class BertAbsConfig(PretrainedConfig):
enc_ff_size: int
The size of the encoder's feed-forward layers.
enc_dropout: int
The dropout probabilitiy for all fully connected layers in the
The dropout probability for all fully connected layers in the
embeddings, layers, pooler and also the attention probabilities in
the encoder.
dec_layer: int
@@ -56,7 +56,7 @@ class BertAbsConfig(PretrainedConfig):
dec_ff_size: int
The size of the decoder's feed-forward layers.
dec_dropout: int
The dropout probabilitiy for all fully connected layers in the
The dropout probability for all fully connected layers in the
embeddings, layers, pooler and also the attention probabilities in
the decoder.
"""

6
examples/seq2seq/bertabs/modeling_bertabs.py
View File

@@ -152,7 +152,7 @@ class TransformerDecoder(nn.Module):
dropout (float): dropout parameters
embeddings (:obj:`onmt.modules.Embeddings`):
embeddings to use, should have positional encodings
attn_type (str): if using a seperate copy attention
attn_type (str): if using a separate copy attention
"""
def __init__(self, num_layers, d_model, heads, d_ff, dropout, embeddings, vocab_size):
@@ -817,11 +817,7 @@ class Translator(object):
Args:
batch (:obj:`Batch`): a batch from a dataset object
data (:obj:`Dataset`): the dataset object
fast (bool): enables fast beam search (may not support all features)
Todo:
Shouldn't need the original dataset.
"""
with torch.no_grad():
return self._fast_translate_batch(batch, self.max_length, min_length=self.min_length)