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

Fixed the sample code in the title 'Quick tour'.

Browse Source
This commit is contained in:
Emrah Budur
2019-10-12 14:17:17 +03:00
parent a701c9b321
commit 5a8c6e771a
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
README.md
View File

@@ -176,10 +176,11 @@ BERT_MODEL_CLASSES = [BertModel, BertForPreTraining, BertForMaskedLM, BertForNex
# All the classes for an architecture can be initiated from pretrained weights for this architecture # All the classes for an architecture can be initiated from pretrained weights for this architecture
# Note that additional weights added for fine-tuning are only initialized # Note that additional weights added for fine-tuning are only initialized
# and need to be trained on the down-stream task # and need to be trained on the down-stream task
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased') pretrained_weights = 'bert-base-uncased'
tokenizer = BertTokenizer.from_pretrained(pretrained_weights)
for model_class in BERT_MODEL_CLASSES: for model_class in BERT_MODEL_CLASSES:
# Load pretrained model/tokenizer # Load pretrained model/tokenizer
model = model_class.from_pretrained('bert-base-uncased') model = model_class.from_pretrained(pretrained_weights)
# Models can return full list of hidden-states & attentions weights at each layer # Models can return full list of hidden-states & attentions weights at each layer
model = model_class.from_pretrained(pretrained_weights, model = model_class.from_pretrained(pretrained_weights,