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

adding bert whole words, bertgerman and gpt-2 medium models, head masking

Browse Source
This commit is contained in:
thomwolf
2019-06-17 11:02:39 +02:00
parent 80684f6f86
commit 34858ae1d9
3 changed files with 56 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
pytorch_pretrained_bert/tokenization.py
View File

@@ -35,6 +35,8 @@ PRETRAINED_VOCAB_ARCHIVE_MAP = {
'bert-base-multilingual-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-cased-vocab.txt",
'bert-base-chinese': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-chinese-vocab.txt",
'bert-base-german-cased': "https://int-deepset-models-bert.s3.eu-central-1.amazonaws.com/pytorch/bert-base-german-cased-vocab.txt",
'bert-large-uncased-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-vocab.txt",
'bert-large-cased-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-whole-word-masking-vocab.txt",
}
PRETRAINED_VOCAB_POSITIONAL_EMBEDDINGS_SIZE_MAP = {
'bert-base-uncased': 512,
@@ -45,6 +47,8 @@ PRETRAINED_VOCAB_POSITIONAL_EMBEDDINGS_SIZE_MAP = {
'bert-base-multilingual-cased': 512,
'bert-base-chinese': 512,
'bert-base-german-cased': 512,
'bert-large-uncased-whole-word-masking': 512,
'bert-large-cased-whole-word-masking': 512,
}
VOCAB_NAME = 'vocab.txt'