[BIG] name change

.circleci/config.yml

 version: 2
 jobs:
     build_py3:
-        working_directory: ~/pytorch-pretrained-BERT
+        working_directory: ~/pytorch-transformers
         docker:
             - image: circleci/python:3.5
         steps:
@@ -10,11 +10,11 @@ jobs:
             - run: sudo pip install pytest codecov pytest-cov
             - run: sudo pip install spacy ftfy==4.4.3
             - run: sudo python -m spacy download en
-            - run: python -m pytest -sv ./pytorch_pretrained_bert/tests/ --cov
+            - run: python -m pytest -sv ./pytorch_transformers/tests/ --cov
             - run: codecov
         parallelism: 4
     build_py2:
-        working_directory: ~/pytorch-pretrained-BERT
+        working_directory: ~/pytorch-transformers
         docker:
             - image: circleci/python:2.7
         steps:
@@ -23,7 +23,7 @@ jobs:
             - run: sudo pip install pytest codecov pytest-cov
             - run: sudo pip install spacy ftfy==4.4.3
             - run: sudo python -m spacy download en
-            - run: python -m pytest -sv ./pytorch_pretrained_bert/tests/ --cov
+            - run: python -m pytest -sv ./pytorch_transformers/tests/ --cov
             - run: codecov
         parallelism: 4
 workflows:

.coveragerc

 [run]
-source=pytorch_pretrained_bert
+source=pytorch_transformers
 [report]
 exclude_lines =
     pragma: no cover

docker/Dockerfile

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

examples/bertology.py

@@ -12,7 +12,7 @@ from torch.utils.data import DataLoader, SequentialSampler, TensorDataset, Subse
 from torch.utils.data.distributed import DistributedSampler
 from torch.nn import CrossEntropyLoss, MSELoss
 
-from pytorch_pretrained_bert import BertForSequenceClassification, BertTokenizer
+from pytorch_transformers import BertForSequenceClassification, BertTokenizer
 
 from utils_glue import processors, output_modes, convert_examples_to_features, compute_metrics
 

examples/generation_xlnet.py

 import torch
 from torch.nn import functional as F
-from pytorch_pretrained_bert import XLNetModel, XLNetLMHeadModel, XLNetTokenizer
+from pytorch_transformers import XLNetModel, XLNetLMHeadModel, XLNetTokenizer
 
 import logging
 logging.basicConfig(level=logging.INFO)

examples/lm_finetuning/finetune_on_pregenerated.py

@@ -13,10 +13,10 @@ from torch.utils.data import DataLoader, Dataset, RandomSampler
 from torch.utils.data.distributed import DistributedSampler
 from tqdm import tqdm
 
-from pytorch_pretrained_bert import WEIGHTS_NAME, CONFIG_NAME
-from pytorch_pretrained_bert.modeling_bert import BertForPreTraining
-from pytorch_pretrained_bert.tokenization_bert import BertTokenizer
-from pytorch_pretrained_bert.optimization import BertAdam, WarmupLinearSchedule
+from pytorch_transformers import WEIGHTS_NAME, CONFIG_NAME
+from pytorch_transformers.modeling_bert import BertForPreTraining
+from pytorch_transformers.tokenization_bert import BertTokenizer
+from pytorch_transformers.optimization import BertAdam, WarmupLinearSchedule
 
 InputFeatures = namedtuple("InputFeatures", "input_ids input_mask segment_ids lm_label_ids is_next")
 

examples/lm_finetuning/pregenerate_training_data.py

@@ -5,7 +5,7 @@ from tempfile import TemporaryDirectory
 import shelve
 
 from random import random, randrange, randint, shuffle, choice
-from pytorch_pretrained_bert.tokenization_bert import BertTokenizer
+from pytorch_transformers.tokenization_bert import BertTokenizer
 import numpy as np
 import json
 import collections

examples/lm_finetuning/simple_lm_finetuning.py

@@ -29,10 +29,10 @@ from torch.utils.data import DataLoader, Dataset, RandomSampler
 from torch.utils.data.distributed import DistributedSampler
 from tqdm import tqdm, trange
 
-from pytorch_pretrained_bert import WEIGHTS_NAME, CONFIG_NAME
-from pytorch_pretrained_bert.modeling_bert import BertForPreTraining
-from pytorch_pretrained_bert.tokenization_bert import BertTokenizer
-from pytorch_pretrained_bert.optimization import BertAdam, WarmupLinearSchedule
+from pytorch_transformers import WEIGHTS_NAME, CONFIG_NAME
+from pytorch_transformers.modeling_bert import BertForPreTraining
+from pytorch_transformers.tokenization_bert import BertTokenizer
+from pytorch_transformers.optimization import BertAdam, WarmupLinearSchedule
 
 logging.basicConfig(format='%(asctime)s - %(levelname)s - %(name)s -   %(message)s',
                     datefmt='%m/%d/%Y %H:%M:%S',

examples/run_bert_classifier.py

@@ -34,10 +34,10 @@ from torch.nn import CrossEntropyLoss, MSELoss
 
 from tensorboardX import SummaryWriter
 
-from pytorch_pretrained_bert import WEIGHTS_NAME, CONFIG_NAME
-from pytorch_pretrained_bert.modeling_bert import BertForSequenceClassification
-from pytorch_pretrained_bert.tokenization_bert import BertTokenizer
-from pytorch_pretrained_bert.optimization import BertAdam, WarmupLinearSchedule
+from pytorch_transformers import WEIGHTS_NAME, CONFIG_NAME
+from pytorch_transformers.modeling_bert import BertForSequenceClassification
+from pytorch_transformers.tokenization_bert import BertTokenizer
+from pytorch_transformers.optimization import BertAdam, WarmupLinearSchedule
 
 from utils_glue import processors, output_modes, convert_examples_to_features, compute_metrics
 

examples/run_bert_extract_features.py

@@ -28,8 +28,8 @@ import torch
 from torch.utils.data import TensorDataset, DataLoader, SequentialSampler
 from torch.utils.data.distributed import DistributedSampler
 
-from pytorch_pretrained_bert.tokenization_bert import BertTokenizer
-from pytorch_pretrained_bert.modeling_bert import BertModel
+from pytorch_transformers.tokenization_bert import BertTokenizer
+from pytorch_transformers.modeling_bert import BertModel
 
 logging.basicConfig(format = '%(asctime)s - %(levelname)s - %(name)s -   %(message)s', 
                     datefmt = '%m/%d/%Y %H:%M:%S',

examples/run_bert_squad.py

@@ -33,10 +33,10 @@ from tqdm import tqdm, trange
 
 from tensorboardX import SummaryWriter
 
-from pytorch_pretrained_bert import WEIGHTS_NAME, CONFIG_NAME
-from pytorch_pretrained_bert.modeling_bert import BertForQuestionAnswering
-from pytorch_pretrained_bert.optimization import BertAdam, WarmupLinearSchedule
-from pytorch_pretrained_bert.tokenization_bert import BertTokenizer
+from pytorch_transformers import WEIGHTS_NAME, CONFIG_NAME
+from pytorch_transformers.modeling_bert import BertForQuestionAnswering
+from pytorch_transformers.optimization import BertAdam, WarmupLinearSchedule
+from pytorch_transformers.tokenization_bert import BertTokenizer
 
 from utils_squad import read_squad_examples, convert_examples_to_features, RawResult, write_predictions
 

examples/run_bert_swag.py

@@ -32,10 +32,10 @@ from torch.utils.data import (DataLoader, RandomSampler, SequentialSampler,
 from torch.utils.data.distributed import DistributedSampler
 from tqdm import tqdm, trange
 
-from pytorch_pretrained_bert.file_utils import PYTORCH_PRETRAINED_BERT_CACHE, WEIGHTS_NAME, CONFIG_NAME
-from pytorch_pretrained_bert.modeling_bert import BertForMultipleChoice, BertConfig
-from pytorch_pretrained_bert.optimization import BertAdam, WarmupLinearSchedule
-from pytorch_pretrained_bert.tokenization_bert import BertTokenizer
+from pytorch_transformers.file_utils import PYTORCH_PRETRAINED_BERT_CACHE, WEIGHTS_NAME, CONFIG_NAME
+from pytorch_transformers.modeling_bert import BertForMultipleChoice, BertConfig
+from pytorch_transformers.optimization import BertAdam, WarmupLinearSchedule
+from pytorch_transformers.tokenization_bert import BertTokenizer
 
 logging.basicConfig(format = '%(asctime)s - %(levelname)s - %(name)s -   %(message)s',
                     datefmt = '%m/%d/%Y %H:%M:%S',

examples/run_gpt2.py

@@ -8,7 +8,7 @@ import torch
 import torch.nn.functional as F
 import numpy as np
 
-from pytorch_pretrained_bert import GPT2LMHeadModel, GPT2Tokenizer
+from pytorch_transformers import GPT2LMHeadModel, GPT2Tokenizer
 
 logging.basicConfig(format = '%(asctime)s - %(levelname)s - %(name)s -   %(message)s',
                     datefmt = '%m/%d/%Y %H:%M:%S',

examples/run_openai_gpt.py

@@ -39,7 +39,7 @@ import torch
 from torch.utils.data import (DataLoader, RandomSampler, SequentialSampler,
                               TensorDataset)
 
-from pytorch_pretrained_bert import (OpenAIGPTDoubleHeadsModel, OpenAIGPTTokenizer,
+from pytorch_transformers import (OpenAIGPTDoubleHeadsModel, OpenAIGPTTokenizer,
                                      OpenAIAdam, cached_path, WEIGHTS_NAME, CONFIG_NAME)
 
 ROCSTORIES_URL = "https://s3.amazonaws.com/datasets.huggingface.co/ROCStories.tar.gz"

examples/run_transfo_xl.py

@@ -28,7 +28,7 @@ import math
 
 import torch
 
-from pytorch_pretrained_bert import TransfoXLLMHeadModel, TransfoXLCorpus, TransfoXLTokenizer
+from pytorch_transformers import TransfoXLLMHeadModel, TransfoXLCorpus, TransfoXLTokenizer
 
 logging.basicConfig(format = '%(asctime)s - %(levelname)s - %(name)s -   %(message)s',
                     datefmt = '%m/%d/%Y %H:%M:%S',

examples/run_xlnet_classifier.py

@@ -34,10 +34,10 @@ from torch.nn import CrossEntropyLoss, MSELoss
 
 from tensorboardX import SummaryWriter
 
-from pytorch_pretrained_bert import WEIGHTS_NAME, CONFIG_NAME
-from pytorch_pretrained_bert.modeling_xlnet import XLNetForSequenceClassification
-from pytorch_pretrained_bert.tokenization_xlnet import XLNetTokenizer
-from pytorch_pretrained_bert.optimization import BertAdam, WarmupLinearSchedule
+from pytorch_transformers import WEIGHTS_NAME, CONFIG_NAME
+from pytorch_transformers.modeling_xlnet import XLNetForSequenceClassification
+from pytorch_transformers.tokenization_xlnet import XLNetTokenizer
+from pytorch_transformers.optimization import BertAdam, WarmupLinearSchedule
 
 from utils_glue import processors, output_modes, convert_examples_to_features, compute_metrics
 

examples/run_xlnet_squad.py

@@ -33,10 +33,10 @@ from tqdm import tqdm, trange
 
 from tensorboardX import SummaryWriter
 
-from pytorch_pretrained_bert import WEIGHTS_NAME, CONFIG_NAME
-from pytorch_pretrained_bert.modeling_xlnet import BertForQuestionAnswering
-from pytorch_pretrained_bert.tokenization_xlnet import XLNetTokenizer
-from pytorch_pretrained_bert.optimization import BertAdam, WarmupLinearSchedule
+from pytorch_transformers import WEIGHTS_NAME, CONFIG_NAME
+from pytorch_transformers.modeling_xlnet import BertForQuestionAnswering
+from pytorch_transformers.tokenization_xlnet import XLNetTokenizer
+from pytorch_transformers.optimization import BertAdam, WarmupLinearSchedule
 
 from utils_squad import read_squad_examples, convert_examples_to_features, RawResult, write_predictions
 

examples/tests/examples_tests.py

+# coding=utf-8
+# Copyright 2018 HuggingFace Inc..
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import os
+import unittest
+import json
+import random
+import shutil
+import pytest
+
+import torch
+
+from pytorch_transformers import PretrainedConfig, PreTrainedModel
+from pytorch_transformers.modeling_bert import BertModel, BertConfig, PRETRAINED_MODEL_ARCHIVE_MAP, PRETRAINED_CONFIG_ARCHIVE_MAP
+
+
+class ModelUtilsTest(unittest.TestCase):
+    def test_model_from_pretrained(self):
+        for model_name in list(PRETRAINED_MODEL_ARCHIVE_MAP.keys())[:1]:
+            config = BertConfig.from_pretrained(model_name)
+            self.assertIsNotNone(config)
+            self.assertIsInstance(config, PretrainedConfig)
+
+            model = BertModel.from_pretrained(model_name)
+            self.assertIsNotNone(model)
+            self.assertIsInstance(model, PreTrainedModel)
+
+            config = BertConfig.from_pretrained(model_name, output_attentions=True, output_hidden_states=True)
+            model = BertModel.from_pretrained(model_name, output_attentions=True, output_hidden_states=True)
+            self.assertEqual(model.config.output_attentions, True)
+            self.assertEqual(model.config.output_hidden_states, True)
+            self.assertEqual(model.config, config)
+
+if __name__ == "__main__":
+    unittest.main()

examples/utils_squad.py

@@ -24,7 +24,7 @@ import math
 import collections
 from io import open
 
-from pytorch_pretrained_bert.tokenization_bert import BasicTokenizer, whitespace_tokenize
+from pytorch_transformers.tokenization_bert import BasicTokenizer, whitespace_tokenize
 
 logger = logging.getLogger(__name__)