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

Add new BERT models for German (cased and uncased)

docs/source/pretrained_models.rst

@@ -53,6 +53,14 @@ Here is the full list of the currently provided pretrained models together with
 |                   | ``bert-base-cased-finetuned-mrpc``                         | | 12-layer, 768-hidden, 12-heads, 110M parameters.                                                                                    |
 |                   |                                                            | | The ``bert-base-cased`` model fine-tuned on MRPC                                                                                    |
 |                   |                                                            | (see `details of fine-tuning in the example section <https://huggingface.co/transformers/examples.html>`__)                           |
+|                   +------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
+|                   | ``bert-base-german-dbmdz-cased``                           | | 12-layer, 768-hidden, 12-heads, 110M parameters.                                                                                    |
+|                   |                                                            | | Trained on cased German text by DBMDZ                                                                                               |
+|                   |                                                            | (see `details on dbmdz repository <https://github.com/dbmdz/german-bert>`__).                                                         |
+|                   +------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
+|                   | ``bert-base-german-dbmdz-uncased``                         | | 12-layer, 768-hidden, 12-heads, 110M parameters.                                                                                    |
+|                   |                                                            | | Trained on uncased German text by DBMDZ                                                                                             |
+|                   |                                                            | (see `details on dbmdz repository <https://github.com/dbmdz/german-bert>`__).                                                         |
 +-------------------+------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
 | GPT               | ``openai-gpt``                                             | | 12-layer, 768-hidden, 12-heads, 110M parameters.                                                                                    |
 |                   |                                                            | | OpenAI GPT English model                                                                                                            |

docs/source/serialization.rst

@@ -33,6 +33,8 @@ where
     * ``bert-large-uncased-whole-word-masking``: 24-layer, 1024-hidden, 16-heads, 340M parameters - Trained with Whole Word Masking (mask all of the the tokens corresponding to a word at once)
     * ``bert-large-cased-whole-word-masking``: 24-layer, 1024-hidden, 16-heads, 340M parameters - Trained with Whole Word Masking (mask all of the the tokens corresponding to a word at once)
     * ``bert-large-uncased-whole-word-masking-finetuned-squad``: The ``bert-large-uncased-whole-word-masking`` model finetuned on SQuAD (using the ``run_bert_squad.py`` examples). Results: *exact_match: 86.91579943235573, f1: 93.1532499015869*
+    * ``bert-base-german-dbmdz-cased``: Trained on German data only, 12-layer, 768-hidden, 12-heads, 110M parameters `Performance Evaluation <https://github.com/dbmdz/german-bert>`__
+    * ``bert-base-german-dbmdz-uncased``: Trained on (uncased) German data only, 12-layer, 768-hidden, 12-heads, 110M parameters `Performance Evaluation <https://github.com/dbmdz/german-bert>`__
     * ``openai-gpt``: OpenAI GPT English model, 12-layer, 768-hidden, 12-heads, 110M parameters
     * ``gpt2``: OpenAI GPT-2 English model, 12-layer, 768-hidden, 12-heads, 117M parameters
     * ``gpt2-medium``: OpenAI GPT-2 English model, 24-layer, 1024-hidden, 16-heads, 345M parameters

transformers/configuration_bert.py

@@ -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",
 }
 
 

transformers/modeling_bert.py

@@ -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):

transformers/tokenization_bert.py

@@ -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},
 }