TF OpenAI GPT

src/transformers/modeling_tf_bert.py

@@ -660,6 +660,13 @@ BERT_INPUTS_DOCSTRING = r"""
     BERT_START_DOCSTRING,
 )
 class TFBertModel(TFBertPreTrainedModel):
+
+    def __init__(self, config, *inputs, **kwargs):
+        super().__init__(config, *inputs, **kwargs)
+        self.bert = TFBertMainLayer(config, name="bert")
+
+    @add_start_docstrings_to_callable(BERT_INPUTS_DOCSTRING)
+    def call(self, inputs, **kwargs):
         r"""
         Returns:
             :obj:`tuple(tf.Tensor)` comprising various elements depending on the configuration (:class:`~transformers.BertConfig`) and inputs:
@@ -693,15 +700,7 @@ class TFBertModel(TFBertPreTrainedModel):
             input_ids = tf.constant(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True))[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
-
         """
-
-    def __init__(self, config, *inputs, **kwargs):
-        super().__init__(config, *inputs, **kwargs)
-        self.bert = TFBertMainLayer(config, name="bert")
-
-    @add_start_docstrings_to_callable(BERT_INPUTS_DOCSTRING)
-    def call(self, inputs, **kwargs):
         outputs = self.bert(inputs, **kwargs)
         return outputs
 

src/transformers/modeling_tf_gpt2.py

@@ -433,6 +433,9 @@ GPT2_INPUTS_DOCSTRING = r"""
             Optionally, instead of passing :obj:`input_ids` you can choose to directly pass an embedded representation.
             This is useful if you want more control over how to convert `input_ids` indices into associated vectors
             than the model's internal embedding lookup matrix.
+        training (:obj:`boolean`, `optional`, defaults to :obj:`False`):
+            Whether to activate dropout modules (if set to :obj:`True`) during training or to de-activate them
+            (if set to :obj:`False`) for evaluation.
 """