[BIG] pytorch-transformers => transformers

examples/run_generation.py

@@ -26,12 +26,12 @@ import torch
 import torch.nn.functional as F
 import numpy as np
 
-from pytorch_transformers import GPT2Config, OpenAIGPTConfig, XLNetConfig, TransfoXLConfig
+from transformers import GPT2Config, OpenAIGPTConfig, XLNetConfig, TransfoXLConfig
 
-from pytorch_transformers import GPT2LMHeadModel, GPT2Tokenizer
-from pytorch_transformers import OpenAIGPTLMHeadModel, OpenAIGPTTokenizer
-from pytorch_transformers import XLNetLMHeadModel, XLNetTokenizer
-from pytorch_transformers import TransfoXLLMHeadModel, TransfoXLTokenizer
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+from transformers import OpenAIGPTLMHeadModel, OpenAIGPTTokenizer
+from transformers import XLNetLMHeadModel, XLNetTokenizer
+from transformers import TransfoXLLMHeadModel, TransfoXLTokenizer
 
 
 logging.basicConfig(format = '%(asctime)s - %(levelname)s - %(name)s -   %(message)s',

examples/run_glue.py

@@ -31,7 +31,7 @@ from torch.utils.data.distributed import DistributedSampler
 from tensorboardX import SummaryWriter
 from tqdm import tqdm, trange
 
-from pytorch_transformers import (WEIGHTS_NAME, BertConfig,
+from transformers import (WEIGHTS_NAME, BertConfig,
                                   BertForSequenceClassification, BertTokenizer,
                                   RobertaConfig,
                                   RobertaForSequenceClassification,
@@ -44,12 +44,12 @@ from pytorch_transformers import (WEIGHTS_NAME, BertConfig,
                                   DistilBertForSequenceClassification,
                                   DistilBertTokenizer)
 
-from pytorch_transformers import AdamW, WarmupLinearSchedule
+from transformers import AdamW, WarmupLinearSchedule
 
-from pytorch_transformers import glue_compute_metrics as compute_metrics
-from pytorch_transformers import glue_output_modes as output_modes
-from pytorch_transformers import glue_processors as processors
-from pytorch_transformers import glue_convert_examples_to_features as convert_examples_to_features
+from transformers import glue_compute_metrics as compute_metrics
+from transformers import glue_output_modes as output_modes
+from transformers import glue_processors as processors
+from transformers import glue_convert_examples_to_features as convert_examples_to_features
 
 logger = logging.getLogger(__name__)
 
@@ -137,7 +137,7 @@ def train(args, train_dataset, model, tokenizer):
                       'token_type_ids': batch[2] if args.model_type in ['bert', 'xlnet'] else None,  # XLM, DistilBERT and RoBERTa don't use segment_ids
                       'labels':         batch[3]}
             outputs = model(**inputs)
-            loss = outputs[0]  # model outputs are always tuple in pytorch-transformers (see doc)
+            loss = outputs[0]  # model outputs are always tuple in transformers (see doc)
 
             if args.n_gpu > 1:
                 loss = loss.mean() # mean() to average on multi-gpu parallel training
@@ -483,7 +483,7 @@ def main():
         checkpoints = [args.output_dir]
         if args.eval_all_checkpoints:
             checkpoints = list(os.path.dirname(c) for c in sorted(glob.glob(args.output_dir + '/**/' + WEIGHTS_NAME, recursive=True)))
-            logging.getLogger("pytorch_transformers.modeling_utils").setLevel(logging.WARN)  # Reduce logging
+            logging.getLogger("transformers.modeling_utils").setLevel(logging.WARN)  # Reduce logging
         logger.info("Evaluate the following checkpoints: %s", checkpoints)
         for checkpoint in checkpoints:
             global_step = checkpoint.split('-')[-1] if len(checkpoints) > 1 else ""

examples/run_lm_finetuning.py

@@ -35,7 +35,7 @@ from torch.utils.data.distributed import DistributedSampler
 from tensorboardX import SummaryWriter
 from tqdm import tqdm, trange
 
-from pytorch_transformers import (WEIGHTS_NAME, AdamW, WarmupLinearSchedule,
+from transformers import (WEIGHTS_NAME, AdamW, WarmupLinearSchedule,
                                   BertConfig, BertForMaskedLM, BertTokenizer,
                                   GPT2Config, GPT2LMHeadModel, GPT2Tokenizer,
                                   OpenAIGPTConfig, OpenAIGPTLMHeadModel, OpenAIGPTTokenizer,
@@ -188,7 +188,7 @@ def train(args, train_dataset, model, tokenizer):
             labels = labels.to(args.device)
             model.train()
             outputs = model(inputs, masked_lm_labels=labels) if args.mlm else model(inputs, labels=labels)
-            loss = outputs[0]  # model outputs are always tuple in pytorch-transformers (see doc)
+            loss = outputs[0]  # model outputs are always tuple in transformers (see doc)
 
             if args.n_gpu > 1:
                 loss = loss.mean()  # mean() to average on multi-gpu parallel training
@@ -481,7 +481,7 @@ def main():
         checkpoints = [args.output_dir]
         if args.eval_all_checkpoints:
             checkpoints = list(os.path.dirname(c) for c in sorted(glob.glob(args.output_dir + '/**/' + WEIGHTS_NAME, recursive=True)))
-            logging.getLogger("pytorch_transformers.modeling_utils").setLevel(logging.WARN)  # Reduce logging
+            logging.getLogger("transformers.modeling_utils").setLevel(logging.WARN)  # Reduce logging
         logger.info("Evaluate the following checkpoints: %s", checkpoints)
         for checkpoint in checkpoints:
             global_step = checkpoint.split('-')[-1] if len(checkpoints) > 1 else ""

examples/run_multiple_choice.py

@@ -32,13 +32,13 @@ from torch.utils.data.distributed import DistributedSampler
 from tensorboardX import SummaryWriter
 from tqdm import tqdm, trange
 
-from pytorch_transformers import (WEIGHTS_NAME, BertConfig,
+from transformers import (WEIGHTS_NAME, BertConfig,
                                   BertForMultipleChoice, BertTokenizer,
                                   XLNetConfig, XLNetForMultipleChoice,
                                   XLNetTokenizer, RobertaConfig,
                                   RobertaForMultipleChoice, RobertaTokenizer)
 
-from pytorch_transformers import AdamW, WarmupLinearSchedule
+from transformers import AdamW, WarmupLinearSchedule
 
 from utils_multiple_choice import (convert_examples_to_features, processors)
 
@@ -141,7 +141,7 @@ def train(args, train_dataset, model, tokenizer):
                       'token_type_ids': batch[2] if args.model_type in ['bert', 'xlnet'] else None,  # XLM don't use segment_ids
                       'labels':         batch[3]}
             outputs = model(**inputs)
-            loss = outputs[0]  # model outputs are always tuple in pytorch-transformers (see doc)
+            loss = outputs[0]  # model outputs are always tuple in transformers (see doc)
 
             if args.n_gpu > 1:
                 loss = loss.mean() # mean() to average on multi-gpu parallel training
@@ -508,7 +508,7 @@ def main():
         checkpoints = [args.output_dir]
         if args.eval_all_checkpoints:
             checkpoints = list(os.path.dirname(c) for c in sorted(glob.glob(args.output_dir + '/**/' + WEIGHTS_NAME, recursive=True)))
-            logging.getLogger("pytorch_transformers.modeling_utils").setLevel(logging.WARN)  # Reduce logging
+            logging.getLogger("transformers.modeling_utils").setLevel(logging.WARN)  # Reduce logging
         logger.info("Evaluate the following checkpoints: %s", checkpoints)
         for checkpoint in checkpoints:
             global_step = checkpoint.split('-')[-1] if len(checkpoints) > 1 else ""
@@ -524,7 +524,7 @@ def main():
         checkpoints = [args.output_dir]
         # if args.eval_all_checkpoints: # can not use this to do test!!
         #     checkpoints = list(os.path.dirname(c) for c in sorted(glob.glob(args.output_dir + '/**/' + WEIGHTS_NAME, recursive=True)))
-        #     logging.getLogger("pytorch_transformers.modeling_utils").setLevel(logging.WARN)  # Reduce logging
+        #     logging.getLogger("transformers.modeling_utils").setLevel(logging.WARN)  # Reduce logging
         logger.info("Evaluate the following checkpoints: %s", checkpoints)
         for checkpoint in checkpoints:
             global_step = checkpoint.split('-')[-1] if len(checkpoints) > 1 else ""

examples/run_squad.py

@@ -32,7 +32,7 @@ from tqdm import tqdm, trange
 
 from tensorboardX import SummaryWriter
 
-from pytorch_transformers import (WEIGHTS_NAME, BertConfig,
+from transformers import (WEIGHTS_NAME, BertConfig,
                                   BertForQuestionAnswering, BertTokenizer,
                                   XLMConfig, XLMForQuestionAnswering,
                                   XLMTokenizer, XLNetConfig,
@@ -40,7 +40,7 @@ from pytorch_transformers import (WEIGHTS_NAME, BertConfig,
                                   XLNetTokenizer,
                                   DistilBertConfig, DistilBertForQuestionAnswering, DistilBertTokenizer)
 
-from pytorch_transformers import AdamW, WarmupLinearSchedule
+from transformers import AdamW, WarmupLinearSchedule
 
 from utils_squad import (read_squad_examples, convert_examples_to_features,
                          RawResult, write_predictions,
@@ -142,7 +142,7 @@ def train(args, train_dataset, model, tokenizer):
                 inputs.update({'cls_index': batch[5],
                                'p_mask':       batch[6]})
             outputs = model(**inputs)
-            loss = outputs[0]  # model outputs are always tuple in pytorch-transformers (see doc)
+            loss = outputs[0]  # model outputs are always tuple in transformers (see doc)
 
             if args.n_gpu > 1:
                 loss = loss.mean() # mean() to average on multi-gpu parallel (not distributed) training
@@ -510,7 +510,7 @@ def main():
         checkpoints = [args.output_dir]
         if args.eval_all_checkpoints:
             checkpoints = list(os.path.dirname(c) for c in sorted(glob.glob(args.output_dir + '/**/' + WEIGHTS_NAME, recursive=True)))
-            logging.getLogger("pytorch_transformers.modeling_utils").setLevel(logging.WARN)  # Reduce model loading logs
+            logging.getLogger("transformers.modeling_utils").setLevel(logging.WARN)  # Reduce model loading logs
 
         logger.info("Evaluate the following checkpoints: %s", checkpoints)
 

examples/run_tf_glue.py

 import tensorflow as tf
 import tensorflow_datasets
-from pytorch_transformers import *
+from transformers import *
 
 # Load dataset, tokenizer, model from pretrained model/vocabulary
 tokenizer = BertTokenizer.from_pretrained('bert-base-cased')

examples/utils_squad.py

@@ -24,7 +24,7 @@ import math
 import collections
 from io import open
 
-from pytorch_transformers.tokenization_bert import BasicTokenizer, whitespace_tokenize
+from transformers.tokenization_bert import BasicTokenizer, whitespace_tokenize
 
 # Required by XLNet evaluation method to compute optimal threshold (see write_predictions_extended() method)
 from utils_squad_evaluate import find_all_best_thresh_v2, make_qid_to_has_ans, get_raw_scores

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)

setup.py

@@ -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
@@ -37,8 +37,8 @@ from io import open
 from setuptools import find_packages, setup
 
 setup(
-    name="pytorch_transformers",
-    version="1.2.0",
+    name="transformers",
+    version="2.0.0",
     author="Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Google AI Language Team Authors, Open AI team Authors",
     author_email="thomas@huggingface.co",
     description="Repository of pre-trained NLP Transformer models: BERT & RoBERTa, GPT & GPT-2, Transformer-XL, XLNet and XLM",
@@ -46,7 +46,7 @@ setup(
     long_description_content_type="text/markdown",
     keywords='NLP deep learning transformer pytorch 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=['numpy',
@@ -58,7 +58,7 @@ setup(
                       'sacremoses'],
     entry_points={
       'console_scripts': [
-        "pytorch_transformers=pytorch_transformers.__main__:main",
+        "transformers=transformers.__main__:main",
       ]
     },
     # python_requires='>=3.5.0',

pytorch_transformers/__init__.py → transformers/__init__.py

-__version__ = "1.2.0"
+__version__ = "2.0.0"
 
 # Work around to update TensorFlow's absl.logging threshold which alters the
 # default Python logging output behavior when present.
@@ -17,7 +17,7 @@ import logging
 logger = logging.getLogger(__name__)  # pylint: disable=invalid-name
 
 # Files and general utilities
-from .file_utils import (PYTORCH_TRANSFORMERS_CACHE, PYTORCH_PRETRAINED_BERT_CACHE,
+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)

pytorch_transformers/__main__.py → transformers/__main__.py

@@ -5,25 +5,25 @@ def main():
         print(
         "This command line utility let you convert original (author released) model checkpoint to pytorch.\n"
         "It 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")
+        ">> 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_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()
@@ -33,7 +33,7 @@ def main():
             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]
@@ -48,13 +48,13 @@ def main():
             try:
                 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]
@@ -72,14 +72,14 @@ def main():
             try:
                 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]
@@ -92,14 +92,14 @@ def main():
             try:
                 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]
@@ -118,7 +118,7 @@ def main():
 
             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`.
 
 

pytorch_transformers/configuration_utils.py → transformers/configuration_utils.py

@@ -59,7 +59,7 @@ class PretrainedConfig(object):
 
     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"
 
@@ -71,13 +71,13 @@ class PretrainedConfig(object):
 
     @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: