Adding Finnish BERT.

transformers/configuration_bert.py

@@ -45,7 +45,9 @@ BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
     'bert-base-japanese': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-config.json",
     'bert-base-japanese-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-whole-word-masking-config.json",
     'bert-base-japanese-char': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-config.json",
-    'bert-base-japanese-char-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-whole-word-masking-config.json"
+    'bert-base-japanese-char-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-whole-word-masking-config.json",
+    'bert-base-finnish-cased-v1': "http://dl.turkunlp.org/finbert/torch-transformers/bert-base-finnish-cased-v1/config.json",
+    'bert-base-finnish-uncased-v1': "http://dl.turkunlp.org/finbert/torch-transformers/bert-base-finnish-uncased-v1/config.json",
 }
 
 

transformers/modeling_bert.py

@@ -51,7 +51,9 @@ BERT_PRETRAINED_MODEL_ARCHIVE_MAP = {
     'bert-base-japanese': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-pytorch_model.bin",
     'bert-base-japanese-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-whole-word-masking-pytorch_model.bin",
     'bert-base-japanese-char': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-pytorch_model.bin",
-    'bert-base-japanese-char-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-whole-word-masking-pytorch_model.bin"
+    'bert-base-japanese-char-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-whole-word-masking-pytorch_model.bin",
+    'bert-base-finnish-cased-v1': "http://dl.turkunlp.org/finbert/torch-transformers/bert-base-finnish-cased-v1/pytorch_model.bin",
+    'bert-base-finnish-uncased-v1': "http://dl.turkunlp.org/finbert/torch-transformers/bert-base-finnish-uncased-v1/pytorch_model.bin",
 }
 
 

transformers/modeling_tf_bert.py

@@ -51,7 +51,9 @@ TF_BERT_PRETRAINED_MODEL_ARCHIVE_MAP = {
     'bert-base-japanese': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-tf_model.h5",
     'bert-base-japanese-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-whole-word-masking-tf_model.h5",
     'bert-base-japanese-char': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-tf_model.h5",
-    'bert-base-japanese-char-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-whole-word-masking-tf_model.h5"
+    'bert-base-japanese-char-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-whole-word-masking-tf_model.h5",
+    #'bert-base-finnish-cased-v1': "http://dl.turkunlp.org/finbert/torch-transformers/bert-base-finnish-cased-v1/pytorch_model.bin",
+    #'bert-base-finnish-uncased-v1': "http://dl.turkunlp.org/finbert/torch-transformers/bert-base-finnish-uncased-v1/pytorch_model.bin",
 }
 
 

transformers/tokenization_bert.py

@@ -46,6 +46,8 @@ PRETRAINED_VOCAB_FILES_MAP = {
         '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",
+        'bert-base-finnish-cased-v1': "http://dl.turkunlp.org/finbert/torch-transformers/bert-base-finnish-cased-v1/vocab.txt",
+        'bert-base-finnish-uncased-v1': "http://dl.turkunlp.org/finbert/torch-transformers/bert-base-finnish-uncased-v1/vocab.txt",
     }
 }
 
@@ -65,6 +67,8 @@ PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
     'bert-base-cased-finetuned-mrpc': 512,
     'bert-base-german-dbmdz-cased': 512,
     'bert-base-german-dbmdz-uncased': 512,
+    'bert-base-finnish-cased-v1': 512,
+    'bert-base-finnish-uncased-v1': 512,
 }
 
 PRETRAINED_INIT_CONFIGURATION = {
@@ -83,6 +87,8 @@ PRETRAINED_INIT_CONFIGURATION = {
     '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},
+    'bert-base-finnish-cased-v1': {'do_lower_case': False},
+    'bert-base-finnish-uncased-v1': {'do_lower_case': True},
 }