[BIG] pytorch-transformers => transformers

pytorch_transformers/convert_bert_original_tf_checkpoint_to_pytorch.py → transformers/convert_bert_original_tf_checkpoint_to_pytorch.py

@@ -21,7 +21,7 @@ from __future__ import print_function
 import argparse
 import torch
 
-from pytorch_transformers import BertConfig, BertForPreTraining, load_tf_weights_in_bert
+from transformers import BertConfig, BertForPreTraining, load_tf_weights_in_bert
 
 import logging
 logging.basicConfig(level=logging.INFO)

pytorch_transformers/convert_bert_pytorch_checkpoint_to_original_tf.py → transformers/convert_bert_pytorch_checkpoint_to_original_tf.py

@@ -20,7 +20,7 @@ import argparse
 import torch
 import numpy as np
 import tensorflow as tf
-from pytorch_transformers import BertModel
+from transformers import BertModel
 
 
 def convert_pytorch_checkpoint_to_tf(model:BertModel, ckpt_dir:str, model_name:str):

pytorch_transformers/convert_gpt2_original_tf_checkpoint_to_pytorch.py → transformers/convert_gpt2_original_tf_checkpoint_to_pytorch.py

@@ -21,7 +21,7 @@ from io import open
 
 import torch
 
-from pytorch_transformers import (CONFIG_NAME, WEIGHTS_NAME,
+from transformers import (CONFIG_NAME, WEIGHTS_NAME,
                                                      GPT2Config,
                                                      GPT2Model,
                                                      load_tf_weights_in_gpt2)

pytorch_transformers/convert_openai_original_tf_checkpoint_to_pytorch.py → transformers/convert_openai_original_tf_checkpoint_to_pytorch.py

@@ -21,7 +21,7 @@ from io import open
 
 import torch
 
-from pytorch_transformers import (CONFIG_NAME, WEIGHTS_NAME,
+from transformers import (CONFIG_NAME, WEIGHTS_NAME,
                                                      OpenAIGPTConfig,
                                                      OpenAIGPTModel,
                                                      load_tf_weights_in_openai_gpt)

pytorch_transformers/convert_pytorch_checkpoint_to_tf2.py → transformers/convert_pytorch_checkpoint_to_tf2.py

@@ -22,9 +22,9 @@ import os
 import argparse
 import tensorflow as tf
 
-from pytorch_transformers import is_torch_available, cached_path
+from transformers import is_torch_available, cached_path
 
-from pytorch_transformers import (BertConfig, TFBertForPreTraining, TFBertForQuestionAnswering, TFBertForSequenceClassification, load_bert_pt_weights_in_tf2, BERT_PRETRAINED_CONFIG_ARCHIVE_MAP,
+from transformers import (BertConfig, TFBertForPreTraining, TFBertForQuestionAnswering, TFBertForSequenceClassification, load_bert_pt_weights_in_tf2, BERT_PRETRAINED_CONFIG_ARCHIVE_MAP,
                                   GPT2Config, TFGPT2LMHeadModel, load_gpt2_pt_weights_in_tf2, GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP,
                                   XLNetConfig, TFXLNetLMHeadModel, load_xlnet_pt_weights_in_tf2, XLNET_PRETRAINED_CONFIG_ARCHIVE_MAP,
                                   XLMConfig, TFXLMWithLMHeadModel, load_xlm_pt_weights_in_tf2, XLM_PRETRAINED_CONFIG_ARCHIVE_MAP,
@@ -36,7 +36,7 @@ from pytorch_transformers import (BertConfig, TFBertForPreTraining, TFBertForQue
 if is_torch_available():
     import torch
     import numpy as np
-    from pytorch_transformers import (BertForPreTraining, BertForQuestionAnswering, BertForSequenceClassification, BERT_PRETRAINED_MODEL_ARCHIVE_MAP,
+    from transformers import (BertForPreTraining, BertForQuestionAnswering, BertForSequenceClassification, BERT_PRETRAINED_MODEL_ARCHIVE_MAP,
                                       GPT2LMHeadModel, GPT2_PRETRAINED_MODEL_ARCHIVE_MAP,
                                       XLNetLMHeadModel, XLNET_PRETRAINED_MODEL_ARCHIVE_MAP,
                                       XLMWithLMHeadModel, XLM_PRETRAINED_MODEL_ARCHIVE_MAP,

pytorch_transformers/convert_roberta_original_pytorch_checkpoint_to_pytorch.py → transformers/convert_roberta_original_pytorch_checkpoint_to_pytorch.py

@@ -23,12 +23,12 @@ import torch
 
 from fairseq.models.roberta import RobertaModel as FairseqRobertaModel
 from fairseq.modules import TransformerSentenceEncoderLayer
-from pytorch_transformers import (BertConfig, BertEncoder,
+from transformers import (BertConfig, BertEncoder,
                                                 BertIntermediate, BertLayer,
                                                 BertModel, BertOutput,
                                                 BertSelfAttention,
                                                 BertSelfOutput)
-from pytorch_transformers import (RobertaEmbeddings,
+from transformers import (RobertaEmbeddings,
                                                    RobertaForMaskedLM,
                                                    RobertaForSequenceClassification,
                                                    RobertaModel)

pytorch_transformers/convert_transfo_xl_original_tf_checkpoint_to_pytorch.py → transformers/convert_transfo_xl_original_tf_checkpoint_to_pytorch.py

@@ -23,12 +23,12 @@ from io import open
 
 import torch
 
-import pytorch_transformers.tokenization_transfo_xl as data_utils
+import transformers.tokenization_transfo_xl as data_utils
 
-from pytorch_transformers import CONFIG_NAME, WEIGHTS_NAME
-from pytorch_transformers import (TransfoXLConfig, TransfoXLLMHeadModel,
+from transformers import CONFIG_NAME, WEIGHTS_NAME
+from transformers import (TransfoXLConfig, TransfoXLLMHeadModel,
                                                       load_tf_weights_in_transfo_xl)
-from pytorch_transformers.tokenization_transfo_xl import (CORPUS_NAME, VOCAB_FILES_NAMES)
+from transformers.tokenization_transfo_xl import (CORPUS_NAME, VOCAB_FILES_NAMES)
 
 if sys.version_info[0] == 2:
     import cPickle as pickle

pytorch_transformers/convert_xlm_original_pytorch_checkpoint_to_pytorch.py → transformers/convert_xlm_original_pytorch_checkpoint_to_pytorch.py

@@ -23,8 +23,8 @@ from io import open
 import torch
 import numpy
 
-from pytorch_transformers import CONFIG_NAME, WEIGHTS_NAME
-from pytorch_transformers.tokenization_xlm import VOCAB_FILES_NAMES
+from transformers import CONFIG_NAME, WEIGHTS_NAME
+from transformers.tokenization_xlm import VOCAB_FILES_NAMES
 
 import logging
 logging.basicConfig(level=logging.INFO)

pytorch_transformers/convert_xlnet_original_tf_checkpoint_to_pytorch.py → transformers/convert_xlnet_original_tf_checkpoint_to_pytorch.py

@@ -22,7 +22,7 @@ import os
 import argparse
 import torch
 
-from pytorch_transformers import (CONFIG_NAME, WEIGHTS_NAME,
+from transformers import (CONFIG_NAME, WEIGHTS_NAME,
                                                     XLNetConfig,
                                                     XLNetLMHeadModel, XLNetForQuestionAnswering,
                                                     XLNetForSequenceClassification,

pytorch_transformers/file_utils.py → transformers/file_utils.py

@@ -48,7 +48,7 @@ except ImportError:
     torch_cache_home = os.path.expanduser(
         os.getenv('TORCH_HOME', os.path.join(
             os.getenv('XDG_CACHE_HOME', '~/.cache'), 'torch')))
-default_cache_path = os.path.join(torch_cache_home, 'pytorch_transformers')
+default_cache_path = os.path.join(torch_cache_home, 'transformers')
 
 try:
     from urllib.parse import urlparse
@@ -65,6 +65,7 @@ except (AttributeError, ImportError):
                                                         default_cache_path))
 
 PYTORCH_TRANSFORMERS_CACHE = PYTORCH_PRETRAINED_BERT_CACHE  # Kept for backward compatibility
+TRANSFORMERS_CACHE = PYTORCH_PRETRAINED_BERT_CACHE  # Kept for backward compatibility
 
 WEIGHTS_NAME = "pytorch_model.bin"
 TF2_WEIGHTS_NAME = 'tf_model.h5'
@@ -131,7 +132,7 @@ def filename_to_url(filename, cache_dir=None):
     Raise ``EnvironmentError`` if `filename` or its stored metadata do not exist.
     """
     if cache_dir is None:
-        cache_dir = PYTORCH_TRANSFORMERS_CACHE
+        cache_dir = TRANSFORMERS_CACHE
     if sys.version_info[0] == 3 and isinstance(cache_dir, Path):
         cache_dir = str(cache_dir)
 
@@ -162,7 +163,7 @@ def cached_path(url_or_filename, cache_dir=None, force_download=False, proxies=N
         force_download: if True, re-dowload the file even if it's already cached in the cache dir.
     """
     if cache_dir is None:
-        cache_dir = PYTORCH_TRANSFORMERS_CACHE
+        cache_dir = TRANSFORMERS_CACHE
     if sys.version_info[0] == 3 and isinstance(url_or_filename, Path):
         url_or_filename = str(url_or_filename)
     if sys.version_info[0] == 3 and isinstance(cache_dir, Path):
@@ -251,7 +252,7 @@ def get_from_cache(url, cache_dir=None, force_download=False, proxies=None):
     If it's not there, download it. Then return the path to the cached file.
     """
     if cache_dir is None:
-        cache_dir = PYTORCH_TRANSFORMERS_CACHE
+        cache_dir = TRANSFORMERS_CACHE
     if sys.version_info[0] == 3 and isinstance(cache_dir, Path):
         cache_dir = str(cache_dir)
     if sys.version_info[0] == 2 and not isinstance(cache_dir, str):

pytorch_transformers/modeling_auto.py → transformers/modeling_auto.py

@@ -36,7 +36,7 @@ logger = logging.getLogger(__name__)
 
 class AutoModel(object):
     r"""
-        :class:`~pytorch_transformers.AutoModel` is a generic model class
+        :class:`~transformers.AutoModel` is a generic model class
         that will be instantiated as one of the base model classes of the library
         when created with the `AutoModel.from_pretrained(pretrained_model_name_or_path)`
         class method.
@@ -84,23 +84,23 @@ class AutoModel(object):
             pretrained_model_name_or_path: either:
 
                 - a string with the `shortcut name` of a pre-trained model to load from cache or download, e.g.: ``bert-base-uncased``.
-                - a path to a `directory` containing model weights saved using :func:`~pytorch_transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/``.
+                - a path to a `directory` containing model weights saved using :func:`~transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/``.
                 - a path or url to a `tensorflow index checkpoint file` (e.g. `./tf_model/model.ckpt.index`). In this case, ``from_tf`` should be set to True and a configuration object should be provided as ``config`` argument. This loading path is slower than converting the TensorFlow checkpoint in a PyTorch model using the provided conversion scripts and loading the PyTorch model afterwards.
 
             model_args: (`optional`) Sequence of positional arguments:
                 All remaning positional arguments will be passed to the underlying model's ``__init__`` method
 
-            config: (`optional`) instance of a class derived from :class:`~pytorch_transformers.PretrainedConfig`:
+            config: (`optional`) instance of a class derived from :class:`~transformers.PretrainedConfig`:
                 Configuration for the model to use instead of an automatically loaded configuation. Configuration can be automatically loaded when:
 
                 - the model is a model provided by the library (loaded with the ``shortcut-name`` string of a pretrained model), or
-                - the model was saved using :func:`~pytorch_transformers.PreTrainedModel.save_pretrained` and is reloaded by suppling the save directory.
+                - the model was saved using :func:`~transformers.PreTrainedModel.save_pretrained` and is reloaded by suppling the save directory.
                 - the model is loaded by suppling a local directory as ``pretrained_model_name_or_path`` and a configuration JSON file named `config.json` is found in the directory.
 
             state_dict: (`optional`) dict:
                 an optional state dictionnary for the model to use instead of a state dictionary loaded from saved weights file.
                 This option can be used if you want to create a model from a pretrained configuration but load your own weights.
-                In this case though, you should check if using :func:`~pytorch_transformers.PreTrainedModel.save_pretrained` and :func:`~pytorch_transformers.PreTrainedModel.from_pretrained` is not a simpler option.
+                In this case though, you should check if using :func:`~transformers.PreTrainedModel.save_pretrained` and :func:`~transformers.PreTrainedModel.from_pretrained` is not a simpler option.
 
             cache_dir: (`optional`) string:
                 Path to a directory in which a downloaded pre-trained model
@@ -120,7 +120,7 @@ class AutoModel(object):
                 Can be used to update the configuration object (after it being loaded) and initiate the model. (e.g. ``output_attention=True``). Behave differently depending on whether a `config` is provided or automatically loaded:
 
                 - If a configuration is provided with ``config``, ``**kwargs`` will be directly passed to the underlying model's ``__init__`` method (we assume all relevant updates to the configuration have already been done)
-                - If a configuration is not provided, ``kwargs`` will be first passed to the configuration class initialization function (:func:`~pytorch_transformers.PretrainedConfig.from_pretrained`). Each key of ``kwargs`` that corresponds to a configuration attribute will be used to override said attribute with the supplied ``kwargs`` value. Remaining keys that do not correspond to any configuration attribute will be passed to the underlying model's ``__init__`` function.
+                - If a configuration is not provided, ``kwargs`` will be first passed to the configuration class initialization function (:func:`~transformers.PretrainedConfig.from_pretrained`). Each key of ``kwargs`` that corresponds to a configuration attribute will be used to override said attribute with the supplied ``kwargs`` value. Remaining keys that do not correspond to any configuration attribute will be passed to the underlying model's ``__init__`` function.
 
         Examples::
 
@@ -157,7 +157,7 @@ class AutoModel(object):
 
 class AutoModelWithLMHead(object):
     r"""
-        :class:`~pytorch_transformers.AutoModelWithLMHead` is a generic model class
+        :class:`~transformers.AutoModelWithLMHead` is a generic model class
         that will be instantiated as one of the language modeling model classes of the library
         when created with the `AutoModelWithLMHead.from_pretrained(pretrained_model_name_or_path)`
         class method.
@@ -208,23 +208,23 @@ class AutoModelWithLMHead(object):
             pretrained_model_name_or_path: either:
 
                 - a string with the `shortcut name` of a pre-trained model to load from cache or download, e.g.: ``bert-base-uncased``.
-                - a path to a `directory` containing model weights saved using :func:`~pytorch_transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/``.
+                - a path to a `directory` containing model weights saved using :func:`~transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/``.
                 - a path or url to a `tensorflow index checkpoint file` (e.g. `./tf_model/model.ckpt.index`). In this case, ``from_tf`` should be set to True and a configuration object should be provided as ``config`` argument. This loading path is slower than converting the TensorFlow checkpoint in a PyTorch model using the provided conversion scripts and loading the PyTorch model afterwards.
 
             model_args: (`optional`) Sequence of positional arguments:
                 All remaning positional arguments will be passed to the underlying model's ``__init__`` method
 
-            config: (`optional`) instance of a class derived from :class:`~pytorch_transformers.PretrainedConfig`:
+            config: (`optional`) instance of a class derived from :class:`~transformers.PretrainedConfig`:
                 Configuration for the model to use instead of an automatically loaded configuation. Configuration can be automatically loaded when:
 
                 - the model is a model provided by the library (loaded with the ``shortcut-name`` string of a pretrained model), or
-                - the model was saved using :func:`~pytorch_transformers.PreTrainedModel.save_pretrained` and is reloaded by suppling the save directory.
+                - the model was saved using :func:`~transformers.PreTrainedModel.save_pretrained` and is reloaded by suppling the save directory.
                 - the model is loaded by suppling a local directory as ``pretrained_model_name_or_path`` and a configuration JSON file named `config.json` is found in the directory.
 
             state_dict: (`optional`) dict:
                 an optional state dictionnary for the model to use instead of a state dictionary loaded from saved weights file.
                 This option can be used if you want to create a model from a pretrained configuration but load your own weights.
-                In this case though, you should check if using :func:`~pytorch_transformers.PreTrainedModel.save_pretrained` and :func:`~pytorch_transformers.PreTrainedModel.from_pretrained` is not a simpler option.
+                In this case though, you should check if using :func:`~transformers.PreTrainedModel.save_pretrained` and :func:`~transformers.PreTrainedModel.from_pretrained` is not a simpler option.
 
             cache_dir: (`optional`) string:
                 Path to a directory in which a downloaded pre-trained model
@@ -244,7 +244,7 @@ class AutoModelWithLMHead(object):
                 Can be used to update the configuration object (after it being loaded) and initiate the model. (e.g. ``output_attention=True``). Behave differently depending on whether a `config` is provided or automatically loaded:
 
                 - If a configuration is provided with ``config``, ``**kwargs`` will be directly passed to the underlying model's ``__init__`` method (we assume all relevant updates to the configuration have already been done)
-                - If a configuration is not provided, ``kwargs`` will be first passed to the configuration class initialization function (:func:`~pytorch_transformers.PretrainedConfig.from_pretrained`). Each key of ``kwargs`` that corresponds to a configuration attribute will be used to override said attribute with the supplied ``kwargs`` value. Remaining keys that do not correspond to any configuration attribute will be passed to the underlying model's ``__init__`` function.
+                - If a configuration is not provided, ``kwargs`` will be first passed to the configuration class initialization function (:func:`~transformers.PretrainedConfig.from_pretrained`). Each key of ``kwargs`` that corresponds to a configuration attribute will be used to override said attribute with the supplied ``kwargs`` value. Remaining keys that do not correspond to any configuration attribute will be passed to the underlying model's ``__init__`` function.
 
         Examples::
 
@@ -281,7 +281,7 @@ class AutoModelWithLMHead(object):
 
 class AutoModelForSequenceClassification(object):
     r"""
-        :class:`~pytorch_transformers.AutoModelForSequenceClassification` is a generic model class
+        :class:`~transformers.AutoModelForSequenceClassification` is a generic model class
         that will be instantiated as one of the sequence classification model classes of the library
         when created with the `AutoModelForSequenceClassification.from_pretrained(pretrained_model_name_or_path)`
         class method.
@@ -326,23 +326,23 @@ class AutoModelForSequenceClassification(object):
             pretrained_model_name_or_path: either:
 
                 - a string with the `shortcut name` of a pre-trained model to load from cache or download, e.g.: ``bert-base-uncased``.
-                - a path to a `directory` containing model weights saved using :func:`~pytorch_transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/``.
+                - a path to a `directory` containing model weights saved using :func:`~transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/``.
                 - a path or url to a `tensorflow index checkpoint file` (e.g. `./tf_model/model.ckpt.index`). In this case, ``from_tf`` should be set to True and a configuration object should be provided as ``config`` argument. This loading path is slower than converting the TensorFlow checkpoint in a PyTorch model using the provided conversion scripts and loading the PyTorch model afterwards.
 
             model_args: (`optional`) Sequence of positional arguments:
                 All remaning positional arguments will be passed to the underlying model's ``__init__`` method
 
-            config: (`optional`) instance of a class derived from :class:`~pytorch_transformers.PretrainedConfig`:
+            config: (`optional`) instance of a class derived from :class:`~transformers.PretrainedConfig`:
                 Configuration for the model to use instead of an automatically loaded configuation. Configuration can be automatically loaded when:
 
                 - the model is a model provided by the library (loaded with the ``shortcut-name`` string of a pretrained model), or
-                - the model was saved using :func:`~pytorch_transformers.PreTrainedModel.save_pretrained` and is reloaded by suppling the save directory.
+                - the model was saved using :func:`~transformers.PreTrainedModel.save_pretrained` and is reloaded by suppling the save directory.
                 - the model is loaded by suppling a local directory as ``pretrained_model_name_or_path`` and a configuration JSON file named `config.json` is found in the directory.
 
             state_dict: (`optional`) dict:
                 an optional state dictionnary for the model to use instead of a state dictionary loaded from saved weights file.
                 This option can be used if you want to create a model from a pretrained configuration but load your own weights.
-                In this case though, you should check if using :func:`~pytorch_transformers.PreTrainedModel.save_pretrained` and :func:`~pytorch_transformers.PreTrainedModel.from_pretrained` is not a simpler option.
+                In this case though, you should check if using :func:`~transformers.PreTrainedModel.save_pretrained` and :func:`~transformers.PreTrainedModel.from_pretrained` is not a simpler option.
 
             cache_dir: (`optional`) string:
                 Path to a directory in which a downloaded pre-trained model
@@ -362,7 +362,7 @@ class AutoModelForSequenceClassification(object):
                 Can be used to update the configuration object (after it being loaded) and initiate the model. (e.g. ``output_attention=True``). Behave differently depending on whether a `config` is provided or automatically loaded:
 
                 - If a configuration is provided with ``config``, ``**kwargs`` will be directly passed to the underlying model's ``__init__`` method (we assume all relevant updates to the configuration have already been done)
-                - If a configuration is not provided, ``kwargs`` will be first passed to the configuration class initialization function (:func:`~pytorch_transformers.PretrainedConfig.from_pretrained`). Each key of ``kwargs`` that corresponds to a configuration attribute will be used to override said attribute with the supplied ``kwargs`` value. Remaining keys that do not correspond to any configuration attribute will be passed to the underlying model's ``__init__`` function.
+                - If a configuration is not provided, ``kwargs`` will be first passed to the configuration class initialization function (:func:`~transformers.PretrainedConfig.from_pretrained`). Each key of ``kwargs`` that corresponds to a configuration attribute will be used to override said attribute with the supplied ``kwargs`` value. Remaining keys that do not correspond to any configuration attribute will be passed to the underlying model's ``__init__`` function.
 
         Examples::
 
@@ -392,7 +392,7 @@ class AutoModelForSequenceClassification(object):
 
 class AutoModelForQuestionAnswering(object):
     r"""
-        :class:`~pytorch_transformers.AutoModelForQuestionAnswering` is a generic model class
+        :class:`~transformers.AutoModelForQuestionAnswering` is a generic model class
         that will be instantiated as one of the question answering model classes of the library
         when created with the `AutoModelForQuestionAnswering.from_pretrained(pretrained_model_name_or_path)`
         class method.
@@ -435,23 +435,23 @@ class AutoModelForQuestionAnswering(object):
             pretrained_model_name_or_path: either:
 
                 - a string with the `shortcut name` of a pre-trained model to load from cache or download, e.g.: ``bert-base-uncased``.
-                - a path to a `directory` containing model weights saved using :func:`~pytorch_transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/``.
+                - a path to a `directory` containing model weights saved using :func:`~transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/``.
                 - a path or url to a `tensorflow index checkpoint file` (e.g. `./tf_model/model.ckpt.index`). In this case, ``from_tf`` should be set to True and a configuration object should be provided as ``config`` argument. This loading path is slower than converting the TensorFlow checkpoint in a PyTorch model using the provided conversion scripts and loading the PyTorch model afterwards.
 
             model_args: (`optional`) Sequence of positional arguments:
                 All remaning positional arguments will be passed to the underlying model's ``__init__`` method
 
-            config: (`optional`) instance of a class derived from :class:`~pytorch_transformers.PretrainedConfig`:
+            config: (`optional`) instance of a class derived from :class:`~transformers.PretrainedConfig`:
                 Configuration for the model to use instead of an automatically loaded configuation. Configuration can be automatically loaded when:
 
                 - the model is a model provided by the library (loaded with the ``shortcut-name`` string of a pretrained model), or
-                - the model was saved using :func:`~pytorch_transformers.PreTrainedModel.save_pretrained` and is reloaded by suppling the save directory.
+                - the model was saved using :func:`~transformers.PreTrainedModel.save_pretrained` and is reloaded by suppling the save directory.
                 - the model is loaded by suppling a local directory as ``pretrained_model_name_or_path`` and a configuration JSON file named `config.json` is found in the directory.
 
             state_dict: (`optional`) dict:
                 an optional state dictionnary for the model to use instead of a state dictionary loaded from saved weights file.
                 This option can be used if you want to create a model from a pretrained configuration but load your own weights.
-                In this case though, you should check if using :func:`~pytorch_transformers.PreTrainedModel.save_pretrained` and :func:`~pytorch_transformers.PreTrainedModel.from_pretrained` is not a simpler option.
+                In this case though, you should check if using :func:`~transformers.PreTrainedModel.save_pretrained` and :func:`~transformers.PreTrainedModel.from_pretrained` is not a simpler option.
 
             cache_dir: (`optional`) string:
                 Path to a directory in which a downloaded pre-trained model
@@ -471,7 +471,7 @@ class AutoModelForQuestionAnswering(object):
                 Can be used to update the configuration object (after it being loaded) and initiate the model. (e.g. ``output_attention=True``). Behave differently depending on whether a `config` is provided or automatically loaded:
 
                 - If a configuration is provided with ``config``, ``**kwargs`` will be directly passed to the underlying model's ``__init__`` method (we assume all relevant updates to the configuration have already been done)
-                - If a configuration is not provided, ``kwargs`` will be first passed to the configuration class initialization function (:func:`~pytorch_transformers.PretrainedConfig.from_pretrained`). Each key of ``kwargs`` that corresponds to a configuration attribute will be used to override said attribute with the supplied ``kwargs`` value. Remaining keys that do not correspond to any configuration attribute will be passed to the underlying model's ``__init__`` function.
+                - If a configuration is not provided, ``kwargs`` will be first passed to the configuration class initialization function (:func:`~transformers.PretrainedConfig.from_pretrained`). Each key of ``kwargs`` that corresponds to a configuration attribute will be used to override said attribute with the supplied ``kwargs`` value. Remaining keys that do not correspond to any configuration attribute will be passed to the underlying model's ``__init__`` function.
 
         Examples::
 

pytorch_transformers/modeling_bert.py → transformers/modeling_bert.py

@@ -486,9 +486,9 @@ BERT_START_DOCSTRING = r"""    The BERT model was proposed in
         https://pytorch.org/docs/stable/nn.html#module
 
     Parameters:
-        config (:class:`~pytorch_transformers.BertConfig`): Model configuration class with all the parameters of the model. 
+        config (:class:`~transformers.BertConfig`): Model configuration class with all the parameters of the model. 
             Initializing with a config file does not load the weights associated with the model, only the configuration.
-            Check out the :meth:`~pytorch_transformers.PreTrainedModel.from_pretrained` method to load the model weights.
+            Check out the :meth:`~transformers.PreTrainedModel.from_pretrained` method to load the model weights.
 """
 
 BERT_INPUTS_DOCSTRING = r"""
@@ -512,9 +512,9 @@ BERT_INPUTS_DOCSTRING = r"""
             Bert is a model with absolute position embeddings so it's usually advised to pad the inputs on
             the right rather than the left.
 
-            Indices can be obtained using :class:`pytorch_transformers.BertTokenizer`.
-            See :func:`pytorch_transformers.PreTrainedTokenizer.encode` and
-            :func:`pytorch_transformers.PreTrainedTokenizer.convert_tokens_to_ids` for details.
+            Indices can be obtained using :class:`transformers.BertTokenizer`.
+            See :func:`transformers.PreTrainedTokenizer.encode` and
+            :func:`transformers.PreTrainedTokenizer.convert_tokens_to_ids` for details.
         **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]``:

pytorch_transformers/modeling_distilbert.py → transformers/modeling_distilbert.py

@@ -372,9 +372,9 @@ DISTILBERT_START_DOCSTRING = r"""
         https://medium.com/huggingface/distilbert-8cf3380435b5
 
     Parameters:
-        config (:class:`~pytorch_transformers.DistilBertConfig`): Model configuration class with all the parameters of the model. 
+        config (:class:`~transformers.DistilBertConfig`): Model configuration class with all the parameters of the model. 
             Initializing with a config file does not load the weights associated with the model, only the configuration.
-            Check out the :meth:`~pytorch_transformers.PreTrainedModel.from_pretrained` method to load the model weights.
+            Check out the :meth:`~transformers.PreTrainedModel.from_pretrained` method to load the model weights.
 """
 
 DISTILBERT_INPUTS_DOCSTRING = r"""

pytorch_transformers/modeling_gpt2.py → transformers/modeling_gpt2.py

@@ -280,9 +280,9 @@ GPT2_START_DOCSTRING = r"""    OpenAI GPT-2 model was proposed in
         https://pytorch.org/docs/stable/nn.html#module
 
     Parameters:
-        config (:class:`~pytorch_transformers.GPT2Config`): Model configuration class with all the parameters of the model.
+        config (:class:`~transformers.GPT2Config`): Model configuration class with all the parameters of the model.
             Initializing with a config file does not load the weights associated with the model, only the configuration.
-            Check out the :meth:`~pytorch_transformers.PreTrainedModel.from_pretrained` method to load the model weights.
+            Check out the :meth:`~transformers.PreTrainedModel.from_pretrained` method to load the model weights.
 """
 
 GPT2_INPUTS_DOCSTRING = r"""    Inputs:
@@ -290,9 +290,9 @@ GPT2_INPUTS_DOCSTRING = r"""    Inputs:
             Indices of input sequence tokens in the vocabulary.
             GPT-2 is a model with absolute position embeddings so it's usually advised to pad the inputs on
             the right rather than the left.
-            Indices can be obtained using :class:`pytorch_transformers.GPT2Tokenizer`.
-            See :func:`pytorch_transformers.PreTrainedTokenizer.encode` and
-            :func:`pytorch_transformers.PreTrainedTokenizer.convert_tokens_to_ids` for details.
+            Indices can be obtained using :class:`transformers.GPT2Tokenizer`.
+            See :func:`transformers.PreTrainedTokenizer.encode` and
+            :func:`transformers.PreTrainedTokenizer.convert_tokens_to_ids` for details.
         **past**:
             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
@@ -493,7 +493,7 @@ class GPT2LMHeadModel(GPT2PreTrainedModel):
     Examples::
 
         import torch
-        from pytorch_transformers import GPT2Tokenizer, GPT2LMHeadModel
+        from transformers import GPT2Tokenizer, GPT2LMHeadModel
 
         tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
         model = GPT2LMHeadModel.from_pretrained('gpt2')
@@ -589,7 +589,7 @@ class GPT2DoubleHeadsModel(GPT2PreTrainedModel):
     Examples::
 
         import torch
-        from pytorch_transformers import GPT2Tokenizer, GPT2DoubleHeadsModel
+        from transformers import GPT2Tokenizer, GPT2DoubleHeadsModel
         
         tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
         model = GPT2DoubleHeadsModel.from_pretrained('gpt2')