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

Fix typo in training (#5510)

Browse Source
This commit is contained in:
ELanning
2020-07-06 06:14:57 -07:00
committed by GitHub
parent 58cca47c16
commit 7ecff0ccbb
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/training.rst
View File

@@ -39,7 +39,7 @@ of the specified model are used to initialize the model. The
library also includes a number of task-specific final layers or 'heads' whose library also includes a number of task-specific final layers or 'heads' whose
weights are instantiated randomly when not present in the specified weights are instantiated randomly when not present in the specified
pre-trained model. For example, instantiating a model with pre-trained model. For example, instantiating a model with
``BertForSequenceClassification.from_pretrained('bert-base-uncased', num_classes=2)`` ``BertForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=2)``
will create a BERT model instance with encoder weights copied from the will create a BERT model instance with encoder weights copied from the
``bert-base-uncased`` model and a randomly initialized sequence ``bert-base-uncased`` model and a randomly initialized sequence
classification head on top of the encoder with an output size of 2. Models classification head on top of the encoder with an output size of 2. Models