[ci] fix 3 remaining slow GPU failures (#4584)

src/transformers/configuration_distilbert.py

@@ -73,10 +73,10 @@ class DistilBertConfig(PretrainedConfig):
                 The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
             qa_dropout (:obj:`float`, optional, defaults to 0.1):
                 The dropout probabilities used in the question answering model
-                :class:`~tranformers.DistilBertForQuestionAnswering`.
+                :class:`~transformers.DistilBertForQuestionAnswering`.
             seq_classif_dropout (:obj:`float`, optional, defaults to 0.2):
                 The dropout probabilities used in the sequence classification model
-                :class:`~tranformers.DistilBertForSequenceClassification`.
+                :class:`~transformers.DistilBertForSequenceClassification`.
 
         Example::
 

src/transformers/modeling_encoder_decoder.py

@@ -125,7 +125,7 @@ class EncoderDecoderModel(PreTrainedModel):
 
         Examples::
 
-            from tranformers import EncoderDecoder
+            from transformers import EncoderDecoder
 
             model = EncoderDecoder.from_encoder_decoder_pretrained('bert-base-uncased', 'bert-base-uncased') # initialize Bert2Bert
         """