Removed `attention_mask` from GPT-2 and GPT documentation. Corrected...

Removed `attention_mask` from GPT-2 and GPT documentation. Corrected `multiple_choice_labels` to actual name `mc_labels`

pytorch_transformers/modeling_gpt2.py

@@ -408,10 +408,6 @@ GPT2_INPUTS_DOCSTRING = r"""    Inputs:
             list of ``torch.FloatTensor`` (one for each layer):
             that contains pre-computed hidden-states (key and values in the attention blocks) as computed by the model
             (see `past` output below). Can be used to speed up sequential decoding.
-        **attention_mask**: (`optional`) ``torch.FloatTensor`` of shape ``(batch_size, sequence_length)``:
-            Mask to avoid performing attention on padding token indices.
-            Mask values selected in ``[0, 1]``:
-            ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
         **head_mask**: (`optional`) ``torch.FloatTensor`` of shape ``(num_heads,)`` or ``(num_layers, num_heads)``:
             Mask to nullify selected heads of the self-attention modules.
             Mask values selected in ``[0, 1]``:
@@ -642,10 +638,6 @@ class GPT2DoubleHeadsModel(GPT2PreTrainedModel):
             list of ``torch.FloatTensor`` (one for each layer):
             that contains pre-computed hidden-states (key and values in the attention blocks) as computed by the model
             (see `past` output below). Can be used to speed up sequential decoding.
-        **attention_mask**: (`optional`) ``torch.FloatTensor`` of shape ``(batch_size, num_choices, sequence_length)``:
-            Mask to avoid performing attention on padding token indices.
-            Mask values selected in ``[0, 1]``:
-            ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
         **head_mask**: (`optional`) ``torch.FloatTensor`` of shape ``(num_heads,)`` or ``(num_layers, num_heads)``:
             Mask to nullify selected heads of the self-attention modules.
             Mask values selected in ``[0, 1]``:
@@ -656,7 +648,7 @@ class GPT2DoubleHeadsModel(GPT2PreTrainedModel):
             Indices are selected in ``[-1, 0, ..., config.vocab_size]``
             All labels set to ``-1`` are ignored (masked), the loss is only
             computed for labels in ``[0, ..., config.vocab_size]``
-        **multiple_choice_labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size)``:
+        **mc_labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size)``:
             Labels for computing the multiple choice classification loss.
             Indices should be in ``[0, ..., num_choices]`` where `num_choices` is the size of the second dimension
             of the input tensors. (see `input_ids` above)

pytorch_transformers/modeling_openai.py

@@ -415,11 +415,7 @@ OPENAI_GPT_INPUTS_DOCSTRING = r"""    Inputs:
         **token_type_ids**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``:
             A parallel sequence of tokens (can be used to indicate various portions of the inputs).
             The embeddings from these tokens will be summed with the respective token embeddings.
-            Indices are selected in the vocabulary (unlike BERT which has a specific vocabulary for segment indices).
-        **attention_mask**: (`optional`) ``torch.FloatTensor`` of shape ``(batch_size, sequence_length)``:
-            Mask to avoid performing attention on padding token indices.
-            Mask values selected in ``[0, 1]``:
-            ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
+            Indices are selected in the vocabulary (unlike BERT which has a specific vocabulary for segment indices)
         **head_mask**: (`optional`) ``torch.FloatTensor`` of shape ``(num_heads,)`` or ``(num_layers, num_heads)``:
             Mask to nullify selected heads of the self-attention modules.
             Mask values selected in ``[0, 1]``:
@@ -626,10 +622,6 @@ class OpenAIGPTDoubleHeadsModel(OpenAIGPTPreTrainedModel):
             A parallel sequence of tokens (can be used to indicate various portions of the inputs).
             The embeddings from these tokens will be summed with the respective token embeddings.
             Indices are selected in the vocabulary (unlike BERT which has a specific vocabulary for segment indices).
-        **attention_mask**: (`optional`) ``torch.FloatTensor`` of shape ``(batch_size, num_choices, sequence_length)``:
-            Mask to avoid performing attention on padding token indices.
-            Mask values selected in ``[0, 1]``:
-            ``1`` for tokens that are NOT MASKED, ``0`` for MASKED tokens.
         **head_mask**: (`optional`) ``torch.FloatTensor`` of shape ``(num_heads,)`` or ``(num_layers, num_heads)``:
             Mask to nullify selected heads of the self-attention modules.
             Mask values selected in ``[0, 1]``:
@@ -640,7 +632,7 @@ class OpenAIGPTDoubleHeadsModel(OpenAIGPTPreTrainedModel):
             Indices are selected in ``[-1, 0, ..., config.vocab_size]``
             All labels set to ``-1`` are ignored (masked), the loss is only
             computed for labels in ``[0, ..., config.vocab_size]``
-        **multiple_choice_labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size)``:
+        **mc_labels**: (`optional`) ``torch.LongTensor`` of shape ``(batch_size)``:
             Labels for computing the multiple choice classification loss.
             Indices should be in ``[0, ..., num_choices]`` where `num_choices` is the size of the second dimension
             of the input tensors. (see `input_ids` above)