Merge pull request #1203 from huggingface/tf2

[2.0] TF 2.0 support

examples/distillation/train.py

@@ -23,8 +23,8 @@ import shutil
 import numpy as np
 import torch
 
-from pytorch_transformers import BertTokenizer, BertForMaskedLM, RobertaTokenizer, RobertaForMaskedLM
-from pytorch_transformers import DistilBertForMaskedLM, DistilBertConfig
+from transformers import BertTokenizer, BertForMaskedLM, RobertaTokenizer, RobertaForMaskedLM
+from transformers import DistilBertForMaskedLM, DistilBertConfig
 
 from distiller import Distiller
 from utils import git_log, logger, init_gpu_params, set_seed

examples/run_bertology.py

@@ -32,7 +32,7 @@ from torch.utils.data import DataLoader, SequentialSampler, TensorDataset, Subse
 from torch.utils.data.distributed import DistributedSampler
 from torch.nn import CrossEntropyLoss, MSELoss
 
-from pytorch_transformers import (WEIGHTS_NAME,
+from transformers import (WEIGHTS_NAME,
                                   BertConfig, BertForSequenceClassification, BertTokenizer,
                                   XLMConfig, XLMForSequenceClassification, XLMTokenizer,
                                   XLNetConfig, XLNetForSequenceClassification, XLNetTokenizer)

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,
@@ -39,12 +39,17 @@ from pytorch_transformers import (WEIGHTS_NAME, BertConfig,
                                   XLMConfig, XLMForSequenceClassification,
                                   XLMTokenizer, XLNetConfig,
                                   XLNetForSequenceClassification,
-                                  XLNetTokenizer)
+                                  XLNetTokenizer,
+                                  DistilBertConfig,
+                                  DistilBertForSequenceClassification,
+                                  DistilBertTokenizer)
 
-from pytorch_transformers import AdamW, WarmupLinearSchedule
+from transformers import AdamW, WarmupLinearSchedule
 
-from utils_glue import (compute_metrics, convert_examples_to_features,
-                        output_modes, processors)
+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__)
 
@@ -55,6 +60,7 @@ MODEL_CLASSES = {
     'xlnet': (XLNetConfig, XLNetForSequenceClassification, XLNetTokenizer),
     'xlm': (XLMConfig, XLMForSequenceClassification, XLMTokenizer),
     'roberta': (RobertaConfig, RobertaForSequenceClassification, RobertaTokenizer),
+    'distilbert': (DistilBertConfig, DistilBertForSequenceClassification, DistilBertTokenizer)
 }
 
 
@@ -128,10 +134,10 @@ def train(args, train_dataset, model, tokenizer):
             batch = tuple(t.to(args.device) for t in batch)
             inputs = {'input_ids':      batch[0],
                       'attention_mask': batch[1],
-                      'token_type_ids': batch[2] if args.model_type in ['bert', 'xlnet'] else None,  # XLM and RoBERTa don't use segment_ids
+                      '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
@@ -148,8 +154,8 @@ def train(args, train_dataset, model, tokenizer):
 
             tr_loss += loss.item()
             if (step + 1) % args.gradient_accumulation_steps == 0:
-                scheduler.step()  # Update learning rate schedule
                 optimizer.step()
+                scheduler.step()  # Update learning rate schedule
                 model.zero_grad()
                 global_step += 1
 
@@ -218,7 +224,7 @@ def evaluate(args, model, tokenizer, prefix=""):
             with torch.no_grad():
                 inputs = {'input_ids':      batch[0],
                           'attention_mask': batch[1],
-                          'token_type_ids': batch[2] if args.model_type in ['bert', 'xlnet'] else None,  # XLM and RoBERTa don't use segment_ids
+                          '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)
                 tmp_eval_loss, logits = outputs[:2]
@@ -272,15 +278,14 @@ def load_and_cache_examples(args, task, tokenizer, evaluate=False):
             # HACK(label indices are swapped in RoBERTa pretrained model)
             label_list[1], label_list[2] = label_list[2], label_list[1] 
         examples = processor.get_dev_examples(args.data_dir) if evaluate else processor.get_train_examples(args.data_dir)
-        features = convert_examples_to_features(examples, label_list, args.max_seq_length, tokenizer, output_mode,
-            cls_token_at_end=bool(args.model_type in ['xlnet']),            # xlnet has a cls token at the end
-            cls_token=tokenizer.cls_token,
-            cls_token_segment_id=2 if args.model_type in ['xlnet'] else 0,
-            sep_token=tokenizer.sep_token,
-            sep_token_extra=bool(args.model_type in ['roberta']),           # roberta uses an extra separator b/w pairs of sentences, cf. github.com/pytorch/fairseq/commit/1684e166e3da03f5b600dbb7855cb98ddfcd0805
-            pad_on_left=bool(args.model_type in ['xlnet']),                 # pad on the left for xlnet
-            pad_token=tokenizer.convert_tokens_to_ids([tokenizer.pad_token])[0],
-            pad_token_segment_id=4 if args.model_type in ['xlnet'] else 0,
+        features = convert_examples_to_features(examples,
+                                                tokenizer,
+                                                label_list=label_list,
+                                                max_length=args.max_seq_length,
+                                                output_mode=output_mode,
+                                                pad_on_left=bool(args.model_type in ['xlnet']),                 # pad on the left for xlnet
+                                                pad_token=tokenizer.convert_tokens_to_ids([tokenizer.pad_token])[0],
+                                                pad_token_segment_id=4 if args.model_type in ['xlnet'] else 0,
         )
         if args.local_rank in [-1, 0]:
             logger.info("Saving features into cached file %s", cached_features_file)
@@ -291,14 +296,14 @@ def load_and_cache_examples(args, task, tokenizer, evaluate=False):
 
     # Convert to Tensors and build dataset
     all_input_ids = torch.tensor([f.input_ids for f in features], dtype=torch.long)
-    all_input_mask = torch.tensor([f.input_mask for f in features], dtype=torch.long)
-    all_segment_ids = torch.tensor([f.segment_ids for f in features], dtype=torch.long)
+    all_attention_mask = torch.tensor([f.attention_mask for f in features], dtype=torch.long)
+    all_token_type_ids = torch.tensor([f.token_type_ids for f in features], dtype=torch.long)
     if output_mode == "classification":
-        all_label_ids = torch.tensor([f.label_id for f in features], dtype=torch.long)
+        all_labels = torch.tensor([f.label for f in features], dtype=torch.long)
     elif output_mode == "regression":
-        all_label_ids = torch.tensor([f.label_id for f in features], dtype=torch.float)
+        all_labels = torch.tensor([f.label for f in features], dtype=torch.float)
 
-    dataset = TensorDataset(all_input_ids, all_input_mask, all_segment_ids, all_label_ids)
+    dataset = TensorDataset(all_input_ids, all_attention_mask, all_token_type_ids, all_labels)
     return dataset
 
 
@@ -478,7 +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

@@ -35,11 +35,12 @@ 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,
-                                  RobertaConfig, RobertaForMaskedLM, RobertaTokenizer)
+                                  RobertaConfig, RobertaForMaskedLM, RobertaTokenizer,
+                                  DistilBertConfig, DistilBertForMaskedLM, DistilBertTokenizer)
 
 
 logger = logging.getLogger(__name__)
@@ -49,7 +50,8 @@ MODEL_CLASSES = {
     'gpt2': (GPT2Config, GPT2LMHeadModel, GPT2Tokenizer),
     'openai-gpt': (OpenAIGPTConfig, OpenAIGPTLMHeadModel, OpenAIGPTTokenizer),
     'bert': (BertConfig, BertForMaskedLM, BertTokenizer),
-    'roberta': (RobertaConfig, RobertaForMaskedLM, RobertaTokenizer)
+    'roberta': (RobertaConfig, RobertaForMaskedLM, RobertaTokenizer),
+    'distilbert': (DistilBertConfig, DistilBertForMaskedLM, DistilBertTokenizer)
 }
 
 
@@ -73,7 +75,7 @@ class TextDataset(Dataset):
             tokenized_text = tokenizer.convert_tokens_to_ids(tokenizer.tokenize(text))
 
             while len(tokenized_text) >= block_size:  # Truncate in block of block_size
-                self.examples.append(tokenizer.add_special_tokens_single_sentence(tokenized_text[:block_size]))
+                self.examples.append(tokenizer.add_special_tokens_single_sequence(tokenized_text[:block_size]))
                 tokenized_text = tokenized_text[block_size:]
             # Note that we are loosing the last truncated example here for the sake of simplicity (no padding)
             # If your dataset is small, first you should loook for a bigger one :-) and second you
@@ -186,7 +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
@@ -380,7 +382,7 @@ def main():
     parser.add_argument('--server_port', type=str, default='', help="For distant debugging.")
     args = parser.parse_args()
 
-    if args.model_type in ["bert", "roberta"] and not args.mlm:
+    if args.model_type in ["bert", "roberta", "distilbert"] and not args.mlm:
         raise ValueError("BERT and RoBERTa do not have LM heads but masked LM heads. They must be run using the --mlm "
                          "flag (masked language modeling).")
     if args.eval_data_file is None and args.do_eval:
@@ -479,7 +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

@@ -32,14 +32,15 @@ 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,
                                   XLNetForQuestionAnswering,
-                                  XLNetTokenizer)
+                                  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,
@@ -59,6 +60,7 @@ MODEL_CLASSES = {
     'bert': (BertConfig, BertForQuestionAnswering, BertTokenizer),
     'xlnet': (XLNetConfig, XLNetForQuestionAnswering, XLNetTokenizer),
     'xlm': (XLMConfig, XLMForQuestionAnswering, XLMTokenizer),
+    'distilbert': (DistilBertConfig, DistilBertForQuestionAnswering, DistilBertTokenizer)
 }
 
 def set_seed(args):
@@ -140,7 +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
@@ -508,7 +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 transformers import *
+
+# Load dataset, tokenizer, model from pretrained model/vocabulary
+tokenizer = BertTokenizer.from_pretrained('bert-base-cased')
+model = TFBertForSequenceClassification.from_pretrained('bert-base-cased')
+data = tensorflow_datasets.load('glue/mrpc')
+
+# Prepare dataset for GLUE as a tf.data.Dataset instance
+train_dataset = glue_convert_examples_to_features(data['train'], tokenizer, 128, 'mrpc')
+valid_dataset = glue_convert_examples_to_features(data['validation'], tokenizer, 128, 'mrpc')
+train_dataset = train_dataset.shuffle(100).batch(32).repeat(2)
+valid_dataset = valid_dataset.batch(64)
+
+# Prepare training: Compile tf.keras model with optimizer, loss and learning rate schedule 
+optimizer = tf.keras.optimizers.Adam(learning_rate=3e-5, epsilon=1e-08, clipnorm=1.0)
+loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
+metric = tf.keras.metrics.SparseCategoricalAccuracy('accuracy')
+model.compile(optimizer=optimizer, loss=loss, metrics=[metric])
+
+# Train and evaluate using tf.keras.Model.fit()
+history = model.fit(train_dataset, epochs=2, steps_per_epoch=115,
+                    validation_data=valid_dataset, validation_steps=7)
+
+>>> Train for 115 steps, validate for 7 steps
+>>> Epoch 1/2
+>>> 115/115 [==============================] - 53s 459ms/step - loss: 0.6033 - accuracy: 0.6712 - val_loss: 0.4964 - val_accuracy: 0.7647
+>>> Epoch 2/2
+>>> 115/115 [==============================] - 33s 289ms/step - loss: 0.4141 - accuracy: 0.8160 - val_loss: 0.3914 - val_accuracy: 0.8382
+
+# Load the TensorFlow model in PyTorch for inspection
+model.save_pretrained('./save/')
+pytorch_model = BertForSequenceClassification.from_pretrained('./save/', from_tf=True)
+
+# Quickly test a few predictions - MRPC is a paraphrasing task, let's see if our model learned the task
+sentence_0 = "This research was consistent with his findings."
+sentence_1 = "His findings were compatible with this research."
+sentence_2 = "His findings were not compatible with this research."
+inputs_1 = tokenizer.encode_plus(sentence_0, sentence_1, add_special_tokens=True, return_tensors='pt')
+inputs_2 = tokenizer.encode_plus(sentence_0, sentence_2, add_special_tokens=True, return_tensors='pt')
+
+pred_1 = pytorch_model(**inputs_1)[0].argmax().item()
+pred_2 = pytorch_model(**inputs_2)[0].argmax().item()
+print("sentence_1 is", "a paraphrase" if pred_1 else "not a paraphrase", "of sentence_0")
+print("sentence_2 is", "a paraphrase" if pred_2 else "not a paraphrase", "of sentence_0")
+>>> sentence_1 is a paraphrase of sentence_0
+>>> sentence_2 is not a paraphrase of sentence_0
\ No newline at end of file

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)

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

@@ -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",
@@ -46,11 +46,10 @@ 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=['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, 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,
+                                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,