riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-08-03 03:31:05 +06:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Added new bert models

Browse Source
This commit is contained in:
thomwolf 2018-11-30 13:56:02 +01:00
parent 0541442558
commit 298107fed7
3 changed files with 9 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -175,7 +175,9 @@ where
- `bert-base-uncased`: 12-layer, 768-hidden, 12-heads, 110M parameters
- `bert-large-uncased`: 24-layer, 1024-hidden, 16-heads, 340M parameters
- `bert-base-cased`: 12-layer, 768-hidden, 12-heads , 110M parameters
- `bert-base-multilingual`: 102 languages, 12-layer, 768-hidden, 12-heads, 110M parameters
- `bert-large-cased`: 24-layer, 1024-hidden, 16-heads, 340M parameters
- `bert-base-multilingual-uncased`: (Orig, not recommended) 102 languages, 12-layer, 768-hidden, 12-heads, 110M parameters
- `bert-base-multilingual-cased`: (New, recommended) 104 languages, 12-layer, 768-hidden, 12-heads, 110M parameters
- `bert-base-chinese`: Chinese Simplified and Traditional, 12-layer, 768-hidden, 12-heads, 110M parameters
- a path or url to a pretrained model archive containing:

4
pytorch_pretrained_bert/modeling.py
View File

@ -42,7 +42,9 @@ PRETRAINED_MODEL_ARCHIVE_MAP = {
'bert-base-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased.tar.gz",
'bert-large-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased.tar.gz",
'bert-base-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased.tar.gz",
'bert-base-multilingual': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual.tar.gz",
'bert-large-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased.tar.gz",
'bert-base-multilingual-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-uncased.tar.gz",
'bert-base-multilingual-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-cased.tar.gz",
'bert-base-chinese': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-chinese.tar.gz",
}
CONFIG_NAME = 'bert_config.json'

4
pytorch_pretrained_bert/tokenization.py
View File

@ -34,7 +34,9 @@ PRETRAINED_VOCAB_ARCHIVE_MAP = {
'bert-base-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-vocab.txt",
'bert-large-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-vocab.txt",
'bert-base-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-vocab.txt",
'bert-base-multilingual': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-vocab.txt",
'bert-large-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-vocab.txt",
'bert-base-multilingual-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-uncased-vocab.txt",
'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",
}