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

Add Dutch pre-trained BERT model

Browse Source
This commit is contained in:
Wietse de Vries
2019-12-19 13:28:53 +01:00
committed by Julien Chaumond
parent 6b4c3ee234
commit f5a236c3ca
5 changed files with 10 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/transformers/tokenization_bert.py
View File

@@ -48,6 +48,7 @@ PRETRAINED_VOCAB_FILES_MAP = {
"bert-base-german-dbmdz-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-uncased-vocab.txt",
"bert-base-finnish-cased-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/TurkuNLP/bert-base-finnish-cased-v1/vocab.txt",
"bert-base-finnish-uncased-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/TurkuNLP/bert-base-finnish-uncased-v1/vocab.txt",
"bert-base-dutch-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/wietsedv/bert-base-dutch-cased/vocab.txt",
}
}
@@ -69,6 +70,7 @@ PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
"bert-base-german-dbmdz-uncased": 512,
"bert-base-finnish-cased-v1": 512,
"bert-base-finnish-uncased-v1": 512,
"bert-base-dutch-cased": 512,
}
PRETRAINED_INIT_CONFIGURATION = {
@@ -89,6 +91,7 @@ PRETRAINED_INIT_CONFIGURATION = {
"bert-base-german-dbmdz-uncased": {"do_lower_case": True},
"bert-base-finnish-cased-v1": {"do_lower_case": False},
"bert-base-finnish-uncased-v1": {"do_lower_case": True},
"bert-base-dutch-cased": {'do_lower_case': False},
}