Add Doc Test GPT-2 (#16439)

* First Pass All Tests Pass

* WIP

* Adding file to documentation tests

* Change the base model for the example in the doc test.

* Fix Code Styling by running
make fixup

* Called Style

* Reverted to gpt2 model rather than distill gpt2
Then used a token classification model over a sequence model for an example.

* Fix Styling Issue

* Hopefully ignores the formatting issue.
Co-authored-by: ArEnSc <xx.mike.chung.xx@gmail.com>

src/transformers/models/gpt2/modeling_gpt2.py

@@ -1231,10 +1231,8 @@ class GPT2DoubleHeadsModel(GPT2PreTrainedModel):
 
         >>> # Add a [CLS] to the vocabulary (we should train it also!)
         >>> num_added_tokens = tokenizer.add_special_tokens({"cls_token": "[CLS]"})
-
-        >>> embedding_layer = model.resize_token_embeddings(
-        ...     len(tokenizer)
-        >>> )  # Update the model embeddings with the new vocabulary size
+        >>> # Update the model embeddings with the new vocabulary size
+        >>> embedding_layer = model.resize_token_embeddings(len(tokenizer))
 
         >>> choices = ["Hello, my dog is cute [CLS]", "Hello, my cat is cute [CLS]"]
         >>> encoded_choices = [tokenizer.encode(s) for s in choices]
@@ -1350,6 +1348,8 @@ class GPT2ForSequenceClassification(GPT2PreTrainedModel):
         checkpoint="microsoft/DialogRPT-updown",
         output_type=SequenceClassifierOutputWithPast,
         config_class=_CONFIG_FOR_DOC,
+        expected_output="'LABEL_0'",
+        expected_loss=5.28,
     )
     def forward(
         self,
@@ -1477,12 +1477,16 @@ class GPT2ForTokenClassification(GPT2PreTrainedModel):
         self.post_init()
 
     @add_start_docstrings_to_model_forward(GPT2_INPUTS_DOCSTRING)
+    # fmt: off
     @add_code_sample_docstrings(
         processor_class=_TOKENIZER_FOR_DOC,
-        checkpoint="microsoft/DialogRPT-updown",
+        checkpoint="brad1141/gpt2-finetuned-comp2",
         output_type=TokenClassifierOutput,
         config_class=_CONFIG_FOR_DOC,
+        expected_loss=0.25,
+        expected_output=["Lead", "Lead", "Lead", "Position", "Lead", "Lead", "Lead", "Lead", "Lead", "Lead", "Lead", "Lead"],
     )
+    # fmt: on
     def forward(
         self,
         input_ids=None,

utils/documentation_tests.txt

@@ -15,6 +15,7 @@ src/transformers/models/data2vec/modeling_data2vec_audio.py
 src/transformers/models/deit/modeling_deit.py
 src/transformers/models/dpt/modeling_dpt.py
 src/transformers/models/glpn/modeling_glpn.py
+src/transformers/models/gpt2/modeling_gpt2.py
 src/transformers/models/hubert/modeling_hubert.py
 src/transformers/models/marian/modeling_marian.py
 src/transformers/models/mbart/modeling_mbart.py