Merge pull request #1203 from huggingface/tf2

[2.0] TF 2.0 support

.circleci/config.yml

 version: 2
 jobs:
-    build_py3:
-        working_directory: ~/pytorch-transformers
+    build_py3_torch_and_tf:
+        working_directory: ~/transformers
         docker:
             - image: circleci/python:3.5
         resource_class: xlarge
         parallelism: 1
         steps:
             - checkout
+            - run: sudo pip install torch
+            - run: sudo pip install tensorflow==2.0.0-rc0
             - run: sudo pip install --progress-bar off .
             - run: sudo pip install pytest codecov pytest-cov
             - run: sudo pip install tensorboardX scikit-learn
-            - run: python -m pytest -sv ./pytorch_transformers/tests/ --cov
+            - run: python -m pytest -sv ./transformers/tests/ --cov
+            - run: codecov
+    build_py3_torch:
+        working_directory: ~/transformers
+        docker:
+            - image: circleci/python:3.5
+        resource_class: xlarge
+        parallelism: 1
+        steps:
+            - checkout
+            - run: sudo pip install torch
+            - run: sudo pip install --progress-bar off .
+            - run: sudo pip install pytest codecov pytest-cov
+            - run: sudo pip install tensorboardX scikit-learn
+            - run: python -m pytest -sv ./transformers/tests/ --cov
             - run: python -m pytest -sv ./examples/
             - run: codecov
-    build_py2:
-        working_directory: ~/pytorch-transformers
+    build_py3_tf:
+        working_directory: ~/transformers
+        docker:
+            - image: circleci/python:3.5
+        resource_class: xlarge
+        parallelism: 1
+        steps:
+            - checkout
+            - run: sudo pip install tensorflow==2.0.0-rc0
+            - run: sudo pip install --progress-bar off .
+            - run: sudo pip install pytest codecov pytest-cov
+            - run: sudo pip install tensorboardX scikit-learn
+            - run: python -m pytest -sv ./transformers/tests/ --cov
+            - run: codecov
+    build_py2_torch:
+        working_directory: ~/transformers
+        resource_class: large
+        parallelism: 1
+        docker:
+            - image: circleci/python:2.7
+        steps:
+            - checkout
+            - run: sudo pip install torch
+            - run: sudo pip install --progress-bar off .
+            - run: sudo pip install pytest codecov pytest-cov
+            - run: python -m pytest -sv ./transformers/tests/ --cov
+            - run: codecov
+    build_py2_tf:
+        working_directory: ~/transformers
         resource_class: large
         parallelism: 1
         docker:
             - image: circleci/python:2.7
         steps:
             - checkout
+            - run: sudo pip install tensorflow==2.0.0-rc0
             - run: sudo pip install --progress-bar off .
             - run: sudo pip install pytest codecov pytest-cov
-            - run: python -m pytest -sv ./pytorch_transformers/tests/ --cov
+            - run: python -m pytest -sv ./transformers/tests/ --cov
             - run: codecov
     deploy_doc:
-        working_directory: ~/pytorch-transformers
+        working_directory: ~/transformers
         docker:
             - image: circleci/python:3.5
         steps:
@@ -48,6 +92,9 @@ workflows:
     version: 2
     build_and_test:
         jobs:
-            - build_py3
-            - build_py2
+            - build_py3_torch_and_tf
+            - build_py3_torch
+            - build_py3_tf
+            - build_py2_torch
+            - build_py2_tf
             - deploy_doc: *workflow_filters
\ No newline at end of file

.coveragerc

 [run]
-source=pytorch_transformers
+source=transformers
 omit =
     # skip convertion scripts from testing for now
     */convert_*

.github/ISSUE_TEMPLATE/migration.md

 ---
 name: "\U0001F4DA Migration from PyTorch-pretrained-Bert"
-about: Report a problem when migrating from PyTorch-pretrained-Bert to PyTorch-Transformers
+about: Report a problem when migrating from PyTorch-pretrained-Bert to Transformers
 ---
 
 ## 📚 Migration

.gitignore

@@ -130,5 +130,5 @@ runs
 examples/runs
 
 # data
-data
+/data
 serialization_dir
\ No newline at end of file

docker/Dockerfile

@@ -2,6 +2,6 @@ FROM pytorch/pytorch:latest
 
 RUN git clone https://github.com/NVIDIA/apex.git && cd apex && python setup.py install --cuda_ext --cpp_ext
 
-RUN pip install pytorch_transformers
+RUN pip install transformers
 
 WORKDIR /workspace
\ No newline at end of file

docs/source/_static/js/custom.js

@@ -16,7 +16,7 @@ function addIcon() {
 function addCustomFooter() {
     const customFooter = document.createElement("div");
     const questionOrIssue = document.createElement("div");
-    questionOrIssue.innerHTML = "Stuck? Read our <a href='https://medium.com/huggingface'>Blog posts</a> or <a href='https://github.com/huggingface/pytorch_transformers'>Create an issue</a>";
+    questionOrIssue.innerHTML = "Stuck? Read our <a href='https://medium.com/huggingface'>Blog posts</a> or <a href='https://github.com/huggingface/transformers'>Create an issue</a>";
     customFooter.appendChild(questionOrIssue);
     customFooter.classList.add("footer");
 

docs/source/bertology.rst

@@ -15,4 +15,4 @@ In order to help this new field develop, we have included a few additional featu
 * accessing all the attention weights for each head of BERT/GPT/GPT-2,
 * retrieving heads output values and gradients to be able to compute head importance score and prune head as explained in https://arxiv.org/abs/1905.10650.
 
-To help you understand and use these features, we have added a specific example script: `bertology.py <https://github.com/huggingface/pytorch-transformers/blob/master/examples/run_bertology.py>`_ while extract information and prune a model pre-trained on GLUE.
+To help you understand and use these features, we have added a specific example script: `bertology.py <https://github.com/huggingface/transformers/blob/master/examples/run_bertology.py>`_ while extract information and prune a model pre-trained on GLUE.

docs/source/conf.py

@@ -19,7 +19,7 @@ sys.path.insert(0, os.path.abspath('../..'))
 
 # -- Project information -----------------------------------------------------
 
-project = u'pytorch-transformers'
+project = u'transformers'
 copyright = u'2019, huggingface'
 author = u'huggingface'
 
@@ -109,7 +109,7 @@ html_static_path = ['_static']
 # -- Options for HTMLHelp output ---------------------------------------------
 
 # Output file base name for HTML help builder.
-htmlhelp_basename = 'pytorch-transformersdoc'
+htmlhelp_basename = 'transformersdoc'
 
 
 # -- Options for LaTeX output ------------------------------------------------
@@ -136,7 +136,7 @@ latex_elements = {
 # (source start file, target name, title,
 #  author, documentclass [howto, manual, or own class]).
 latex_documents = [
-    (master_doc, 'pytorch-transformers.tex', u'pytorch-transformers Documentation',
+    (master_doc, 'transformers.tex', u'transformers Documentation',
      u'huggingface', 'manual'),
 ]
 
@@ -146,7 +146,7 @@ latex_documents = [
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
 man_pages = [
-    (master_doc, 'pytorch-transformers', u'pytorch-transformers Documentation',
+    (master_doc, 'transformers', u'transformers Documentation',
      [author], 1)
 ]
 
@@ -157,8 +157,8 @@ man_pages = [
 # (source start file, target name, title, author,
 #  dir menu entry, description, category)
 texinfo_documents = [
-    (master_doc, 'pytorch-transformers', u'pytorch-transformers Documentation',
-     author, 'pytorch-transformers', 'One line description of project.',
+    (master_doc, 'transformers', u'transformers Documentation',
+     author, 'transformers', 'One line description of project.',
      'Miscellaneous'),
 ]
 

docs/source/converting_tensorflow_models.rst

@@ -6,7 +6,7 @@ A command-line interface is provided to convert original Bert/GPT/GPT-2/Transfor
 BERT
 ^^^^
 
-You can convert any TensorFlow checkpoint for BERT (in particular `the pre-trained models released by Google <https://github.com/google-research/bert#pre-trained-models>`_\ ) in a PyTorch save file by using the `convert_tf_checkpoint_to_pytorch.py <https://github.com/huggingface/pytorch-transformers/blob/master/pytorch_transformers/convert_tf_checkpoint_to_pytorch.py>`_ script.
+You can convert any TensorFlow checkpoint for BERT (in particular `the pre-trained models released by Google <https://github.com/google-research/bert#pre-trained-models>`_\ ) in a PyTorch save file by using the `convert_tf_checkpoint_to_pytorch.py <https://github.com/huggingface/transformers/blob/master/transformers/convert_tf_checkpoint_to_pytorch.py>`_ script.
 
 This CLI takes as input a TensorFlow checkpoint (three files starting with ``bert_model.ckpt``\ ) and the associated configuration file (\ ``bert_config.json``\ ), and creates a PyTorch model for this configuration, loads the weights from the TensorFlow checkpoint in the PyTorch model and saves the resulting model in a standard PyTorch save file that can be imported using ``torch.load()`` (see examples in `run_bert_extract_features.py <https://github.com/huggingface/pytorch-pretrained-BERT/tree/master/examples/run_bert_extract_features.py>`_\ , `run_bert_classifier.py <https://github.com/huggingface/pytorch-pretrained-BERT/tree/master/examples/run_bert_classifier.py>`_ and `run_bert_squad.py <https://github.com/huggingface/pytorch-pretrained-BERT/tree/master/examples/run_bert_squad.py>`_\ ).
 
@@ -20,7 +20,7 @@ Here is an example of the conversion process for a pre-trained ``BERT-Base Uncas
 
    export BERT_BASE_DIR=/path/to/bert/uncased_L-12_H-768_A-12
 
-   pytorch_transformers bert \
+   transformers bert \
      $BERT_BASE_DIR/bert_model.ckpt \
      $BERT_BASE_DIR/bert_config.json \
      $BERT_BASE_DIR/pytorch_model.bin
@@ -36,7 +36,7 @@ Here is an example of the conversion process for a pre-trained OpenAI GPT model,
 
    export OPENAI_GPT_CHECKPOINT_FOLDER_PATH=/path/to/openai/pretrained/numpy/weights
 
-   pytorch_transformers gpt \
+   transformers gpt \
      $OPENAI_GPT_CHECKPOINT_FOLDER_PATH \
      $PYTORCH_DUMP_OUTPUT \
      [OPENAI_GPT_CONFIG]
@@ -50,7 +50,7 @@ Here is an example of the conversion process for a pre-trained OpenAI GPT-2 mode
 
    export OPENAI_GPT2_CHECKPOINT_PATH=/path/to/gpt2/pretrained/weights
 
-   pytorch_transformers gpt2 \
+   transformers gpt2 \
      $OPENAI_GPT2_CHECKPOINT_PATH \
      $PYTORCH_DUMP_OUTPUT \
      [OPENAI_GPT2_CONFIG]
@@ -64,7 +64,7 @@ Here is an example of the conversion process for a pre-trained Transformer-XL mo
 
    export TRANSFO_XL_CHECKPOINT_FOLDER_PATH=/path/to/transfo/xl/checkpoint
 
-   pytorch_transformers transfo_xl \
+   transformers transfo_xl \
      $TRANSFO_XL_CHECKPOINT_FOLDER_PATH \
      $PYTORCH_DUMP_OUTPUT \
      [TRANSFO_XL_CONFIG]
@@ -80,7 +80,7 @@ Here is an example of the conversion process for a pre-trained XLNet model, fine
    export TRANSFO_XL_CHECKPOINT_PATH=/path/to/xlnet/checkpoint
    export TRANSFO_XL_CONFIG_PATH=/path/to/xlnet/config
 
-   pytorch_transformers xlnet \
+   transformers xlnet \
      $TRANSFO_XL_CHECKPOINT_PATH \
      $TRANSFO_XL_CONFIG_PATH \
      $PYTORCH_DUMP_OUTPUT \
@@ -96,6 +96,6 @@ Here is an example of the conversion process for a pre-trained XLM model:
 
    export XLM_CHECKPOINT_PATH=/path/to/xlm/checkpoint
 
-   pytorch_transformers xlm \
+   transformers xlm \
      $XLM_CHECKPOINT_PATH \
      $PYTORCH_DUMP_OUTPUT \

docs/source/index.rst

-Pytorch-Transformers
+Transformers
 ================================================================================================================================================
 
-PyTorch-Transformers is a library of state-of-the-art pre-trained models for Natural Language Processing (NLP).
+Transformers is a library of state-of-the-art pre-trained models for Natural Language Processing (NLP).
 
 The library currently contains PyTorch implementations, pre-trained model weights, usage scripts and conversion utilities for the following models:
 
@@ -12,7 +12,7 @@ The library currently contains PyTorch implementations, pre-trained model weight
 5. `XLNet <https://github.com/zihangdai/xlnet>`_ (from Google/CMU) released with the paper `​XLNet: Generalized Autoregressive Pretraining for Language Understanding <https://arxiv.org/abs/1906.08237>`_ by Zhilin Yang*, Zihang Dai*, Yiming Yang, Jaime Carbonell, Ruslan Salakhutdinov, Quoc V. Le.
 6. `XLM <https://github.com/facebookresearch/XLM>`_ (from Facebook) released together with the paper `Cross-lingual Language Model Pretraining <https://arxiv.org/abs/1901.07291>`_ by Guillaume Lample and Alexis Conneau.
 7. `RoBERTa <https://github.com/pytorch/fairseq/tree/master/examples/roberta>`_ (from Facebook), released together with the paper a `Robustly Optimized BERT Pretraining Approach <https://arxiv.org/abs/1907.11692>`_ by Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, Veselin Stoyanov.
-8. `DistilBERT <https://huggingface.co/pytorch-transformers/model_doc/distilbert.html>`_ (from HuggingFace) released together with the blog post `Smaller, faster, cheaper, lighter: Introducing DistilBERT, a distilled version of BERT <https://medium.com/huggingface/distilbert-8cf3380435b5>`_ by Victor Sanh, Lysandre Debut and Thomas Wolf.
+8. `DistilBERT <https://huggingface.co/transformers/model_doc/distilbert.html>`_ (from HuggingFace) released together with the blog post `Smaller, faster, cheaper, lighter: Introducing DistilBERT, a distilled version of BERT <https://medium.com/huggingface/distilbert-8cf3380435b5>`_ by Victor Sanh, Lysandre Debut and Thomas Wolf.
 
 .. toctree::
     :maxdepth: 2

docs/source/installation.rst

 Installation
 ================================================
 
-PyTorch-Transformers is tested on Python 2.7 and 3.5+ (examples are tested only on python 3.5+) and PyTorch 1.1.0
+Transformers is tested on Python 2.7 and 3.5+ (examples are tested only on python 3.5+) and PyTorch 1.1.0
 
 With pip
 ^^^^^^^^
@@ -10,7 +10,7 @@ PyTorch Transformers can be installed using pip as follows:
 
 .. code-block:: bash
 
-   pip install pytorch-transformers
+   pip install transformers
 
 From source
 ^^^^^^^^^^^
@@ -19,15 +19,15 @@ To install from source, clone the repository and install with:
 
 .. code-block:: bash
 
-    git clone https://github.com/huggingface/pytorch-transformers.git
-    cd pytorch-transformers
+    git clone https://github.com/huggingface/transformers.git
+    cd transformers
     pip install [--editable] .
 
 
 Tests
 ^^^^^
 
-An extensive test suite is included to test the library behavior and several examples. Library tests can be found in the `tests folder <https://github.com/huggingface/pytorch-transformers/tree/master/pytorch_transformers/tests>`_ and examples tests in the `examples folder <https://github.com/huggingface/pytorch-transformers/tree/master/examples>`_.
+An extensive test suite is included to test the library behavior and several examples. Library tests can be found in the `tests folder <https://github.com/huggingface/transformers/tree/master/transformers/tests>`_ and examples tests in the `examples folder <https://github.com/huggingface/transformers/tree/master/examples>`_.
 
 Tests can be run using `pytest` (install pytest if needed with `pip install pytest`).
 
@@ -35,7 +35,7 @@ Run all the tests from the root of the cloned repository with the commands:
 
 .. code-block:: bash
 
-    python -m pytest -sv ./pytorch_transformers/tests/
+    python -m pytest -sv ./transformers/tests/
     python -m pytest -sv ./examples/
 
 

docs/source/main_classes/configuration.rst

@@ -6,5 +6,5 @@ The base class ``PretrainedConfig`` implements the common methods for loading/sa
 ``PretrainedConfig``
 ~~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: pytorch_transformers.PretrainedConfig
+.. autoclass:: transformers.PretrainedConfig
     :members:

docs/source/main_classes/model.rst

@@ -11,5 +11,5 @@ The base class ``PreTrainedModel`` implements the common methods for loading/sav
 ``PreTrainedModel``
 ~~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: pytorch_transformers.PreTrainedModel
+.. autoclass:: transformers.PreTrainedModel
     :members:

docs/source/main_classes/optimizer_schedules.rst

@@ -9,7 +9,7 @@ The ``.optimization`` module provides:
 ``AdamW``
 ~~~~~~~~~~~~~~~~
 
-.. autoclass:: pytorch_transformers.AdamW
+.. autoclass:: transformers.AdamW
     :members:
 
 Schedules
@@ -18,11 +18,11 @@ Schedules
 Learning Rate Schedules
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-.. autoclass:: pytorch_transformers.ConstantLRSchedule
+.. autoclass:: transformers.ConstantLRSchedule
     :members:
 
 
-.. autoclass:: pytorch_transformers.WarmupConstantSchedule
+.. autoclass:: transformers.WarmupConstantSchedule
     :members:
 
 .. image:: /imgs/warmup_constant_schedule.png
@@ -30,7 +30,7 @@ Learning Rate Schedules
     :alt:
 
 
-.. autoclass:: pytorch_transformers.WarmupCosineSchedule
+.. autoclass:: transformers.WarmupCosineSchedule
     :members:
 
 .. image:: /imgs/warmup_cosine_schedule.png
@@ -38,7 +38,7 @@ Learning Rate Schedules
     :alt:
 
 
-.. autoclass:: pytorch_transformers.WarmupCosineWithHardRestartsSchedule
+.. autoclass:: transformers.WarmupCosineWithHardRestartsSchedule
     :members:
 
 .. image:: /imgs/warmup_cosine_hard_restarts_schedule.png
@@ -47,7 +47,7 @@ Learning Rate Schedules
 
 
 
-.. autoclass:: pytorch_transformers.WarmupLinearSchedule
+.. autoclass:: transformers.WarmupLinearSchedule
     :members:
 
 .. image:: /imgs/warmup_linear_schedule.png

docs/source/main_classes/tokenizer.rst

@@ -12,5 +12,5 @@ The base class ``PreTrainedTokenizer`` implements the common methods for loading
 ``PreTrainedTokenizer``
 ~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: pytorch_transformers.PreTrainedTokenizer
+.. autoclass:: transformers.PreTrainedTokenizer
     :members:

docs/source/migration.md

 # Migrating from pytorch-pretrained-bert
 
 
-Here is a quick summary of what you should take care of when migrating from `pytorch-pretrained-bert` to `pytorch-transformers`
+Here is a quick summary of what you should take care of when migrating from `pytorch-pretrained-bert` to `transformers`
 
 ### Models always output `tuples`
 
-The main breaking change when migrating from `pytorch-pretrained-bert` to `pytorch-transformers` is that the models forward method always outputs a `tuple` with various elements depending on the model and the configuration parameters.
+The main breaking change when migrating from `pytorch-pretrained-bert` to `transformers` is that the models forward method always outputs a `tuple` with various elements depending on the model and the configuration parameters.
 
-The exact content of the tuples for each model are detailled in the models' docstrings and the [documentation](https://huggingface.co/pytorch-transformers/).
+The exact content of the tuples for each model are detailled in the models' docstrings and the [documentation](https://huggingface.co/transformers/).
 
 In pretty much every case, you will be fine by taking the first element of the output as the output you previously used in `pytorch-pretrained-bert`.
 
-Here is a `pytorch-pretrained-bert` to `pytorch-transformers` conversion example for a `BertForSequenceClassification` classification model:
+Here is a `pytorch-pretrained-bert` to `transformers` conversion example for a `BertForSequenceClassification` classification model:
 
 ```python
 # Let's load our model
@@ -20,11 +20,11 @@ model = BertForSequenceClassification.from_pretrained('bert-base-uncased')
 # If you used to have this line in pytorch-pretrained-bert:
 loss = model(input_ids, labels=labels)
 
-# Now just use this line in pytorch-transformers to extract the loss from the output tuple:
+# Now just use this line in transformers to extract the loss from the output tuple:
 outputs = model(input_ids, labels=labels)
 loss = outputs[0]
 
-# In pytorch-transformers you can also have access to the logits:
+# In transformers you can also have access to the logits:
 loss, logits = outputs[:2]
 
 # And even the attention weigths if you configure the model to output them (and other outputs too, see the docstrings and documentation)
@@ -96,7 +96,7 @@ for batch in train_data:
     loss.backward()
     optimizer.step()
 
-### In PyTorch-Transformers, optimizer and schedules are splitted and instantiated like this:
+### In Transformers, optimizer and schedules are splitted and instantiated like this:
 optimizer = AdamW(model.parameters(), lr=lr, correct_bias=False)  # To reproduce BertAdam specific behavior set correct_bias=False
 scheduler = WarmupLinearSchedule(optimizer, warmup_steps=num_warmup_steps, t_total=num_total_steps)  # PyTorch scheduler
 ### and used like this:

docs/source/model_doc/auto.rst

@@ -11,19 +11,19 @@ Instantiating one of ``AutoModel``, ``AutoConfig`` and ``AutoTokenizer`` will di
 ``AutoConfig``
 ~~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: pytorch_transformers.AutoConfig
+.. autoclass:: transformers.AutoConfig
     :members:
 
 
 ``AutoModel``
 ~~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: pytorch_transformers.AutoModel
+.. autoclass:: transformers.AutoModel
     :members:
 
 
 ``AutoTokenizer``
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: pytorch_transformers.AutoTokenizer
+.. autoclass:: transformers.AutoTokenizer
     :members:

docs/source/model_doc/bert.rst

@@ -4,69 +4,69 @@ BERT
 ``BertConfig``
 ~~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: pytorch_transformers.BertConfig
+.. autoclass:: transformers.BertConfig
     :members:
 
 
 ``BertTokenizer``
 ~~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: pytorch_transformers.BertTokenizer
+.. autoclass:: transformers.BertTokenizer
     :members:
 
 
 ``BertModel``
 ~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: pytorch_transformers.BertModel
+.. autoclass:: transformers.BertModel
     :members:
 
 
 ``BertForPreTraining``
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: pytorch_transformers.BertForPreTraining
+.. autoclass:: transformers.BertForPreTraining
     :members:
 
 
 ``BertForMaskedLM``
 ~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: pytorch_transformers.BertForMaskedLM
+.. autoclass:: transformers.BertForMaskedLM
     :members:
 
 
 ``BertForNextSentencePrediction``
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: pytorch_transformers.BertForNextSentencePrediction
+.. autoclass:: transformers.BertForNextSentencePrediction
     :members:
 
 
 ``BertForSequenceClassification``
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: pytorch_transformers.BertForSequenceClassification
+.. autoclass:: transformers.BertForSequenceClassification
     :members:
 
 
 ``BertForMultipleChoice``
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: pytorch_transformers.BertForMultipleChoice
+.. autoclass:: transformers.BertForMultipleChoice
     :members:
 
 
 ``BertForTokenClassification``
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: pytorch_transformers.BertForTokenClassification
+.. autoclass:: transformers.BertForTokenClassification
     :members:
 
 
 ``BertForQuestionAnswering``
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. autoclass:: pytorch_transformers.BertForQuestionAnswering
+.. autoclass:: transformers.BertForQuestionAnswering
     :members: