tiny fixes

README.md

@@ -288,7 +288,7 @@ This is the model provided as `bert-large-uncased-whole-word-masking-finetuned-s
 ### `run_generation.py`: Text generation with GPT, GPT-2, Transformer-XL and XLNet
 
 A conditional generation script is also included to generate text from a prompt.
-The generation script includes the [tricks](https://github.com/rusiaaman/XLNet-gen#methodology) proposed by by Aman Rusia to get high quality generation with memory models like Transformer-XL and XLNet (include a predefined text to make short inputs longer).
+The generation script includes the [tricks](https://github.com/rusiaaman/XLNet-gen#methodology) proposed by Aman Rusia to get high quality generation with memory models like Transformer-XL and XLNet (include a predefined text to make short inputs longer).
 
 Here is how to run the script with the small version of OpenAI GPT-2 model:
 

pytorch_transformers/modeling_bert.py

@@ -527,7 +527,7 @@ BERT_INPUTS_DOCSTRING = r"""
             ``1`` indicates the head is **not masked**, ``0`` indicates the head is **masked**.
 """
 
-@add_start_docstrings("The bare Bert Model transformer outputing raw hidden-states without any specific head on top.",
+@add_start_docstrings("The bare Bert Model transformer outputting raw hidden-states without any specific head on top.",
                       BERT_START_DOCSTRING, BERT_INPUTS_DOCSTRING)
 class BertModel(BertPreTrainedModel):
     r"""

pytorch_transformers/modeling_distilbert.py

@@ -394,7 +394,7 @@ DISTILBERT_INPUTS_DOCSTRING = r"""
             ``1`` indicates the head is **not masked**, ``0`` indicates the head is **masked**.
 """
 
-@add_start_docstrings("The bare DistilBERT encoder/transformer outputing raw hidden-states without any specific head on top.",
+@add_start_docstrings("The bare DistilBERT encoder/transformer outputting raw hidden-states without any specific head on top.",
                       DISTILBERT_START_DOCSTRING, DISTILBERT_INPUTS_DOCSTRING)
 class DistilBertModel(DistilBertPreTrainedModel):
     r"""

pytorch_transformers/modeling_gpt2.py

@@ -314,7 +314,7 @@ GPT2_INPUTS_DOCSTRING = r"""    Inputs:
             ``1`` indicates the head is **not masked**, ``0`` indicates the head is **masked**.
 """
 
-@add_start_docstrings("The bare GPT2 Model transformer outputing raw hidden-states without any specific head on top.",
+@add_start_docstrings("The bare GPT2 Model transformer outputting raw hidden-states without any specific head on top.",
                       GPT2_START_DOCSTRING, GPT2_INPUTS_DOCSTRING)
 class GPT2Model(GPT2PreTrainedModel):
     r"""

pytorch_transformers/modeling_openai.py

@@ -324,7 +324,7 @@ OPENAI_GPT_INPUTS_DOCSTRING = r"""    Inputs:
             ``1`` indicates the head is **not masked**, ``0`` indicates the head is **masked**.
 """
 
-@add_start_docstrings("The bare OpenAI GPT transformer model outputing raw hidden-states without any specific head on top.",
+@add_start_docstrings("The bare OpenAI GPT transformer model outputting raw hidden-states without any specific head on top.",
                       OPENAI_GPT_START_DOCSTRING, OPENAI_GPT_INPUTS_DOCSTRING)
 class OpenAIGPTModel(OpenAIGPTPreTrainedModel):
     r"""

pytorch_transformers/modeling_roberta.py

@@ -124,7 +124,7 @@ ROBERTA_INPUTS_DOCSTRING = r"""
             ``1`` indicates the head is **not masked**, ``0`` indicates the head is **masked**.
 """
 
-@add_start_docstrings("The bare RoBERTa Model transformer outputing raw hidden-states without any specific head on top.",
+@add_start_docstrings("The bare RoBERTa Model transformer outputting raw hidden-states without any specific head on top.",
                       ROBERTA_START_DOCSTRING, ROBERTA_INPUTS_DOCSTRING)
 class RobertaModel(BertModel):
     r"""

pytorch_transformers/modeling_transfo_xl.py

@@ -820,7 +820,7 @@ TRANSFO_XL_INPUTS_DOCSTRING = r"""
             ``1`` indicates the head is **not masked**, ``0`` indicates the head is **masked**.
 """
 
-@add_start_docstrings("The bare Bert Model transformer outputing raw hidden-states without any specific head on top.",
+@add_start_docstrings("The bare Bert Model transformer outputting raw hidden-states without any specific head on top.",
                       TRANSFO_XL_START_DOCSTRING, TRANSFO_XL_INPUTS_DOCSTRING)
 class TransfoXLModel(TransfoXLPreTrainedModel):
     r"""

pytorch_transformers/modeling_xlm.py

@@ -313,7 +313,7 @@ XLM_INPUTS_DOCSTRING = r"""
             ``1`` indicates the head is **not masked**, ``0`` indicates the head is **masked**.
 """
 
-@add_start_docstrings("The bare XLM Model transformer outputing raw hidden-states without any specific head on top.",
+@add_start_docstrings("The bare XLM Model transformer outputting raw hidden-states without any specific head on top.",
                       XLM_START_DOCSTRING, XLM_INPUTS_DOCSTRING)
 class XLMModel(XLMPreTrainedModel):
     r"""

pytorch_transformers/modeling_xlnet.py

@@ -546,7 +546,7 @@ XLNET_INPUTS_DOCSTRING = r"""
             ``1`` indicates the head is **not masked**, ``0`` indicates the head is **masked**.
 """
 
-@add_start_docstrings("The bare XLNet Model transformer outputing raw hidden-states without any specific head on top.",
+@add_start_docstrings("The bare XLNet Model transformer outputting raw hidden-states without any specific head on top.",
                       XLNET_START_DOCSTRING, XLNET_INPUTS_DOCSTRING)
 class XLNetModel(XLNetPreTrainedModel):
     r"""