Add Doc Test for BERT (#16523)

* Add doctest BERT

* make fixup

* fix typo

* change checkpoints

* make fixup

* define doctest output value, update doctest for mobilebert

* solve fix-copies

* update QA target start index and end index

* change checkpoint for docs and reuse defined variable

* Update src/transformers/models/bert/modeling_tf_bert.py
Co-authored-by: Yih-Dar <2521628+ydshieh@users.noreply.github.com>

* Apply suggestions from code review
Co-authored-by: Yih-Dar <2521628+ydshieh@users.noreply.github.com>

* Apply suggestions from code review
Co-authored-by: Yih-Dar <2521628+ydshieh@users.noreply.github.com>

* make fixup
Co-authored-by: Yih-Dar <2521628+ydshieh@users.noreply.github.com>

src/transformers/models/bert/modeling_bert.py

@@ -63,6 +63,26 @@ _CHECKPOINT_FOR_DOC = "bert-base-uncased"
 _CONFIG_FOR_DOC = "BertConfig"
 _TOKENIZER_FOR_DOC = "BertTokenizer"
 
+# TokenClassification docstring
+_CHECKPOINT_FOR_TOKEN_CLASSIFICATION = "dbmdz/bert-large-cased-finetuned-conll03-english"
+_TOKEN_CLASS_EXPECTED_OUTPUT = (
+    "['O', 'I-ORG', 'I-ORG', 'I-ORG', 'O', 'O', 'O', 'O', 'O', 'I-LOC', 'O', 'I-LOC', " "'I-LOC'] "
+)
+_TOKEN_CLASS_EXPECTED_LOSS = 0.01
+
+# QuestionAnswering docstring
+_CHECKPOINT_FOR_QA = "deepset/bert-base-cased-squad2"
+_QA_EXPECTED_OUTPUT = "'a nice puppet'"
+_QA_EXPECTED_LOSS = 7.41
+_QA_TARGET_START_INDEX = 14
+_QA_TARGET_END_INDEX = 15
+
+# SequenceClassification docstring
+_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION = "textattack/bert-base-uncased-yelp-polarity"
+_SEQ_CLASS_EXPECTED_OUTPUT = "'LABEL_1'"
+_SEQ_CLASS_EXPECTED_LOSS = 0.01
+
+
 BERT_PRETRAINED_MODEL_ARCHIVE_LIST = [
     "bert-base-uncased",
     "bert-large-uncased",
@@ -1156,7 +1176,12 @@ class BertLMHeadModel(BertPreTrainedModel):
         self.cls.predictions.decoder = new_embeddings
 
     @add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
-    @replace_return_docstrings(output_type=CausalLMOutputWithCrossAttentions, config_class=_CONFIG_FOR_DOC)
+    @add_code_sample_docstrings(
+        processor_class=_TOKENIZER_FOR_DOC,
+        checkpoint=_CHECKPOINT_FOR_DOC,
+        output_type=CausalLMOutputWithCrossAttentions,
+        config_class=_CONFIG_FOR_DOC,
+    )
     def forward(
         self,
         input_ids: Optional[torch.Tensor] = None,
@@ -1175,49 +1200,28 @@ class BertLMHeadModel(BertPreTrainedModel):
         return_dict: Optional[bool] = None,
     ) -> Union[Tuple[torch.Tensor], CausalLMOutputWithCrossAttentions]:
         r"""
-            encoder_hidden_states  (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
-                Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention
-                if the model is configured as a decoder.
-            encoder_attention_mask (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*):
-                Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used
-                in the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`:
-
-                - 1 for tokens that are **not masked**,
-                - 0 for tokens that are **masked**.
-            labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
-                Labels for computing the left-to-right language modeling loss (next word prediction). Indices should be
-                in `[-100, 0, ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100`
-                are ignored (masked), the loss is only computed for the tokens with labels n `[0, ...,
-                config.vocab_size]`
-            past_key_values (`tuple(tuple(torch.FloatTensor))` of length `config.n_layers` with each tuple having 4 tensors of shape `(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`):
-                Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up
-                decoding.
-
-                If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those
-                that don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of
-                all `decoder_input_ids` of shape `(batch_size, sequence_length)`.
-            use_cache (`bool`, *optional*):
-                If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding
-                (see `past_key_values`).
-
-        Returns:
-
-        Example:
-
-        ```python
-        >>> from transformers import BertTokenizer, BertLMHeadModel, BertConfig
-        >>> import torch
-
-        >>> tokenizer = BertTokenizer.from_pretrained("bert-base-cased")
-        >>> config = BertConfig.from_pretrained("bert-base-cased")
-        >>> config.is_decoder = True
-        >>> model = BertLMHeadModel.from_pretrained("bert-base-cased", config=config)
+        encoder_hidden_states  (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
+            Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if
+            the model is configured as a decoder.
+        encoder_attention_mask (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, *optional*):
+            Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in
+            the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`:
 
-        >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
-        >>> outputs = model(**inputs)
+            - 1 for tokens that are **not masked**,
+            - 0 for tokens that are **masked**.
+        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
+            Labels for computing the left-to-right language modeling loss (next word prediction). Indices should be in
+            `[-100, 0, ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are
+            ignored (masked), the loss is only computed for the tokens with labels n `[0, ..., config.vocab_size]`
+        past_key_values (`tuple(tuple(torch.FloatTensor))` of length `config.n_layers` with each tuple having 4 tensors of shape `(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`):
+            Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding.
 
-        >>> prediction_logits = outputs.logits
-        ```
+            If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that
+            don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of all
+            `decoder_input_ids` of shape `(batch_size, sequence_length)`.
+        use_cache (`bool`, *optional*):
+            If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see
+            `past_key_values`).
         """
         return_dict = return_dict if return_dict is not None else self.config.use_return_dict
         if labels is not None:
@@ -1315,6 +1319,8 @@ class BertForMaskedLM(BertPreTrainedModel):
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=MaskedLMOutput,
         config_class=_CONFIG_FOR_DOC,
+        expected_output="'paris'",
+        expected_loss=0.88,
     )
     def forward(
         self,
@@ -1517,9 +1523,11 @@ class BertForSequenceClassification(BertPreTrainedModel):
     @add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
         processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint=_CHECKPOINT_FOR_DOC,
+        checkpoint=_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION,
         output_type=SequenceClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
+        expected_output=_SEQ_CLASS_EXPECTED_OUTPUT,
+        expected_loss=_SEQ_CLASS_EXPECTED_LOSS,
     )
     def forward(
         self,
@@ -1716,9 +1724,11 @@ class BertForTokenClassification(BertPreTrainedModel):
     @add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
         processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint=_CHECKPOINT_FOR_DOC,
+        checkpoint=_CHECKPOINT_FOR_TOKEN_CLASSIFICATION,
         output_type=TokenClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
+        expected_output=_TOKEN_CLASS_EXPECTED_OUTPUT,
+        expected_loss=_TOKEN_CLASS_EXPECTED_LOSS,
     )
     def forward(
         self,
@@ -1797,9 +1807,13 @@ class BertForQuestionAnswering(BertPreTrainedModel):
     @add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
         processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint=_CHECKPOINT_FOR_DOC,
+        checkpoint=_CHECKPOINT_FOR_QA,
         output_type=QuestionAnsweringModelOutput,
         config_class=_CONFIG_FOR_DOC,
+        qa_target_start_index=_QA_TARGET_START_INDEX,
+        qa_target_end_index=_QA_TARGET_END_INDEX,
+        expected_output=_QA_EXPECTED_OUTPUT,
+        expected_loss=_QA_EXPECTED_LOSS,
     )
     def forward(
         self,

src/transformers/models/bert/modeling_tf_bert.py

@@ -65,10 +65,29 @@ from .configuration_bert import BertConfig
 
 logger = logging.get_logger(__name__)
 
-_CHECKPOINT_FOR_DOC = "bert-base-cased"
+_CHECKPOINT_FOR_DOC = "bert-base-uncased"
 _CONFIG_FOR_DOC = "BertConfig"
 _TOKENIZER_FOR_DOC = "BertTokenizer"
 
+# TokenClassification docstring
+_CHECKPOINT_FOR_TOKEN_CLASSIFICATION = "dbmdz/bert-large-cased-finetuned-conll03-english"
+_TOKEN_CLASS_EXPECTED_OUTPUT = (
+    "['O', 'I-ORG', 'I-ORG', 'I-ORG', 'O', 'O', 'O', 'O', 'O', 'I-LOC', 'O', 'I-LOC', " "'I-LOC'] "
+)
+_TOKEN_CLASS_EXPECTED_LOSS = 0.01
+
+# QuestionAnswering docstring
+_CHECKPOINT_FOR_QA = "ydshieh/bert-base-cased-squad2"
+_QA_EXPECTED_OUTPUT = "'a nice puppet'"
+_QA_EXPECTED_LOSS = 7.41
+_QA_TARGET_START_INDEX = 14
+_QA_TARGET_END_INDEX = 15
+
+# SequenceClassification docstring
+_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION = "ydshieh/bert-base-uncased-yelp-polarity"
+_SEQ_CLASS_EXPECTED_OUTPUT = "'LABEL_1'"
+_SEQ_CLASS_EXPECTED_LOSS = 0.01
+
 TF_BERT_PRETRAINED_MODEL_ARCHIVE_LIST = [
     "bert-base-uncased",
     "bert-large-uncased",
@@ -1197,11 +1216,11 @@ class TFBertForPreTraining(TFBertPreTrainedModel, TFBertPreTrainingLoss):
 
         >>> tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
         >>> model = TFBertForPreTraining.from_pretrained("bert-base-uncased")
-        >>> input_ids = tf.constant(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True))[
-        ...     None, :
-        >>> ]  # Batch size 1
+        >>> input_ids = tokenizer("Hello, my dog is cute", add_special_tokens=True, return_tensors="tf")
+        >>> # Batch size 1
+
         >>> outputs = model(input_ids)
-        >>> prediction_scores, seq_relationship_scores = outputs[:2]
+        >>> prediction_logits, seq_relationship_logits = outputs[:2]
         ```"""
         outputs = self.bert(
             input_ids=input_ids,
@@ -1285,6 +1304,8 @@ class TFBertForMaskedLM(TFBertPreTrainedModel, TFMaskedLanguageModelingLoss):
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=TFMaskedLMOutput,
         config_class=_CONFIG_FOR_DOC,
+        expected_output="'paris'",
+        expected_loss=0.88,
     )
     def call(
         self,
@@ -1606,9 +1627,11 @@ class TFBertForSequenceClassification(TFBertPreTrainedModel, TFSequenceClassific
     @add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
         processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint=_CHECKPOINT_FOR_DOC,
+        checkpoint=_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION,
         output_type=TFSequenceClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
+        expected_output=_SEQ_CLASS_EXPECTED_OUTPUT,
+        expected_loss=_SEQ_CLASS_EXPECTED_LOSS,
     )
     def call(
         self,
@@ -1833,9 +1856,11 @@ class TFBertForTokenClassification(TFBertPreTrainedModel, TFTokenClassificationL
     @add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
         processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint=_CHECKPOINT_FOR_DOC,
+        checkpoint=_CHECKPOINT_FOR_TOKEN_CLASSIFICATION,
         output_type=TFTokenClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
+        expected_output=_TOKEN_CLASS_EXPECTED_OUTPUT,
+        expected_loss=_TOKEN_CLASS_EXPECTED_LOSS,
     )
     def call(
         self,
@@ -1923,9 +1948,11 @@ class TFBertForQuestionAnswering(TFBertPreTrainedModel, TFQuestionAnsweringLoss)
     @add_start_docstrings_to_model_forward(BERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
         processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint=_CHECKPOINT_FOR_DOC,
+        checkpoint=_CHECKPOINT_FOR_QA,
         output_type=TFQuestionAnsweringModelOutput,
         config_class=_CONFIG_FOR_DOC,
+        expected_output=_QA_EXPECTED_OUTPUT,
+        expected_loss=_QA_EXPECTED_LOSS,
     )
     def call(
         self,

src/transformers/models/mobilebert/modeling_mobilebert.py

@@ -59,6 +59,23 @@ _CHECKPOINT_FOR_DOC = "google/mobilebert-uncased"
 _CONFIG_FOR_DOC = "MobileBertConfig"
 _TOKENIZER_FOR_DOC = "MobileBertTokenizer"
 
+# TokenClassification docstring
+_CHECKPOINT_FOR_TOKEN_CLASSIFICATION = "mrm8488/mobilebert-finetuned-ner"
+_TOKEN_CLASS_EXPECTED_OUTPUT = "['I-ORG', 'I-ORG', 'O', 'O', 'O', 'O', 'O', 'I-LOC', 'O', 'I-LOC', 'I-LOC']"
+_TOKEN_CLASS_EXPECTED_LOSS = 0.03
+
+# QuestionAnswering docstring
+_CHECKPOINT_FOR_QA = "csarron/mobilebert-uncased-squad-v2"
+_QA_EXPECTED_OUTPUT = "'a nice puppet'"
+_QA_EXPECTED_LOSS = 3.98
+_QA_TARGET_START_INDEX = 12
+_QA_TARGET_END_INDEX = 13
+
+# SequenceClassification docstring
+_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION = "lordtt13/emo-mobilebert"
+_SEQ_CLASS_EXPECTED_OUTPUT = "'others'"
+_SEQ_CLASS_EXPECTED_LOSS = "4.72"
+
 MOBILEBERT_PRETRAINED_MODEL_ARCHIVE_LIST = ["google/mobilebert-uncased"]
 
 
@@ -962,9 +979,8 @@ class MobileBertForPreTraining(MobileBertPreTrainedModel):
         >>> tokenizer = MobileBertTokenizer.from_pretrained("google/mobilebert-uncased")
         >>> model = MobileBertForPreTraining.from_pretrained("google/mobilebert-uncased")
 
-        >>> input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True)).unsqueeze(
-        ...     0
-        >>> )  # Batch size 1
+        >>> input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True)).unsqueeze(0)
+        >>> # Batch size 1
         >>> outputs = model(input_ids)
 
         >>> prediction_logits = outputs.prediction_logits
@@ -1039,6 +1055,8 @@ class MobileBertForMaskedLM(MobileBertPreTrainedModel):
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=MaskedLMOutput,
         config_class=_CONFIG_FOR_DOC,
+        expected_output="'paris'",
+        expected_loss=0.57,
     )
     def forward(
         self,
@@ -1229,9 +1247,11 @@ class MobileBertForSequenceClassification(MobileBertPreTrainedModel):
     @add_start_docstrings_to_model_forward(MOBILEBERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
         processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint=_CHECKPOINT_FOR_DOC,
+        checkpoint=_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION,
         output_type=SequenceClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
+        expected_output=_SEQ_CLASS_EXPECTED_OUTPUT,
+        expected_loss=_SEQ_CLASS_EXPECTED_LOSS,
     )
     def forward(
         self,
@@ -1330,9 +1350,13 @@ class MobileBertForQuestionAnswering(MobileBertPreTrainedModel):
     @add_start_docstrings_to_model_forward(MOBILEBERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
         processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint=_CHECKPOINT_FOR_DOC,
+        checkpoint=_CHECKPOINT_FOR_QA,
         output_type=QuestionAnsweringModelOutput,
         config_class=_CONFIG_FOR_DOC,
+        qa_target_start_index=_QA_TARGET_START_INDEX,
+        qa_target_end_index=_QA_TARGET_END_INDEX,
+        expected_output=_QA_EXPECTED_OUTPUT,
+        expected_loss=_QA_EXPECTED_LOSS,
     )
     def forward(
         self,
@@ -1536,9 +1560,11 @@ class MobileBertForTokenClassification(MobileBertPreTrainedModel):
     @add_start_docstrings_to_model_forward(MOBILEBERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
         processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint=_CHECKPOINT_FOR_DOC,
+        checkpoint=_CHECKPOINT_FOR_TOKEN_CLASSIFICATION,
         output_type=TokenClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
+        expected_output=_TOKEN_CLASS_EXPECTED_OUTPUT,
+        expected_loss=_TOKEN_CLASS_EXPECTED_LOSS,
     )
     def forward(
         self,

src/transformers/models/mobilebert/modeling_tf_mobilebert.py

@@ -63,6 +63,23 @@ _CHECKPOINT_FOR_DOC = "google/mobilebert-uncased"
 _CONFIG_FOR_DOC = "MobileBertConfig"
 _TOKENIZER_FOR_DOC = "MobileBertTokenizer"
 
+# TokenClassification docstring
+_CHECKPOINT_FOR_TOKEN_CLASSIFICATION = "vumichien/mobilebert-finetuned-ner"
+_TOKEN_CLASS_EXPECTED_OUTPUT = "['I-ORG', 'I-ORG', 'O', 'O', 'O', 'O', 'O', 'I-LOC', 'O', 'I-LOC', 'I-LOC']"
+_TOKEN_CLASS_EXPECTED_LOSS = 0.03
+
+# QuestionAnswering docstring
+_CHECKPOINT_FOR_QA = "vumichien/mobilebert-uncased-squad-v2"
+_QA_EXPECTED_OUTPUT = "'a nice puppet'"
+_QA_EXPECTED_LOSS = 3.98
+_QA_TARGET_START_INDEX = 12
+_QA_TARGET_END_INDEX = 13
+
+# SequenceClassification docstring
+_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION = "vumichien/emo-mobilebert"
+_SEQ_CLASS_EXPECTED_OUTPUT = "'others'"
+_SEQ_CLASS_EXPECTED_LOSS = "4.72"
+
 TF_MOBILEBERT_PRETRAINED_MODEL_ARCHIVE_LIST = [
     "google/mobilebert-uncased",
     # See all MobileBERT models at https://huggingface.co/models?filter=mobilebert
@@ -1075,6 +1092,8 @@ class TFMobileBertForMaskedLM(TFMobileBertPreTrainedModel, TFMaskedLanguageModel
         checkpoint=_CHECKPOINT_FOR_DOC,
         output_type=TFMaskedLMOutput,
         config_class=_CONFIG_FOR_DOC,
+        expected_output="'paris'",
+        expected_loss=0.57,
     )
     def call(
         self,
@@ -1265,9 +1284,11 @@ class TFMobileBertForSequenceClassification(TFMobileBertPreTrainedModel, TFSeque
     @add_start_docstrings_to_model_forward(MOBILEBERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
         processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint=_CHECKPOINT_FOR_DOC,
+        checkpoint=_CHECKPOINT_FOR_SEQUENCE_CLASSIFICATION,
         output_type=TFSequenceClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
+        expected_output=_SEQ_CLASS_EXPECTED_OUTPUT,
+        expected_loss=_SEQ_CLASS_EXPECTED_LOSS,
     )
     def call(
         self,
@@ -1357,9 +1378,13 @@ class TFMobileBertForQuestionAnswering(TFMobileBertPreTrainedModel, TFQuestionAn
     @add_start_docstrings_to_model_forward(MOBILEBERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
         processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint=_CHECKPOINT_FOR_DOC,
+        checkpoint=_CHECKPOINT_FOR_QA,
         output_type=TFQuestionAnsweringModelOutput,
         config_class=_CONFIG_FOR_DOC,
+        qa_target_start_index=_QA_TARGET_START_INDEX,
+        qa_target_end_index=_QA_TARGET_END_INDEX,
+        expected_output=_QA_EXPECTED_OUTPUT,
+        expected_loss=_QA_EXPECTED_LOSS,
     )
     def call(
         self,
@@ -1601,9 +1626,11 @@ class TFMobileBertForTokenClassification(TFMobileBertPreTrainedModel, TFTokenCla
     @add_start_docstrings_to_model_forward(MOBILEBERT_INPUTS_DOCSTRING.format("batch_size, sequence_length"))
     @add_code_sample_docstrings(
         processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint=_CHECKPOINT_FOR_DOC,
+        checkpoint=_CHECKPOINT_FOR_TOKEN_CLASSIFICATION,
         output_type=TFTokenClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
+        expected_output=_TOKEN_CLASS_EXPECTED_OUTPUT,
+        expected_loss=_TOKEN_CLASS_EXPECTED_LOSS,
     )
     def call(
         self,

utils/documentation_tests.txt

@@ -5,6 +5,8 @@ docs/source/en/model_doc/tapex.mdx
 src/transformers/generation_utils.py
 src/transformers/models/bart/modeling_bart.py
 src/transformers/models/beit/modeling_beit.py
+src/transformers/models/bert/modeling_bert.py
+src/transformers/models/bert/modeling_tf_bert.py
 src/transformers/models/bigbird_pegasus/modeling_bigbird_pegasus.py
 src/transformers/models/blenderbot/modeling_blenderbot.py
 src/transformers/models/blenderbot_small/modeling_blenderbot_small.py
@@ -16,6 +18,8 @@ src/transformers/models/glpn/modeling_glpn.py
 src/transformers/models/hubert/modeling_hubert.py
 src/transformers/models/marian/modeling_marian.py
 src/transformers/models/mbart/modeling_mbart.py
+src/transformers/models/mobilebert/modeling_mobilebert.py
+src/transformers/models/mobilebert/modeling_tf_mobilebert.py
 src/transformers/models/pegasus/modeling_pegasus.py
 src/transformers/models/plbart/modeling_plbart.py
 src/transformers/models/poolformer/modeling_poolformer.py