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

Merge pull request #1492 from stefan-it/bert-german-dbmdz-models

Browse Source 
Add new BERT models for German (cased and uncased)
This commit is contained in:
Thomas Wolf
2019-10-11 13:01:52 +02:00
committed by GitHub
parent 573dde9b44 5f25a5f367
commit 700331b5ec
5 changed files with 20 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
transformers/configuration_bert.py
View File

@@ -40,6 +40,8 @@ BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
'bert-large-uncased-whole-word-masking-finetuned-squad': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-finetuned-squad-config.json",
'bert-large-cased-whole-word-masking-finetuned-squad': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-whole-word-masking-finetuned-squad-config.json",
'bert-base-cased-finetuned-mrpc': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-finetuned-mrpc-config.json",
'bert-base-german-dbmdz-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-cased-config.json",
'bert-base-german-dbmdz-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-uncased-config.json",
}

2
transformers/modeling_bert.py
View File

@@ -48,6 +48,8 @@ BERT_PRETRAINED_MODEL_ARCHIVE_MAP = {
'bert-large-uncased-whole-word-masking-finetuned-squad': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-finetuned-squad-pytorch_model.bin",
'bert-large-cased-whole-word-masking-finetuned-squad': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-whole-word-masking-finetuned-squad-pytorch_model.bin",
'bert-base-cased-finetuned-mrpc': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-finetuned-mrpc-pytorch_model.bin",
'bert-base-german-dbmdz-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-cased-pytorch_model.bin",
'bert-base-german-dbmdz-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-uncased-pytorch_model.bin",
}
def load_tf_weights_in_bert(model, config, tf_checkpoint_path):

6
transformers/tokenization_bert.py
View File

@@ -44,6 +44,8 @@ PRETRAINED_VOCAB_FILES_MAP = {
'bert-large-uncased-whole-word-masking-finetuned-squad': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-finetuned-squad-vocab.txt",
'bert-large-cased-whole-word-masking-finetuned-squad': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-whole-word-masking-finetuned-squad-vocab.txt",
'bert-base-cased-finetuned-mrpc': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-finetuned-mrpc-vocab.txt",
'bert-base-german-dbmdz-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-cased-vocab.txt",
'bert-base-german-dbmdz-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-uncased-vocab.txt",
}
}
@@ -61,6 +63,8 @@ PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
'bert-large-uncased-whole-word-masking-finetuned-squad': 512,
'bert-large-cased-whole-word-masking-finetuned-squad': 512,
'bert-base-cased-finetuned-mrpc': 512,
'bert-base-german-dbmdz-cased': 512,
'bert-base-german-dbmdz-uncased': 512,
}
PRETRAINED_INIT_CONFIGURATION = {
@@ -77,6 +81,8 @@ PRETRAINED_INIT_CONFIGURATION = {
'bert-large-uncased-whole-word-masking-finetuned-squad': {'do_lower_case': True},
'bert-large-cased-whole-word-masking-finetuned-squad': {'do_lower_case': False},
'bert-base-cased-finetuned-mrpc': {'do_lower_case': False},
'bert-base-german-dbmdz-cased': {'do_lower_case': False},
'bert-base-german-dbmdz-uncased': {'do_lower_case': True},
}