Merge branch 'master' into master

hubconf.py

-from pytorch_transformers import (
+from transformers import (
     AutoTokenizer, AutoConfig, AutoModel, AutoModelWithLMHead, AutoModelForSequenceClassification, AutoModelForQuestionAnswering
 )
-from pytorch_transformers.file_utils import add_start_docstrings
+from transformers.file_utils import add_start_docstrings
 
 dependencies = ['torch', 'tqdm', 'boto3', 'requests', 'regex', 'sentencepiece', 'sacremoses']
 
@@ -11,12 +11,12 @@ def config(*args, **kwargs):
                 # Using torch.hub !
                 import torch
 
-                config = torch.hub.load('huggingface/pytorch-transformers', 'config', 'bert-base-uncased')  # Download configuration from S3 and cache.
-                config = torch.hub.load('huggingface/pytorch-transformers', 'config', './test/bert_saved_model/')  # E.g. config (or model) was saved using `save_pretrained('./test/saved_model/')`
-                config = torch.hub.load('huggingface/pytorch-transformers', 'config', './test/bert_saved_model/my_configuration.json')
-                config = torch.hub.load('huggingface/pytorch-transformers', 'config', 'bert-base-uncased', output_attention=True, foo=False)
+                config = torch.hub.load('huggingface/transformers', 'config', 'bert-base-uncased')  # Download configuration from S3 and cache.
+                config = torch.hub.load('huggingface/transformers', 'config', './test/bert_saved_model/')  # E.g. config (or model) was saved using `save_pretrained('./test/saved_model/')`
+                config = torch.hub.load('huggingface/transformers', 'config', './test/bert_saved_model/my_configuration.json')
+                config = torch.hub.load('huggingface/transformers', 'config', 'bert-base-uncased', output_attention=True, foo=False)
                 assert config.output_attention == True
-                config, unused_kwargs = torch.hub.load('huggingface/pytorch-transformers', 'config', 'bert-base-uncased', output_attention=True, foo=False, return_unused_kwargs=True)
+                config, unused_kwargs = torch.hub.load('huggingface/transformers', 'config', 'bert-base-uncased', output_attention=True, foo=False, return_unused_kwargs=True)
                 assert config.output_attention == True
                 assert unused_kwargs == {'foo': False}
 
@@ -31,8 +31,8 @@ def tokenizer(*args, **kwargs):
         # Using torch.hub !
         import torch
 
-        tokenizer = torch.hub.load('huggingface/pytorch-transformers', 'tokenizer', 'bert-base-uncased')    # Download vocabulary from S3 and cache.
-        tokenizer = torch.hub.load('huggingface/pytorch-transformers', 'tokenizer', './test/bert_saved_model/')  # E.g. tokenizer was saved using `save_pretrained('./test/saved_model/')`
+        tokenizer = torch.hub.load('huggingface/transformers', 'tokenizer', 'bert-base-uncased')    # Download vocabulary from S3 and cache.
+        tokenizer = torch.hub.load('huggingface/transformers', 'tokenizer', './test/bert_saved_model/')  # E.g. tokenizer was saved using `save_pretrained('./test/saved_model/')`
 
     """
 
@@ -45,13 +45,13 @@ def model(*args, **kwargs):
             # Using torch.hub !
             import torch
 
-            model = torch.hub.load('huggingface/pytorch-transformers', 'model', 'bert-base-uncased')    # Download model and configuration from S3 and cache.
-            model = torch.hub.load('huggingface/pytorch-transformers', 'model', './test/bert_model/')  # E.g. model was saved using `save_pretrained('./test/saved_model/')`
-            model = torch.hub.load('huggingface/pytorch-transformers', 'model', 'bert-base-uncased', output_attention=True)  # Update configuration during loading
+            model = torch.hub.load('huggingface/transformers', 'model', 'bert-base-uncased')    # Download model and configuration from S3 and cache.
+            model = torch.hub.load('huggingface/transformers', 'model', './test/bert_model/')  # E.g. model was saved using `save_pretrained('./test/saved_model/')`
+            model = torch.hub.load('huggingface/transformers', 'model', 'bert-base-uncased', output_attention=True)  # Update configuration during loading
             assert model.config.output_attention == True
             # Loading from a TF checkpoint file instead of a PyTorch model (slower)
             config = AutoConfig.from_json_file('./tf_model/bert_tf_model_config.json')
-            model = torch.hub.load('huggingface/pytorch-transformers', 'model', './tf_model/bert_tf_checkpoint.ckpt.index', from_tf=True, config=config)
+            model = torch.hub.load('huggingface/transformers', 'model', './tf_model/bert_tf_checkpoint.ckpt.index', from_tf=True, config=config)
 
         """
 
@@ -63,13 +63,13 @@ def modelWithLMHead(*args, **kwargs):
         # Using torch.hub !
         import torch
 
-        model = torch.hub.load('huggingface/pytorch-transformers', 'modelWithLMHead', 'bert-base-uncased')    # Download model and configuration from S3 and cache.
-        model = torch.hub.load('huggingface/pytorch-transformers', 'modelWithLMHead', './test/bert_model/')  # E.g. model was saved using `save_pretrained('./test/saved_model/')`
-        model = torch.hub.load('huggingface/pytorch-transformers', 'modelWithLMHead', 'bert-base-uncased', output_attention=True)  # Update configuration during loading
+        model = torch.hub.load('huggingface/transformers', 'modelWithLMHead', 'bert-base-uncased')    # Download model and configuration from S3 and cache.
+        model = torch.hub.load('huggingface/transformers', 'modelWithLMHead', './test/bert_model/')  # E.g. model was saved using `save_pretrained('./test/saved_model/')`
+        model = torch.hub.load('huggingface/transformers', 'modelWithLMHead', 'bert-base-uncased', output_attention=True)  # Update configuration during loading
         assert model.config.output_attention == True
         # Loading from a TF checkpoint file instead of a PyTorch model (slower)
         config = AutoConfig.from_json_file('./tf_model/bert_tf_model_config.json')
-        model = torch.hub.load('huggingface/pytorch-transformers', 'modelWithLMHead', './tf_model/bert_tf_checkpoint.ckpt.index', from_tf=True, config=config)
+        model = torch.hub.load('huggingface/transformers', 'modelWithLMHead', './tf_model/bert_tf_checkpoint.ckpt.index', from_tf=True, config=config)
 
     """
     return AutoModelWithLMHead.from_pretrained(*args, **kwargs)
@@ -81,13 +81,13 @@ def modelForSequenceClassification(*args, **kwargs):
             # Using torch.hub !
             import torch
 
-            model = torch.hub.load('huggingface/pytorch-transformers', 'modelForSequenceClassification', 'bert-base-uncased')    # Download model and configuration from S3 and cache.
-            model = torch.hub.load('huggingface/pytorch-transformers', 'modelForSequenceClassification', './test/bert_model/')  # E.g. model was saved using `save_pretrained('./test/saved_model/')`
-            model = torch.hub.load('huggingface/pytorch-transformers', 'modelForSequenceClassification', 'bert-base-uncased', output_attention=True)  # Update configuration during loading
+            model = torch.hub.load('huggingface/transformers', 'modelForSequenceClassification', 'bert-base-uncased')    # Download model and configuration from S3 and cache.
+            model = torch.hub.load('huggingface/transformers', 'modelForSequenceClassification', './test/bert_model/')  # E.g. model was saved using `save_pretrained('./test/saved_model/')`
+            model = torch.hub.load('huggingface/transformers', 'modelForSequenceClassification', 'bert-base-uncased', output_attention=True)  # Update configuration during loading
             assert model.config.output_attention == True
             # Loading from a TF checkpoint file instead of a PyTorch model (slower)
             config = AutoConfig.from_json_file('./tf_model/bert_tf_model_config.json')
-            model = torch.hub.load('huggingface/pytorch-transformers', 'modelForSequenceClassification', './tf_model/bert_tf_checkpoint.ckpt.index', from_tf=True, config=config)
+            model = torch.hub.load('huggingface/transformers', 'modelForSequenceClassification', './tf_model/bert_tf_checkpoint.ckpt.index', from_tf=True, config=config)
 
         """
 
@@ -100,13 +100,13 @@ def modelForQuestionAnswering(*args, **kwargs):
         # Using torch.hub !
         import torch
 
-        model = torch.hub.load('huggingface/pytorch-transformers', 'modelForQuestionAnswering', 'bert-base-uncased')    # Download model and configuration from S3 and cache.
-        model = torch.hub.load('huggingface/pytorch-transformers', 'modelForQuestionAnswering', './test/bert_model/')  # E.g. model was saved using `save_pretrained('./test/saved_model/')`
-        model = torch.hub.load('huggingface/pytorch-transformers', 'modelForQuestionAnswering', 'bert-base-uncased', output_attention=True)  # Update configuration during loading
+        model = torch.hub.load('huggingface/transformers', 'modelForQuestionAnswering', 'bert-base-uncased')    # Download model and configuration from S3 and cache.
+        model = torch.hub.load('huggingface/transformers', 'modelForQuestionAnswering', './test/bert_model/')  # E.g. model was saved using `save_pretrained('./test/saved_model/')`
+        model = torch.hub.load('huggingface/transformers', 'modelForQuestionAnswering', 'bert-base-uncased', output_attention=True)  # Update configuration during loading
         assert model.config.output_attention == True
         # Loading from a TF checkpoint file instead of a PyTorch model (slower)
         config = AutoConfig.from_json_file('./tf_model/bert_tf_model_config.json')
-        model = torch.hub.load('huggingface/pytorch-transformers', 'modelForQuestionAnswering', './tf_model/bert_tf_checkpoint.ckpt.index', from_tf=True, config=config)
+        model = torch.hub.load('huggingface/transformers', 'modelForQuestionAnswering', './tf_model/bert_tf_checkpoint.ckpt.index', from_tf=True, config=config)
 
     """
     return AutoModelForQuestionAnswering.from_pretrained(*args, **kwargs)

pytorch_transformers/__init__.py

-__version__ = "1.2.0"
-# Work around to update TensorFlow's absl.logging threshold which alters the
-# default Python logging output behavior when present.
-# see: https://github.com/abseil/abseil-py/issues/99
-# and: https://github.com/tensorflow/tensorflow/issues/26691#issuecomment-500369493
-try:
-    import absl.logging
-    absl.logging.set_verbosity('info')
-    absl.logging.set_stderrthreshold('info')
-    absl.logging._warn_preinit_stderr = False
-except:
-    pass
-
-# Tokenizer
-from .tokenization_utils import (PreTrainedTokenizer)
-from .tokenization_auto import AutoTokenizer
-from .tokenization_bert import BertTokenizer, BasicTokenizer, WordpieceTokenizer
-from .tokenization_openai import OpenAIGPTTokenizer
-from .tokenization_transfo_xl import (TransfoXLTokenizer, TransfoXLCorpus)
-from .tokenization_gpt2 import GPT2Tokenizer
-from .tokenization_xlnet import XLNetTokenizer, SPIECE_UNDERLINE
-from .tokenization_xlm import XLMTokenizer
-from .tokenization_roberta import RobertaTokenizer
-from .tokenization_distilbert import DistilBertTokenizer
-
-# Configurations
-from .configuration_utils import PretrainedConfig
-from .configuration_auto import AutoConfig
-from .configuration_bert import BertConfig, BERT_PRETRAINED_CONFIG_ARCHIVE_MAP
-from .configuration_openai import OpenAIGPTConfig, OPENAI_GPT_PRETRAINED_CONFIG_ARCHIVE_MAP
-from .configuration_transfo_xl import TransfoXLConfig, TRANSFO_XL_PRETRAINED_CONFIG_ARCHIVE_MAP
-from .configuration_gpt2 import GPT2Config, GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP
-from .configuration_xlnet import XLNetConfig, XLNET_PRETRAINED_CONFIG_ARCHIVE_MAP
-from .configuration_xlm import XLMConfig, XLM_PRETRAINED_CONFIG_ARCHIVE_MAP
-from .configuration_roberta import RobertaConfig, ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP
-from .configuration_distilbert import DistilBertConfig, DISTILBERT_PRETRAINED_CONFIG_ARCHIVE_MAP
-
-# Modeling
-from .modeling_utils import (PreTrainedModel, prune_layer, Conv1D)
-from .modeling_auto import (AutoModel, AutoModelForSequenceClassification, AutoModelForQuestionAnswering,
-                            AutoModelWithLMHead)
-
-from .modeling_bert import (BertPreTrainedModel, BertModel, BertForPreTraining,
-                            BertForMaskedLM, BertForNextSentencePrediction,
-                            BertForSequenceClassification, BertForMultipleChoice,
-                            BertForTokenClassification, BertForQuestionAnswering,
-                            load_tf_weights_in_bert, BERT_PRETRAINED_MODEL_ARCHIVE_MAP)
-from .modeling_openai import (OpenAIGPTPreTrainedModel, OpenAIGPTModel,
-                              OpenAIGPTLMHeadModel, OpenAIGPTDoubleHeadsModel,
-                              load_tf_weights_in_openai_gpt, OPENAI_GPT_PRETRAINED_MODEL_ARCHIVE_MAP)
-from .modeling_transfo_xl import (TransfoXLPreTrainedModel, TransfoXLModel, TransfoXLLMHeadModel,
-                                  load_tf_weights_in_transfo_xl, TRANSFO_XL_PRETRAINED_MODEL_ARCHIVE_MAP)
-from .modeling_gpt2 import (GPT2PreTrainedModel, GPT2Model,
-                            GPT2LMHeadModel, GPT2DoubleHeadsModel,
-                            load_tf_weights_in_gpt2, GPT2_PRETRAINED_MODEL_ARCHIVE_MAP)
-from .modeling_xlnet import (XLNetPreTrainedModel, XLNetModel, XLNetLMHeadModel,
-                             XLNetForSequenceClassification, XLNetForQuestionAnswering, XLNetForMultipleChoice,
-                             load_tf_weights_in_xlnet, XLNET_PRETRAINED_MODEL_ARCHIVE_MAP)
-from .modeling_xlm import (XLMPreTrainedModel , XLMModel,
-                           XLMWithLMHeadModel, XLMForSequenceClassification,
-                           XLMForQuestionAnswering, XLM_PRETRAINED_MODEL_ARCHIVE_MAP)
-from .modeling_roberta import (RobertaForMaskedLM, RobertaModel, RobertaForSequenceClassification,
-                               RobertaForMultipleChoice, ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP)
-from .modeling_distilbert import (DistilBertForMaskedLM, DistilBertModel,
-                               DistilBertForSequenceClassification, DistilBertForQuestionAnswering,
-                               DISTILBERT_PRETRAINED_MODEL_ARCHIVE_MAP)
-
-# Optimization
-from .optimization import (AdamW, ConstantLRSchedule, WarmupConstantSchedule, WarmupCosineSchedule,
-                           WarmupCosineWithHardRestartsSchedule, WarmupLinearSchedule)
-
-# Files and general utilities
-from .file_utils import (PYTORCH_TRANSFORMERS_CACHE, PYTORCH_PRETRAINED_BERT_CACHE,
-                         cached_path, add_start_docstrings, add_end_docstrings,
-                         WEIGHTS_NAME, TF_WEIGHTS_NAME, CONFIG_NAME)

requirements.txt

-# PyTorch
-torch>=1.0.0
 # progress bars in model download and training scripts
 tqdm
 # Accessing files from S3 directly.

setup.py

@@ -13,11 +13,11 @@ To create the package for pypi.
 4. Build both the sources and the wheel. Do not change anything in setup.py between
    creating the wheel and the source distribution (obviously).
 
-   For the wheel, run: "python setup.py bdist_wheel" in the top level allennlp directory.
+   For the wheel, run: "python setup.py bdist_wheel" in the top level directory.
    (this will build a wheel for the python version you use to build it - make sure you use python 3.x).
 
    For the sources, run: "python setup.py sdist"
-   You should now have a /dist directory with both .whl and .tar.gz source versions of allennlp.
+   You should now have a /dist directory with both .whl and .tar.gz source versions.
 
 5. Check that everything looks correct by uploading the package to the pypi test server:
 
@@ -25,7 +25,7 @@ To create the package for pypi.
    (pypi suggest using twine as other methods upload files via plaintext.)
 
    Check that you can install it in a virtualenv by running:
-   pip install -i https://testpypi.python.org/pypi pytorch-transformers
+   pip install -i https://testpypi.python.org/pypi transformers
 
 6. Upload the final version to actual pypi:
    twine upload dist/* -r pypi
@@ -37,20 +37,19 @@ from io import open
 from setuptools import find_packages, setup
 
 setup(
-    name="pytorch_transformers",
-    version="1.2.0",
-    author="Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Google AI Language Team Authors, Open AI team Authors",
+    name="transformers",
+    version="2.0.0",
+    author="Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Google AI Language Team Authors, Open AI team Authors, Facebook AI Authors, Carnegie Mellon University Authors",
     author_email="thomas@huggingface.co",
-    description="Repository of pre-trained NLP Transformer models: BERT & RoBERTa, GPT & GPT-2, Transformer-XL, XLNet and XLM",
+    description="State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch",
     long_description=open("README.md", "r", encoding='utf-8').read(),
     long_description_content_type="text/markdown",
-    keywords='NLP deep learning transformer pytorch BERT GPT GPT-2 google openai CMU',
+    keywords='NLP deep learning transformer pytorch tensorflow BERT GPT GPT-2 google openai CMU',
     license='Apache',
-    url="https://github.com/huggingface/pytorch-transformers",
+    url="https://github.com/huggingface/transformers",
     packages=find_packages(exclude=["*.tests", "*.tests.*",
                                     "tests.*", "tests"]),
-    install_requires=['torch>=1.0.0',
-                      'numpy',
+    install_requires=['numpy',
                       'boto3',
                       'requests',
                       'tqdm',
@@ -59,7 +58,7 @@ setup(
                       'sacremoses'],
     entry_points={
       'console_scripts': [
-        "pytorch_transformers=pytorch_transformers.__main__:main",
+        "transformers=transformers.__main__:main",
       ]
     },
     # python_requires='>=3.5.0',

transformers/__init__.py

+__version__ = "2.0.0"
+
+# Work around to update TensorFlow's absl.logging threshold which alters the
+# default Python logging output behavior when present.
+# see: https://github.com/abseil/abseil-py/issues/99
+# and: https://github.com/tensorflow/tensorflow/issues/26691#issuecomment-500369493
+try:
+    import absl.logging
+    absl.logging.set_verbosity('info')
+    absl.logging.set_stderrthreshold('info')
+    absl.logging._warn_preinit_stderr = False
+except:
+    pass
+
+import logging
+
+logger = logging.getLogger(__name__)  # pylint: disable=invalid-name
+
+# Files and general utilities
+from .file_utils import (TRANSFORMERS_CACHE, PYTORCH_TRANSFORMERS_CACHE, PYTORCH_PRETRAINED_BERT_CACHE,
+                         cached_path, add_start_docstrings, add_end_docstrings,
+                         WEIGHTS_NAME, TF2_WEIGHTS_NAME, TF_WEIGHTS_NAME, CONFIG_NAME,
+                         is_tf_available, is_torch_available)
+
+from .data import (is_sklearn_available,
+                   InputExample, InputFeatures, DataProcessor,
+                   glue_output_modes, glue_convert_examples_to_features,
+                   glue_processors, glue_tasks_num_labels)
+
+if is_sklearn_available():
+    from .data import glue_compute_metrics
+
+# Tokenizers
+from .tokenization_utils import (PreTrainedTokenizer)
+from .tokenization_auto import AutoTokenizer
+from .tokenization_bert import BertTokenizer, BasicTokenizer, WordpieceTokenizer
+from .tokenization_openai import OpenAIGPTTokenizer
+from .tokenization_transfo_xl import (TransfoXLTokenizer, TransfoXLCorpus)
+from .tokenization_gpt2 import GPT2Tokenizer
+from .tokenization_xlnet import XLNetTokenizer, SPIECE_UNDERLINE
+from .tokenization_xlm import XLMTokenizer
+from .tokenization_roberta import RobertaTokenizer
+from .tokenization_distilbert import DistilBertTokenizer
+
+# Configurations
+from .configuration_utils import PretrainedConfig
+from .configuration_auto import AutoConfig
+from .configuration_bert import BertConfig, BERT_PRETRAINED_CONFIG_ARCHIVE_MAP
+from .configuration_openai import OpenAIGPTConfig, OPENAI_GPT_PRETRAINED_CONFIG_ARCHIVE_MAP
+from .configuration_transfo_xl import TransfoXLConfig, TRANSFO_XL_PRETRAINED_CONFIG_ARCHIVE_MAP
+from .configuration_gpt2 import GPT2Config, GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP
+from .configuration_xlnet import XLNetConfig, XLNET_PRETRAINED_CONFIG_ARCHIVE_MAP
+from .configuration_xlm import XLMConfig, XLM_PRETRAINED_CONFIG_ARCHIVE_MAP
+from .configuration_roberta import RobertaConfig, ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP
+from .configuration_distilbert import DistilBertConfig, DISTILBERT_PRETRAINED_CONFIG_ARCHIVE_MAP
+
+# Modeling
+if is_torch_available():
+    from .modeling_utils import (PreTrainedModel, prune_layer, Conv1D)
+    from .modeling_auto import (AutoModel, AutoModelForSequenceClassification, AutoModelForQuestionAnswering,
+                                AutoModelWithLMHead)
+
+    from .modeling_bert import (BertPreTrainedModel, BertModel, BertForPreTraining,
+                                BertForMaskedLM, BertForNextSentencePrediction,
+                                BertForSequenceClassification, BertForMultipleChoice,
+                                BertForTokenClassification, BertForQuestionAnswering,
+                                load_tf_weights_in_bert, BERT_PRETRAINED_MODEL_ARCHIVE_MAP)
+    from .modeling_openai import (OpenAIGPTPreTrainedModel, OpenAIGPTModel,
+                                OpenAIGPTLMHeadModel, OpenAIGPTDoubleHeadsModel,
+                                load_tf_weights_in_openai_gpt, OPENAI_GPT_PRETRAINED_MODEL_ARCHIVE_MAP)
+    from .modeling_transfo_xl import (TransfoXLPreTrainedModel, TransfoXLModel, TransfoXLLMHeadModel,
+                                    load_tf_weights_in_transfo_xl, TRANSFO_XL_PRETRAINED_MODEL_ARCHIVE_MAP)
+    from .modeling_gpt2 import (GPT2PreTrainedModel, GPT2Model,
+                                GPT2LMHeadModel, GPT2DoubleHeadsModel,
+                                load_tf_weights_in_gpt2, GPT2_PRETRAINED_MODEL_ARCHIVE_MAP)
+    from .modeling_xlnet import (XLNetPreTrainedModel, XLNetModel, XLNetLMHeadModel,
+                                XLNetForSequenceClassification, XLNetForMultipleChoice,
+                                XLNetForQuestionAnsweringSimple, XLNetForQuestionAnswering,
+                                load_tf_weights_in_xlnet, XLNET_PRETRAINED_MODEL_ARCHIVE_MAP)
+    from .modeling_xlm import (XLMPreTrainedModel , XLMModel,
+                            XLMWithLMHeadModel, XLMForSequenceClassification,
+                            XLMForQuestionAnswering, XLMForQuestionAnsweringSimple,
+                            XLM_PRETRAINED_MODEL_ARCHIVE_MAP)
+    from .modeling_roberta import (RobertaForMaskedLM, RobertaModel,
+                                RobertaForSequenceClassification, RobertaForMultipleChoice,
+                                ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP)
+    from .modeling_distilbert import (DistilBertForMaskedLM, DistilBertModel,
+                                DistilBertForSequenceClassification, DistilBertForQuestionAnswering,
+                                DISTILBERT_PRETRAINED_MODEL_ARCHIVE_MAP)
+
+    # Optimization
+    from .optimization import (AdamW, ConstantLRSchedule, WarmupConstantSchedule, WarmupCosineSchedule,
+                               WarmupCosineWithHardRestartsSchedule, WarmupLinearSchedule)
+
+
+# TensorFlow
+if is_tf_available():
+    from .modeling_tf_utils import TFPreTrainedModel, TFSharedEmbeddings, TFSequenceSummary
+    from .modeling_tf_auto import (TFAutoModel, TFAutoModelForSequenceClassification, TFAutoModelForQuestionAnswering,
+                                   TFAutoModelWithLMHead)
+
+    from .modeling_tf_bert import (TFBertPreTrainedModel, TFBertMainLayer, TFBertEmbeddings,
+                                   TFBertModel, TFBertForPreTraining,
+                                   TFBertForMaskedLM, TFBertForNextSentencePrediction,
+                                   TFBertForSequenceClassification, TFBertForMultipleChoice,
+                                   TFBertForTokenClassification, TFBertForQuestionAnswering,
+                                   load_bert_pt_weights_in_tf2,
+                                   TF_BERT_PRETRAINED_MODEL_ARCHIVE_MAP)
+
+    from .modeling_tf_gpt2 import (TFGPT2PreTrainedModel, TFGPT2MainLayer,
+                                   TFGPT2Model, TFGPT2LMHeadModel, TFGPT2DoubleHeadsModel,
+                                   load_gpt2_pt_weights_in_tf2,
+                                   TF_GPT2_PRETRAINED_MODEL_ARCHIVE_MAP)
+
+    from .modeling_tf_openai import (TFOpenAIGPTPreTrainedModel, TFOpenAIGPTMainLayer,
+                                     TFOpenAIGPTModel, TFOpenAIGPTLMHeadModel, TFOpenAIGPTDoubleHeadsModel,
+                                     load_openai_gpt_pt_weights_in_tf2,
+                                     TF_OPENAI_GPT_PRETRAINED_MODEL_ARCHIVE_MAP)
+
+    from .modeling_tf_transfo_xl import (TFTransfoXLPreTrainedModel, TFTransfoXLMainLayer,
+                                         TFTransfoXLModel, TFTransfoXLLMHeadModel,
+                                         load_transfo_xl_pt_weights_in_tf2,
+                                         TF_TRANSFO_XL_PRETRAINED_MODEL_ARCHIVE_MAP)
+
+    from .modeling_tf_xlnet import (TFXLNetPreTrainedModel, TFXLNetMainLayer,
+                                    TFXLNetModel, TFXLNetLMHeadModel,
+                                    TFXLNetForSequenceClassification,
+                                    TFXLNetForQuestionAnsweringSimple,
+                                    load_xlnet_pt_weights_in_tf2,
+                                    TF_XLNET_PRETRAINED_MODEL_ARCHIVE_MAP)
+
+    from .modeling_tf_xlm import (TFXLMPreTrainedModel, TFXLMMainLayer,
+                                  TFXLMModel, TFXLMWithLMHeadModel,
+                                  TFXLMForSequenceClassification,
+                                  TFXLMForQuestionAnsweringSimple,
+                                  load_xlm_pt_weights_in_tf2,
+                                  TF_XLM_PRETRAINED_MODEL_ARCHIVE_MAP)
+
+    from .modeling_tf_roberta import (TFRobertaPreTrainedModel, TFRobertaMainLayer,
+                                      TFRobertaModel, TFRobertaForMaskedLM,
+                                      TFRobertaForSequenceClassification,
+                                      load_roberta_pt_weights_in_tf2,
+                                      TF_ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP)
+
+    from .modeling_tf_distilbert import (TFDistilBertPreTrainedModel, TFDistilBertMainLayer,
+                                         TFDistilBertModel, TFDistilBertForMaskedLM,
+                                         TFDistilBertForSequenceClassification,
+                                         TFDistilBertForQuestionAnswering,
+                                         load_distilbert_pt_weights_in_tf2,
+                                         TF_DISTILBERT_PRETRAINED_MODEL_ARCHIVE_MAP)
+
+# TF 2.0 <=> PyTorch conversion utilities
+if is_tf_available() and is_torch_available():
+    from .modeling_tf_pytorch_utils import (convert_tf_weight_name_to_pt_weight_name,
+                                            load_pytorch_checkpoint_in_tf2_model,
+                                            load_pytorch_weights_in_tf2_model,
+                                            load_pytorch_model_in_tf2_model,
+                                            load_tf2_checkpoint_in_pytorch_model,
+                                            load_tf2_weights_in_pytorch_model,
+                                            load_tf2_model_in_pytorch_model)
+
+if not is_tf_available() and not is_torch_available():
+    logger.warning("Neither PyTorch nor TensorFlow >= 2.0 have been found."
+                   "Models won't be available and only tokenizers, configuration"
+                   "and file/data utilities can be used.")

pytorch_transformers/__main__.py → transformers/__main__.py

@@ -3,36 +3,37 @@ def main():
     import sys
     if (len(sys.argv) < 4 or len(sys.argv) > 6) or sys.argv[1] not in ["bert", "gpt", "transfo_xl", "gpt2", "xlnet", "xlm"]:
         print(
-        "Should be used as one of: \n"
-        ">> pytorch_transformers bert TF_CHECKPOINT TF_CONFIG PYTORCH_DUMP_OUTPUT, \n"
-        ">> pytorch_transformers gpt OPENAI_GPT_CHECKPOINT_FOLDER_PATH PYTORCH_DUMP_OUTPUT [OPENAI_GPT_CONFIG], \n"
-        ">> pytorch_transformers transfo_xl TF_CHECKPOINT_OR_DATASET PYTORCH_DUMP_OUTPUT [TF_CONFIG] or \n"
-        ">> pytorch_transformers gpt2 TF_CHECKPOINT PYTORCH_DUMP_OUTPUT [GPT2_CONFIG] or \n"
-        ">> pytorch_transformers xlnet TF_CHECKPOINT TF_CONFIG PYTORCH_DUMP_OUTPUT [FINETUNING_TASK_NAME] or \n"
-        ">> pytorch_transformers xlm XLM_CHECKPOINT_PATH PYTORCH_DUMP_OUTPUT")
+        "This command line utility let you convert original (author released) model checkpoint to pytorch.\n"
+        "It should be used as one of: \n"
+        ">> transformers bert TF_CHECKPOINT TF_CONFIG PYTORCH_DUMP_OUTPUT, \n"
+        ">> transformers gpt OPENAI_GPT_CHECKPOINT_FOLDER_PATH PYTORCH_DUMP_OUTPUT [OPENAI_GPT_CONFIG], \n"
+        ">> transformers transfo_xl TF_CHECKPOINT_OR_DATASET PYTORCH_DUMP_OUTPUT [TF_CONFIG] or \n"
+        ">> transformers gpt2 TF_CHECKPOINT PYTORCH_DUMP_OUTPUT [GPT2_CONFIG] or \n"
+        ">> transformers xlnet TF_CHECKPOINT TF_CONFIG PYTORCH_DUMP_OUTPUT [FINETUNING_TASK_NAME] or \n"
+        ">> transformers xlm XLM_CHECKPOINT_PATH PYTORCH_DUMP_OUTPUT")
     else:
         if sys.argv[1] == "bert":
             try:
-                from .convert_tf_checkpoint_to_pytorch import convert_tf_checkpoint_to_pytorch
+                from .convert_bert_original_tf_checkpoint_to_pytorch import convert_tf_checkpoint_to_pytorch
             except ImportError:
-                print("pytorch_transformers can only be used from the commandline to convert TensorFlow models in PyTorch, "
+                print("transformers can only be used from the commandline to convert TensorFlow models in PyTorch, "
                     "In that case, it requires TensorFlow to be installed. Please see "
                     "https://www.tensorflow.org/install/ for installation instructions.")
                 raise
 
             if len(sys.argv) != 5:
                 # pylint: disable=line-too-long
-                print("Should be used as `pytorch_transformers bert TF_CHECKPOINT TF_CONFIG PYTORCH_DUMP_OUTPUT`")
+                print("Should be used as `transformers bert TF_CHECKPOINT TF_CONFIG PYTORCH_DUMP_OUTPUT`")
             else:
                 PYTORCH_DUMP_OUTPUT = sys.argv.pop()
                 TF_CONFIG = sys.argv.pop()
                 TF_CHECKPOINT = sys.argv.pop()
                 convert_tf_checkpoint_to_pytorch(TF_CHECKPOINT, TF_CONFIG, PYTORCH_DUMP_OUTPUT)
         elif sys.argv[1] == "gpt":
-            from .convert_openai_checkpoint_to_pytorch import convert_openai_checkpoint_to_pytorch
+            from .convert_openai_original_tf_checkpoint_to_pytorch import convert_openai_checkpoint_to_pytorch
             if len(sys.argv) < 4 or len(sys.argv) > 5:
                 # pylint: disable=line-too-long
-                print("Should be used as `pytorch_transformers gpt OPENAI_GPT_CHECKPOINT_FOLDER_PATH PYTORCH_DUMP_OUTPUT [OPENAI_GPT_CONFIG]`")
+                print("Should be used as `transformers gpt OPENAI_GPT_CHECKPOINT_FOLDER_PATH PYTORCH_DUMP_OUTPUT [OPENAI_GPT_CONFIG]`")
             else:
                 OPENAI_GPT_CHECKPOINT_FOLDER_PATH = sys.argv[2]
                 PYTORCH_DUMP_OUTPUT = sys.argv[3]
@@ -45,15 +46,15 @@ def main():
                                                     PYTORCH_DUMP_OUTPUT)
         elif sys.argv[1] == "transfo_xl":
             try:
-                from .convert_transfo_xl_checkpoint_to_pytorch import convert_transfo_xl_checkpoint_to_pytorch
+                from .convert_transfo_xl_original_tf_checkpoint_to_pytorch import convert_transfo_xl_checkpoint_to_pytorch
             except ImportError:
-                print("pytorch_transformers can only be used from the commandline to convert TensorFlow models in PyTorch, "
+                print("transformers can only be used from the commandline to convert TensorFlow models in PyTorch, "
                     "In that case, it requires TensorFlow to be installed. Please see "
                     "https://www.tensorflow.org/install/ for installation instructions.")
                 raise
             if len(sys.argv) < 4 or len(sys.argv) > 5:
                 # pylint: disable=line-too-long
-                print("Should be used as `pytorch_transformers transfo_xl TF_CHECKPOINT/TF_DATASET_FILE PYTORCH_DUMP_OUTPUT [TF_CONFIG]`")
+                print("Should be used as `transformers transfo_xl TF_CHECKPOINT/TF_DATASET_FILE PYTORCH_DUMP_OUTPUT [TF_CONFIG]`")
             else:
                 if 'ckpt' in sys.argv[2].lower():
                     TF_CHECKPOINT = sys.argv[2]
@@ -69,16 +70,16 @@ def main():
                 convert_transfo_xl_checkpoint_to_pytorch(TF_CHECKPOINT, TF_CONFIG, PYTORCH_DUMP_OUTPUT, TF_DATASET_FILE)
         elif sys.argv[1] == "gpt2":
             try:
-                from .convert_gpt2_checkpoint_to_pytorch import convert_gpt2_checkpoint_to_pytorch
+                from .convert_gpt2_original_tf_checkpoint_to_pytorch import convert_gpt2_checkpoint_to_pytorch
             except ImportError:
-                print("pytorch_transformers can only be used from the commandline to convert TensorFlow models in PyTorch, "
+                print("transformers can only be used from the commandline to convert TensorFlow models in PyTorch, "
                     "In that case, it requires TensorFlow to be installed. Please see "
                     "https://www.tensorflow.org/install/ for installation instructions.")
                 raise
 
             if len(sys.argv) < 4 or len(sys.argv) > 5:
                 # pylint: disable=line-too-long
-                print("Should be used as `pytorch_transformers gpt2 TF_CHECKPOINT PYTORCH_DUMP_OUTPUT [TF_CONFIG]`")
+                print("Should be used as `transformers gpt2 TF_CHECKPOINT PYTORCH_DUMP_OUTPUT [TF_CONFIG]`")
             else:
                 TF_CHECKPOINT = sys.argv[2]
                 PYTORCH_DUMP_OUTPUT = sys.argv[3]
@@ -89,16 +90,16 @@ def main():
                 convert_gpt2_checkpoint_to_pytorch(TF_CHECKPOINT, TF_CONFIG, PYTORCH_DUMP_OUTPUT)
         elif sys.argv[1] == "xlnet":
             try:
-                from .convert_xlnet_checkpoint_to_pytorch import convert_xlnet_checkpoint_to_pytorch
+                from .convert_xlnet_original_tf_checkpoint_to_pytorch import convert_xlnet_checkpoint_to_pytorch
             except ImportError:
-                print("pytorch_transformers can only be used from the commandline to convert TensorFlow models in PyTorch, "
+                print("transformers can only be used from the commandline to convert TensorFlow models in PyTorch, "
                     "In that case, it requires TensorFlow to be installed. Please see "
                     "https://www.tensorflow.org/install/ for installation instructions.")
                 raise
 
             if len(sys.argv) < 5 or len(sys.argv) > 6:
                 # pylint: disable=line-too-long
-                print("Should be used as `pytorch_transformers xlnet TF_CHECKPOINT TF_CONFIG PYTORCH_DUMP_OUTPUT [FINETUNING_TASK_NAME]`")
+                print("Should be used as `transformers xlnet TF_CHECKPOINT TF_CONFIG PYTORCH_DUMP_OUTPUT [FINETUNING_TASK_NAME]`")
             else:
                 TF_CHECKPOINT = sys.argv[2]
                 TF_CONFIG = sys.argv[3]
@@ -113,11 +114,11 @@ def main():
                                                     PYTORCH_DUMP_OUTPUT,
                                                     FINETUNING_TASK)
         elif sys.argv[1] == "xlm":
-            from .convert_xlm_checkpoint_to_pytorch import convert_xlm_checkpoint_to_pytorch
+            from .convert_xlm_original_pytorch_checkpoint_to_pytorch import convert_xlm_checkpoint_to_pytorch
 
             if len(sys.argv) != 4:
                 # pylint: disable=line-too-long
-                print("Should be used as `pytorch_transformers xlm XLM_CHECKPOINT_PATH PYTORCH_DUMP_OUTPUT`")
+                print("Should be used as `transformers xlm XLM_CHECKPOINT_PATH PYTORCH_DUMP_OUTPUT`")
             else:
                 XLM_CHECKPOINT_PATH = sys.argv[2]
                 PYTORCH_DUMP_OUTPUT = sys.argv[3]

pytorch_transformers/configuration_auto.py → transformers/configuration_auto.py

@@ -31,7 +31,7 @@ logger = logging.getLogger(__name__)
 
 
 class AutoConfig(object):
-    r""":class:`~pytorch_transformers.AutoConfig` is a generic configuration class
+    r""":class:`~transformers.AutoConfig` is a generic configuration class
         that will be instantiated as one of the configuration classes of the library
         when created with the `AutoConfig.from_pretrained(pretrained_model_name_or_path)`
         class method.
@@ -76,7 +76,7 @@ class AutoConfig(object):
             pretrained_model_name_or_path: either:
 
                 - a string with the `shortcut name` of a pre-trained model configuration to load from cache or download, e.g.: ``bert-base-uncased``.
-                - a path to a `directory` containing a configuration file saved using the :func:`~pytorch_transformers.PretrainedConfig.save_pretrained` method, e.g.: ``./my_model_directory/``.
+                - a path to a `directory` containing a configuration file saved using the :func:`~transformers.PretrainedConfig.save_pretrained` method, e.g.: ``./my_model_directory/``.
                 - a path or url to a saved configuration JSON `file`, e.g.: ``./my_model_directory/configuration.json``.
 
             cache_dir: (`optional`) string:

pytorch_transformers/configuration_bert.py → transformers/configuration_bert.py

@@ -45,7 +45,7 @@ BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
 
 class BertConfig(PretrainedConfig):
     r"""
-        :class:`~pytorch_transformers.BertConfig` is the configuration class to store the configuration of a
+        :class:`~transformers.BertConfig` is the configuration class to store the configuration of a
         `BertModel`.
 
 
@@ -58,7 +58,7 @@ class BertConfig(PretrainedConfig):
             intermediate_size: The size of the "intermediate" (i.e., feed-forward)
                 layer in the Transformer encoder.
             hidden_act: The non-linear activation function (function or string) in the
-                encoder and pooler. If string, "gelu", "relu" and "swish" are supported.
+                encoder and pooler. If string, "gelu", "relu", "swish" and "gelu_new" are supported.
             hidden_dropout_prob: The dropout probabilitiy for all fully connected
                 layers in the embeddings, encoder, and pooler.
             attention_probs_dropout_prob: The dropout ratio for the attention

pytorch_transformers/configuration_distilbert.py → transformers/configuration_distilbert.py

@@ -37,7 +37,7 @@ class DistilBertConfig(PretrainedConfig):
     def __init__(self,
                  vocab_size_or_config_json_file=30522,
                  max_position_embeddings=512,
-                 sinusoidal_pos_embds=True,
+                 sinusoidal_pos_embds=False,
                  n_layers=6,
                  n_heads=12,
                  dim=768,

pytorch_transformers/configuration_gpt2.py → transformers/configuration_gpt2.py

@@ -28,7 +28,8 @@ logger = logging.getLogger(__name__)
 
 GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP = {"gpt2": "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-config.json",
                                       "gpt2-medium": "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-medium-config.json",
-                                      "gpt2-large": "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-large-config.json"}
+                                      "gpt2-large": "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-large-config.json",
+                                      "distilgpt2": "https://s3.amazonaws.com/models.huggingface.co/bert/distilgpt2-config.json",}
 
 class GPT2Config(PretrainedConfig):
     """Configuration class to store the configuration of a `GPT2Model`.

pytorch_transformers/configuration_openai.py → transformers/configuration_openai.py

@@ -36,7 +36,6 @@ class OpenAIGPTConfig(PretrainedConfig):
 
     Args:
         vocab_size_or_config_json_file: Vocabulary size of `inputs_ids` in `OpenAIGPTModel` or a configuration json file.
-        n_special: The number of special tokens to learn during fine-tuning ('[SEP]', '[CLF]', ...)
         n_positions: Number of positional embeddings.
         n_ctx: Size of the causal mask (usually same as n_positions).
         n_embd: Dimensionality of the embeddings and hidden states.

pytorch_transformers/configuration_transfo_xl.py → transformers/configuration_transfo_xl.py

@@ -95,19 +95,12 @@ class TransfoXLConfig(PretrainedConfig):
                  init_range=0.01,
                  proj_init_std=0.01,
                  init_std=0.02,
+                 layer_norm_epsilon=1e-5,
                  **kwargs):
         """Constructs TransfoXLConfig.
         """
         super(TransfoXLConfig, self).__init__(**kwargs)
-
-        if isinstance(vocab_size_or_config_json_file, str) or (sys.version_info[0] == 2
-                        and isinstance(vocab_size_or_config_json_file, unicode)):
-            with open(vocab_size_or_config_json_file, "r", encoding='utf-8') as reader:
-                json_config = json.loads(reader.read())
-            for key, value in json_config.items():
-                self.__dict__[key] = value
-        elif isinstance(vocab_size_or_config_json_file, int):
-            self.n_token = vocab_size_or_config_json_file
+        self.n_token = vocab_size_or_config_json_file if isinstance(vocab_size_or_config_json_file, int) else -1
         self.cutoffs = []
         self.cutoffs.extend(cutoffs)
         self.tie_weight = tie_weight
@@ -138,7 +131,15 @@ class TransfoXLConfig(PretrainedConfig):
         self.init_range = init_range
         self.proj_init_std = proj_init_std
         self.init_std = init_std
-        else:
+        self.layer_norm_epsilon = layer_norm_epsilon
+
+        if isinstance(vocab_size_or_config_json_file, str) or (sys.version_info[0] == 2
+                        and isinstance(vocab_size_or_config_json_file, unicode)):
+            with open(vocab_size_or_config_json_file, "r", encoding='utf-8') as reader:
+                json_config = json.loads(reader.read())
+            for key, value in json_config.items():
+                self.__dict__[key] = value
+        elif not isinstance(vocab_size_or_config_json_file, int):
             raise ValueError("First argument must be either a vocabulary size (int)"
                              " or the path to a pretrained model config file (str)")
 

pytorch_transformers/configuration_utils.py → transformers/configuration_utils.py

@@ -54,11 +54,12 @@ class PretrainedConfig(object):
         self.output_attentions = kwargs.pop('output_attentions', False)
         self.output_hidden_states = kwargs.pop('output_hidden_states', False)
         self.torchscript = kwargs.pop('torchscript', False)
+        self.use_bfloat16 = kwargs.pop('use_bfloat16', False)
         self.pruned_heads = kwargs.pop('pruned_heads', {})
 
     def save_pretrained(self, save_directory):
         """ Save a configuration object to the directory `save_directory`, so that it
-            can be re-loaded using the :func:`~pytorch_transformers.PretrainedConfig.from_pretrained` class method.
+            can be re-loaded using the :func:`~transformers.PretrainedConfig.from_pretrained` class method.
         """
         assert os.path.isdir(save_directory), "Saving path should be a directory where the model and configuration can be saved"
 
@@ -66,16 +67,17 @@ class PretrainedConfig(object):
         output_config_file = os.path.join(save_directory, CONFIG_NAME)
 
         self.to_json_file(output_config_file)
+        logger.info("Configuration saved in {}".format(output_config_file))
 
     @classmethod
     def from_pretrained(cls, pretrained_model_name_or_path, **kwargs):
-        r""" Instantiate a :class:`~pytorch_transformers.PretrainedConfig` (or a derived class) from a pre-trained model configuration.
+        r""" Instantiate a :class:`~transformers.PretrainedConfig` (or a derived class) from a pre-trained model configuration.
 
         Parameters:
             pretrained_model_name_or_path: either:
 
                 - a string with the `shortcut name` of a pre-trained model configuration to load from cache or download, e.g.: ``bert-base-uncased``.
-                - a path to a `directory` containing a configuration file saved using the :func:`~pytorch_transformers.PretrainedConfig.save_pretrained` method, e.g.: ``./my_model_directory/``.
+                - a path to a `directory` containing a configuration file saved using the :func:`~transformers.PretrainedConfig.save_pretrained` method, e.g.: ``./my_model_directory/``.
                 - a path or url to a saved configuration JSON `file`, e.g.: ``./my_model_directory/configuration.json``.
 
             cache_dir: (`optional`) string:
@@ -174,7 +176,7 @@ class PretrainedConfig(object):
         """Constructs a `Config` from a Python dictionary of parameters."""
         config = cls(vocab_size_or_config_json_file=-1)
         for key, value in json_object.items():
-            config.__dict__[key] = value
+            setattr(config, key, value)
         return config
 
     @classmethod

pytorch_transformers/configuration_xlm.py → transformers/configuration_xlm.py

@@ -56,8 +56,6 @@ class XLMConfig(PretrainedConfig):
 
         dropout: The dropout probabilitiy for all fully connected
             layers in the embeddings, encoder, and pooler.
-        dropatt: The dropout ratio for the attention
-            probabilities.
         max_position_embeddings: The maximum sequence length that this model might
             ever be used with. Typically set this to something large just in case
             (e.g., 512 or 1024 or 2048).
@@ -66,7 +64,6 @@ class XLMConfig(PretrainedConfig):
         layer_norm_eps: The epsilon used by LayerNorm.
 
         dropout: float, dropout rate.
-        dropatt: float, dropout rate on attention probabilities.
         init: str, the initialization scheme, either "normal" or "uniform".
         init_range: float, initialize the parameters with a uniform distribution
             in [-init_range, init_range]. Only effective when init="uniform".

pytorch_transformers/configuration_xlnet.py → transformers/configuration_xlnet.py

@@ -49,14 +49,11 @@ class XLNetConfig(PretrainedConfig):
 
         dropout: The dropout probabilitiy for all fully connected
             layers in the embeddings, encoder, and pooler.
-        dropatt: The dropout ratio for the attention
-            probabilities.
         initializer_range: The sttdev of the truncated_normal_initializer for
             initializing all weight matrices.
         layer_norm_eps: The epsilon used by LayerNorm.
 
         dropout: float, dropout rate.
-        dropatt: float, dropout rate on attention probabilities.
         init: str, the initialization scheme, either "normal" or "uniform".
         init_range: float, initialize the parameters with a uniform distribution
             in [-init_range, init_range]. Only effective when init="uniform".
@@ -80,6 +77,7 @@ class XLNetConfig(PretrainedConfig):
                  n_layer=24,
                  n_head=16,
                  d_inner=4096,
+                 max_position_embeddings=512,
                  ff_activation="gelu",
                  untie_r=True,
                  attn_type="bi",
@@ -112,7 +110,7 @@ class XLNetConfig(PretrainedConfig):
             with open(vocab_size_or_config_json_file, "r", encoding='utf-8') as reader:
                 json_config = json.loads(reader.read())
             for key, value in json_config.items():
-                self.__dict__[key] = value
+                setattr(config, key, value)
         elif isinstance(vocab_size_or_config_json_file, int):
             self.n_token = vocab_size_or_config_json_file
             self.d_model = d_model

pytorch_transformers/convert_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_pytorch_checkpoint_to_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_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_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)