distilbert-base-cased weights + Readmes + omissions

README.md

@@ -195,7 +195,7 @@ MODELS = [(BertModel,       BertTokenizer,       'bert-base-uncased'),
           (TransfoXLModel,  TransfoXLTokenizer,  'transfo-xl-wt103'),
           (XLNetModel,      XLNetTokenizer,      'xlnet-base-cased'),
           (XLMModel,        XLMTokenizer,        'xlm-mlm-enfr-1024'),
-          (DistilBertModel, DistilBertTokenizer, 'distilbert-base-uncased'),
+          (DistilBertModel, DistilBertTokenizer, 'distilbert-base-cased'),
           (RobertaModel,    RobertaTokenizer,    'roberta-base'),
           (XLMRobertaModel, XLMRobertaTokenizer, 'xlm-roberta-base'),
          ]

docs/source/pretrained_models.rst

@@ -179,6 +179,14 @@ For a list that includes community-uploaded models, refer to `https://huggingfac
 |                   |                                                            | | The DistilBERT model distilled from the BERT model `bert-base-uncased` checkpoint, with an additional linear layer.                 |
 |                   |                                                            | (see `details <https://github.com/huggingface/transformers/tree/master/examples/distillation>`__)                                     |
 |                   +------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
+|                   | ``distilbert-base-cased``                                  | | 6-layer, 768-hidden, 12-heads, 65M parameters                                                                                       |
+|                   |                                                            | | The DistilBERT model distilled from the BERT model `bert-base-cased` checkpoint                                                     |
+|                   |                                                            | (see `details <https://github.com/huggingface/transformers/tree/master/examples/distillation>`__)                                     |
+|                   +------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
+|                   | ``distilbert-base-cased-distilled-squad``                  | | 6-layer, 768-hidden, 12-heads, 65M parameters                                                                                       |
+|                   |                                                            | | The DistilBERT model distilled from the BERT model `bert-base-cased` checkpoint, with an additional question answering layer.       |
+|                   |                                                            | (see `details <https://github.com/huggingface/transformers/tree/master/examples/distillation>`__)                                     |
+|                   +------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
 |                   | ``distilgpt2``                                             | | 6-layer, 768-hidden, 12-heads, 82M parameters                                                                                       |
 |                   |                                                            | | The DistilGPT2 model distilled from the GPT2 model `gpt2` checkpoint.                                                               |
 |                   |                                                            | (see `details <https://github.com/huggingface/transformers/tree/master/examples/distillation>`__)                                     |

examples/distillation/README.md

@@ -31,8 +31,10 @@ Here are the results on the dev sets of GLUE:
 
 | Model                     | Macro-score                    | CoLA | MNLI | MRPC | QNLI | QQP  | RTE  | SST-2| STS-B| WNLI              |
 | :---:                     |    :---:                       | :---:| :---:| :---:| :---:| :---:| :---:| :---:| :---:| :---:             |
-| BERT-base-uncased         |  **77.6**                      | 49.2 | 80.8 | 87.4 | 87.5 | 86.4 | 61.7 | 92.0 | 83.8 | 45.1              |
-| DistilBERT-base-uncased   |  **76.8**                      | 43.6 | 79.0 | 87.5 | 85.3 | 84.9 | 59.9 | 90.7 | 81.2 | 56.3              |
+| BERT-base-uncased         |  **74.9**                      | 49.2 | 80.8 | 87.4 | 87.5 | 86.4 | 61.7 | 92.0 | 83.8 | 45.1              |
+| DistilBERT-base-uncased   |  **74.3**                      | 43.6 | 79.0 | 87.5 | 85.3 | 84.9 | 59.9 | 90.7 | 81.2 | 56.3              |
+| BERT-base-cased           |  **78.2**                      | 58.2 | 83.9 | 87.8 | 91.0 | 89.2 | 66.1 | 91.7 | 89.2 | 46.5              |
+| DistilBERT-base-cased     |  **75.9**                      | 47.2 | 81.5 | 85.6 | 88.2 | 87.8 | 60.6 | 90.4 | 85.5 | 56.3              |
 | ---                       |    ---                         |  --- |  --- |  --- |  --- |  --- |  --- |  --- |  --- |  ---              |
 | RoBERTa-base (reported)   |  **83.2**/**86.4**<sup>2</sup> | 63.6 | 87.6 | 90.2 | 92.8 | 91.9 | 78.7 | 94.8 | 91.2 | 57.7<sup>3</sup>  |
 | DistilRoBERTa<sup>1</sup> |  **79.0**/**82.3**<sup>2</sup> | 59.3 | 84.0 | 86.6 | 90.8 | 89.4 | 67.9 | 92.5 | 88.3 | 52.1              |
@@ -63,7 +65,9 @@ This part of the library has only be tested with Python3.6+. There are few speci
 Transformers includes five pre-trained Distil* models, currently only provided for English and German (we are investigating the possibility to train and release a multilingual version of DistilBERT):
 
 - `distilbert-base-uncased`: DistilBERT English language model pretrained on the same data used to pretrain Bert (concatenation of the Toronto Book Corpus and full English Wikipedia) using distillation with the supervision of the `bert-base-uncased` version of Bert. The model has 6 layers, 768 dimension and 12 heads, totalizing 66M parameters.
-- `distilbert-base-uncased-distilled-squad`: A finetuned version of `distilbert-base-uncased` finetuned using (a second step of) knwoledge distillation on SQuAD 1.0. This model reaches a F1 score of 86.9 on the dev set (for comparison, Bert `bert-base-uncased` version reaches a 88.5 F1 score).
+- `distilbert-base-uncased-distilled-squad`: A finetuned version of `distilbert-base-uncased` finetuned using (a second step of) knwoledge distillation on SQuAD 1.0. This model reaches a F1 score of 79.8 on the dev set (for comparison, Bert `bert-base-uncased` version reaches a 82.3 F1 score).
+- `distilbert-base-cased`: DistilBERT English language model pretrained on the same data used to pretrain Bert (concatenation of the Toronto Book Corpus and full English Wikipedia) using distillation with the supervision of the `bert-base-cased` version of Bert. The model has 6 layers, 768 dimension and 12 heads, totalizing 65M parameters.
+- `distilbert-base-cased-distilled-squad`: A finetuned version of `distilbert-base-cased` finetuned using (a second step of) knwoledge distillation on SQuAD 1.0. This model reaches a F1 score of 87.1 on the dev set (for comparison, Bert `bert-base-cased` version reaches a 88.7 F1 score).
 - `distilbert-base-german-cased`: DistilBERT German language model pretrained on 1/2 of the data used to pretrain Bert using distillation with the supervision of the `bert-base-german-dbmdz-cased` version of German DBMDZ Bert. For NER tasks the model reaches a F1 score of 83.49 on the CoNLL-2003 test set (for comparison, `bert-base-german-dbmdz-cased` reaches a 84.52 F1 score), and a F1 score of 85.23 on the GermEval 2014 test set (`bert-base-german-dbmdz-cased` reaches a 86.89 F1 score).
 - `distilgpt2`: DistilGPT2 English language model pretrained with the supervision of `gpt2` (the smallest version of GPT2) on [OpenWebTextCorpus](https://skylion007.github.io/OpenWebTextCorpus/), a reproduction of OpenAI's WebText dataset. The model has 6 layers, 768 dimension and 12 heads, totalizing 82M parameters (compared to 124M parameters for GPT2). On average, DistilGPT2 is two times faster than GPT2.
 - `distilroberta-base`: DistilRoBERTa English language model pretrained with the supervision of `roberta-base` solely on [OpenWebTextCorpus](https://skylion007.github.io/OpenWebTextCorpus/), a reproduction of OpenAI's WebText dataset (it is ~4 times less training data than the teacher RoBERTa). The model has 6 layers, 768 dimension and 12 heads, totalizing 82M parameters (compared to 125M parameters for RoBERTa-base). On average DistilRoBERTa is twice as fast as Roberta-base.
@@ -72,8 +76,8 @@ Transformers includes five pre-trained Distil* models, currently only provided f
 Using DistilBERT is very similar to using BERT. DistilBERT share the same tokenizer as BERT's `bert-base-uncased` even though we provide a link to this tokenizer under the `DistilBertTokenizer` name to have a consistent naming between the library models.
 
 ```python
-tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
-model = DistilBertModel.from_pretrained('distilbert-base-uncased')
+tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-cased')
+model = DistilBertModel.from_pretrained('distilbert-base-cased')
 
 input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute")).unsqueeze(0)
 outputs = model(input_ids)
@@ -81,6 +85,7 @@ last_hidden_states = outputs[0]  # The last hidden-state is the first element of
 ```
 
 Similarly, using the other Distil* models simply consists in calling the base classes with a different pretrained checkpoint:
+- DistilBERT uncased: `model = DistilBertModel.from_pretrained('distilbert-base-uncased')`
 - DistilGPT2: `model = GPT2Model.from_pretrained('distilgpt2')`
 - DistilRoBERTa: `model = RobertaModel.from_pretrained('distilroberta-base')`
 - DistilmBERT: `model = DistilBertModel.from_pretrained('distilbert-base-multilingual-cased')`

examples/distillation/training_configs/distilbert-base-cased.json

+{
+	"activation": "gelu",
+	"attention_dropout": 0.1,
+	"dim": 768,
+	"dropout": 0.1,
+	"hidden_dim": 3072,
+	"initializer_range": 0.02,
+	"max_position_embeddings": 512,
+	"n_heads": 12,
+	"n_layers": 6,
+	"sinusoidal_pos_embds": true,
+	"tie_weights_": true,
+	"vocab_size": 28996
+  }
+  
\ No newline at end of file

src/transformers/configuration_distilbert.py

@@ -25,6 +25,8 @@ logger = logging.getLogger(__name__)
 DISTILBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
     "distilbert-base-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-uncased-config.json",
     "distilbert-base-uncased-distilled-squad": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-uncased-distilled-squad-config.json",
+    "distilbert-base-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-cased-config.json",
+    "distilbert-base-cased-distilled-squad": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-cased-distilled-squad-config.json",
     "distilbert-base-german-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-german-cased-config.json",
     "distilbert-base-multilingual-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-multilingual-cased-config.json",
     "distilbert-base-uncased-finetuned-sst-2-english": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-uncased-finetuned-sst-2-english-config.json",

src/transformers/convert_pytorch_checkpoint_to_tf2.py

@@ -277,7 +277,7 @@ MODEL_CLASSES = {
         DISTILBERT_PRETRAINED_MODEL_ARCHIVE_MAP,
         DISTILBERT_PRETRAINED_CONFIG_ARCHIVE_MAP,
     ),
-    "distilbert-base-uncased-distilled-squad": (
+    "distilbert-base-distilled-squad": (
         DistilBertConfig,
         TFDistilBertForQuestionAnswering,
         DistilBertForQuestionAnswering,

src/transformers/modeling_distilbert.py

@@ -38,6 +38,8 @@ logger = logging.getLogger(__name__)
 DISTILBERT_PRETRAINED_MODEL_ARCHIVE_MAP = {
     "distilbert-base-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-uncased-pytorch_model.bin",
     "distilbert-base-uncased-distilled-squad": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-uncased-distilled-squad-pytorch_model.bin",
+    "distilbert-base-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-cased-pytorch_model.bin",
+    "distilbert-base-cased-distilled-squad": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-cased-distilled-squad-pytorch_model.bin",
     "distilbert-base-german-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-german-cased-pytorch_model.bin",
     "distilbert-base-multilingual-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-multilingual-cased-pytorch_model.bin",
     "distilbert-base-uncased-finetuned-sst-2-english": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-uncased-finetuned-sst-2-english-pytorch_model.bin",
@@ -440,8 +442,8 @@ class DistilBertModel(DistilBertPreTrainedModel):
         from transformers import DistilBertTokenizer, DistilBertModel
         import torch
 
-        tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
-        model = DistilBertModel.from_pretrained('distilbert-base-uncased')
+        tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-cased')
+        model = DistilBertModel.from_pretrained('distilbert-base-cased')
 
         input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True)).unsqueeze(0)  # Batch size 1
         outputs = model(input_ids)
@@ -544,8 +546,8 @@ class DistilBertForMaskedLM(DistilBertPreTrainedModel):
         from transformers import DistilBertTokenizer, DistilBertForMaskedLM
         import torch
 
-        tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
-        model = DistilBertForMaskedLM.from_pretrained('distilbert-base-uncased')
+        tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-cased')
+        model = DistilBertForMaskedLM.from_pretrained('distilbert-base-cased')
         input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True)).unsqueeze(0)  # Batch size 1
         outputs = model(input_ids, masked_lm_labels=input_ids)
         loss, prediction_scores = outputs[:2]
@@ -619,8 +621,8 @@ class DistilBertForSequenceClassification(DistilBertPreTrainedModel):
         from transformers import DistilBertTokenizer, DistilBertForSequenceClassification
         import torch
 
-        tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
-        model = DistilBertForSequenceClassification.from_pretrained('distilbert-base-uncased')
+        tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-cased')
+        model = DistilBertForSequenceClassification.from_pretrained('distilbert-base-cased')
         input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True)).unsqueeze(0)  # Batch size 1
         labels = torch.tensor([1]).unsqueeze(0)  # Batch size 1
         outputs = model(input_ids, labels=labels)
@@ -711,8 +713,8 @@ class DistilBertForQuestionAnswering(DistilBertPreTrainedModel):
         from transformers import DistilBertTokenizer, DistilBertForQuestionAnswering
         import torch
 
-        tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
-        model = DistilBertForQuestionAnswering.from_pretrained('distilbert-base-uncased')
+        tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-cased')
+        model = DistilBertForQuestionAnswering.from_pretrained('distilbert-base-cased')
         input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True)).unsqueeze(0)  # Batch size 1
         start_positions = torch.tensor([1])
         end_positions = torch.tensor([3])
@@ -798,8 +800,8 @@ class DistilBertForTokenClassification(DistilBertPreTrainedModel):
         from transformers import DistilBertTokenizer, DistilBertForTokenClassification
         import torch
 
-        tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
-        model = DistilBertForTokenClassification.from_pretrained('distilbert-base-uncased')
+        tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-cased')
+        model = DistilBertForTokenClassification.from_pretrained('distilbert-base-cased')
         input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute")).unsqueeze(0)  # Batch size 1
         labels = torch.tensor([1] * input_ids.size(1)).unsqueeze(0)  # Batch size 1
         outputs = model(input_ids, labels=labels)

src/transformers/modeling_tf_distilbert.py

@@ -33,6 +33,8 @@ logger = logging.getLogger(__name__)
 TF_DISTILBERT_PRETRAINED_MODEL_ARCHIVE_MAP = {
     "distilbert-base-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-uncased-tf_model.h5",
     "distilbert-base-uncased-distilled-squad": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-uncased-distilled-squad-tf_model.h5",
+    "distilbert-base-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-cased-tf_model.h5",
+    "distilbert-base-cased-distilled-squad": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-cased-distilled-squad-tf_model.h5",
     "distilbert-base-multilingual-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-multilingual-cased-tf_model.h5",
     "distilbert-base-uncased-finetuned-sst-2-english": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-uncased-finetuned-sst-2-english-tf_model.h5",
 }
@@ -78,8 +80,6 @@ class TFEmbeddings(tf.keras.layers.Layer):
             embeddings_initializer=get_initializer(config.initializer_range),
             name="position_embeddings",
         )
-        if config.sinusoidal_pos_embds:
-            raise NotImplementedError
 
         self.LayerNorm = tf.keras.layers.LayerNormalization(epsilon=1e-12, name="LayerNorm")
         self.dropout = tf.keras.layers.Dropout(config.dropout)
@@ -563,8 +563,8 @@ class TFDistilBertModel(TFDistilBertPreTrainedModel):
         import tensorflow as tf
         from transformers import DistilBertTokenizer, TFDistilBertModel
 
-        tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
-        model = TFDistilBertModel.from_pretrained('distilbert-base-uncased')
+        tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-cased')
+        model = TFDistilBertModel.from_pretrained('distilbert-base-cased')
         input_ids = tf.constant(tokenizer.encode("Hello, my dog is cute"))[None, :]  # Batch size 1
         outputs = model(input_ids)
         last_hidden_states = outputs[0]  # The last hidden-state is the first element of the output tuple
@@ -637,8 +637,8 @@ class TFDistilBertForMaskedLM(TFDistilBertPreTrainedModel):
         import tensorflow as tf
         from transformers import DistilBertTokenizer, TFDistilBertForMaskedLM
 
-        tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
-        model = TFDistilBertForMaskedLM.from_pretrained('distilbert-base-uncased')
+        tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-cased')
+        model = TFDistilBertForMaskedLM.from_pretrained('distilbert-base-cased')
         input_ids = tf.constant(tokenizer.encode("Hello, my dog is cute"))[None, :]  # Batch size 1
         outputs = model(input_ids)
         prediction_scores = outputs[0]
@@ -701,8 +701,8 @@ class TFDistilBertForSequenceClassification(TFDistilBertPreTrainedModel):
         import tensorflow as tf
         from transformers import DistilBertTokenizer, TFDistilBertForSequenceClassification
 
-        tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
-        model = TFDistilBertForSequenceClassification.from_pretrained('distilbert-base-uncased')
+        tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-cased')
+        model = TFDistilBertForSequenceClassification.from_pretrained('distilbert-base-cased')
         input_ids = tf.constant(tokenizer.encode("Hello, my dog is cute"))[None, :]  # Batch size 1
         outputs = model(input_ids)
         logits = outputs[0]
@@ -759,8 +759,8 @@ class TFDistilBertForTokenClassification(TFDistilBertPreTrainedModel):
         import tensorflow as tf
         from transformers import DistilBertTokenizer, TFDistilBertForTokenClassification
 
-        tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
-        model = TFDistilBertForTokenClassification.from_pretrained('distilbert-base-uncased')
+        tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-cased')
+        model = TFDistilBertForTokenClassification.from_pretrained('distilbert-base-cased')
         input_ids = tf.constant(tokenizer.encode("Hello, my dog is cute"))[None, :]  # Batch size 1
         outputs = model(input_ids)
         scores = outputs[0]
@@ -818,8 +818,8 @@ class TFDistilBertForQuestionAnswering(TFDistilBertPreTrainedModel):
         import tensorflow as tf
         from transformers import DistilBertTokenizer, TFDistilBertForQuestionAnswering
 
-        tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
-        model = TFDistilBertForQuestionAnswering.from_pretrained('distilbert-base-uncased')
+        tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-cased')
+        model = TFDistilBertForQuestionAnswering.from_pretrained('distilbert-base-cased')
         input_ids = tf.constant(tokenizer.encode("Hello, my dog is cute"))[None, :]  # Batch size 1
         outputs = model(input_ids)
         start_scores, end_scores = outputs[:2]

src/transformers/pipelines.py

@@ -941,9 +941,9 @@ SUPPORTED_TASKS = {
         "tf": TFAutoModel if is_tf_available() else None,
         "pt": AutoModel if is_torch_available() else None,
         "default": {
-            "model": {"pt": "distilbert-base-uncased", "tf": "distilbert-base-uncased"},
+            "model": {"pt": "distilbert-base-cased", "tf": "distilbert-base-cased"},
             "config": None,
-            "tokenizer": "distilbert-base-uncased",
+            "tokenizer": "distilbert-base-cased",
         },
     },
     "sentiment-analysis": {
@@ -978,11 +978,11 @@ SUPPORTED_TASKS = {
         "pt": AutoModelForQuestionAnswering if is_torch_available() else None,
         "default": {
             "model": {
-                "pt": "distilbert-base-uncased-distilled-squad",
-                "tf": "distilbert-base-uncased-distilled-squad",
+                "pt": "distilbert-base-cased-distilled-squad",
+                "tf": "distilbert-base-cased-distilled-squad",
             },
             "config": None,
-            "tokenizer": "distilbert-base-uncased",
+            "tokenizer": "distilbert-base-cased",
         },
     },
     "fill-mask": {
@@ -1015,7 +1015,7 @@ def pipeline(
 
     Examples:
         pipeline('sentiment-analysis')
-        pipeline('question-answering', model='distilbert-base-uncased-distilled-squad', tokenizer='bert-base-cased')
+        pipeline('question-answering', model='distilbert-base-cased-distilled-squad', tokenizer='bert-base-cased')
         pipeline('ner', model=AutoModel.from_pretrained(...), tokenizer=AutoTokenizer.from_pretrained(...)
         pipeline('ner', model='dbmdz/bert-large-cased-finetuned-conll03-english', tokenizer='bert-base-cased')
         pipeline('ner', model='https://...pytorch-model.bin', config='https://...config.json', tokenizer='bert-base-cased')

src/transformers/tokenization_distilbert.py

@@ -28,6 +28,8 @@ PRETRAINED_VOCAB_FILES_MAP = {
     "vocab_file": {
         "distilbert-base-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-vocab.txt",
         "distilbert-base-uncased-distilled-squad": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-vocab.txt",
+        "distilbert-base-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-vocab.txt",
+        "distilbert-base-cased-distilled-squad": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-vocab.txt",
         "distilbert-base-german-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-german-cased-vocab.txt",
         "distilbert-base-multilingual-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-cased-vocab.txt",
     }
@@ -36,6 +38,8 @@ PRETRAINED_VOCAB_FILES_MAP = {
 PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
     "distilbert-base-uncased": 512,
     "distilbert-base-uncased-distilled-squad": 512,
+    "distilbert-base-cased": 512,
+    "distilbert-base-cased-distilled-squad": 512,
     "distilbert-base-german-cased": 512,
     "distilbert-base-multilingual-cased": 512,
 }
@@ -44,6 +48,8 @@ PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
 PRETRAINED_INIT_CONFIGURATION = {
     "distilbert-base-uncased": {"do_lower_case": True},
     "distilbert-base-uncased-distilled-squad": {"do_lower_case": True},
+    "distilbert-base-cased": {"do_lower_case": False},
+    "distilbert-base-cased-distilled-squad": {"do_lower_case": False},
     "distilbert-base-german-cased": {"do_lower_case": False},
     "distilbert-base-multilingual-cased": {"do_lower_case": False},
 }

tests/test_pipelines.py

@@ -10,13 +10,13 @@ from .utils import require_tf, require_torch
 QA_FINETUNED_MODELS = {
     ("bert-base-uncased", "bert-large-uncased-whole-word-masking-finetuned-squad", None),
     ("bert-base-cased", "bert-large-cased-whole-word-masking-finetuned-squad", None),
-    ("bert-base-uncased", "distilbert-base-uncased-distilled-squad", None),
+    ("bert-base-uncased", "distilbert-base-cased-distilled-squad", None),
 }
 
 TF_QA_FINETUNED_MODELS = {
     ("bert-base-uncased", "bert-large-uncased-whole-word-masking-finetuned-squad", None),
     ("bert-base-cased", "bert-large-cased-whole-word-masking-finetuned-squad", None),
-    ("bert-base-uncased", "distilbert-base-uncased-distilled-squad", None),
+    ("bert-base-uncased", "distilbert-base-cased-distilled-squad", None),
 }
 
 TF_NER_FINETUNED_MODELS = {
@@ -38,13 +38,13 @@ NER_FINETUNED_MODELS = {
 FEATURE_EXTRACT_FINETUNED_MODELS = {
     ("bert-base-cased", "bert-base-cased", None),
     # ('xlnet-base-cased', 'xlnet-base-cased', None), # Disabled for now as it crash for TF2
-    ("distilbert-base-uncased", "distilbert-base-uncased", None),
+    ("distilbert-base-cased", "distilbert-base-cased", None),
 }
 
 TF_FEATURE_EXTRACT_FINETUNED_MODELS = {
     ("bert-base-cased", "bert-base-cased", None),
     # ('xlnet-base-cased', 'xlnet-base-cased', None), # Disabled for now as it crash for TF2
-    ("distilbert-base-uncased", "distilbert-base-uncased", None),
+    ("distilbert-base-cased", "distilbert-base-cased", None),
 }
 
 TF_TEXT_CLASSIF_FINETUNED_MODELS = {