Merge branch 'master' into t5

.circleci/config.yml

@@ -70,6 +70,27 @@ jobs:
             - run: sudo pip install pytest codecov pytest-cov
             - run: python -m pytest -sv ./transformers/tests/ --cov
             - run: codecov
+    build_py3_custom_tokenizers:
+        working_directory: ~/transformers
+        docker:
+            - image: circleci/python:3.5
+        steps:
+            - checkout
+            - run: sudo pip install --progress-bar off .
+            - run: sudo pip install pytest
+            - run: sudo pip install mecab-python3
+            - run: RUN_CUSTOM_TOKENIZERS=1 python -m pytest -sv ./transformers/tests/tokenization_bert_japanese_test.py
+    build_py2_custom_tokenizers:
+        working_directory: ~/transformers
+        docker:
+            - image: circleci/python:2.7
+        steps:
+            - checkout
+            - run: sudo pip install --progress-bar off .
+            - run: sudo pip install pytest
+            - run: sudo apt-get -y install libmecab-dev mecab mecab-ipadic-utf8 swig
+            - run: sudo pip install mecab-python
+            - run: RUN_CUSTOM_TOKENIZERS=1 python -m pytest -sv ./transformers/tests/tokenization_bert_japanese_test.py
     deploy_doc:
         working_directory: ~/transformers
         docker:
@@ -82,6 +103,16 @@ jobs:
             - run: sudo pip install --progress-bar off -r docs/requirements.txt
             - run: sudo pip install --progress-bar off -r requirements.txt
             - run: ./.circleci/deploy.sh
+    repository_consistency:
+        working_directory: ~/transformers
+        docker:
+            - image: circleci/python:3.5
+        resource_class: small
+        parallelism: 1
+        steps:
+            - checkout
+            - run: sudo pip install requests
+            - run: python ./utils/link_tester.py
 workflow_filters: &workflow_filters
     filters:
         branches:
@@ -91,6 +122,9 @@ workflows:
     version: 2
     build_and_test:
         jobs:
+            - repository_consistency
+            - build_py3_custom_tokenizers
+            - build_py2_custom_tokenizers
             - build_py3_torch_and_tf
             - build_py3_torch
             - build_py3_tf

docs/source/pretrained_models.rst

@@ -61,6 +61,24 @@ Here is the full list of the currently provided pretrained models together with
 |                   | ``bert-base-german-dbmdz-uncased``                         | | 12-layer, 768-hidden, 12-heads, 110M parameters.                                                                                    |
 |                   |                                                            | | Trained on uncased German text by DBMDZ                                                                                             |
 |                   |                                                            | (see `details on dbmdz repository <https://github.com/dbmdz/german-bert>`__).                                                         |
+|                   +------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
+|                   | ``bert-base-japanese``                                     | | 12-layer, 768-hidden, 12-heads, 110M parameters.                                                                                    |
+|                   |                                                            | | Trained on Japanese text. Text is tokenized with MeCab and WordPiece.                                                               |
+|                   |                                                            | | `MeCab <https://taku910.github.io/mecab/>`__ is required for tokenization.                                                          |
+|                   |                                                            | (see `details on cl-tohoku repository <https://github.com/cl-tohoku/bert-japanese>`__).                                               |
+|                   +------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
+|                   | ``bert-base-japanese-whole-word-masking``                  | | 12-layer, 768-hidden, 12-heads, 110M parameters.                                                                                    |
+|                   |                                                            | | Trained on Japanese text using Whole-Word-Masking. Text is tokenized with MeCab and WordPiece.                                      |
+|                   |                                                            | | `MeCab <https://taku910.github.io/mecab/>`__ is required for tokenization.                                                          |
+|                   |                                                            | (see `details on cl-tohoku repository <https://github.com/cl-tohoku/bert-japanese>`__).                                               |
+|                   +------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
+|                   | ``bert-base-japanese-char``                                | | 12-layer, 768-hidden, 12-heads, 110M parameters.                                                                                    |
+|                   |                                                            | | Trained on Japanese text. Text is tokenized into characters.                                                                        |
+|                   |                                                            | (see `details on cl-tohoku repository <https://github.com/cl-tohoku/bert-japanese>`__).                                               |
+|                   +------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
+|                   | ``bert-base-japanese-char-whole-word-masking``             | | 12-layer, 768-hidden, 12-heads, 110M parameters.                                                                                    |
+|                   |                                                            | | Trained on Japanese text using Whole-Word-Masking. Text is tokenized into characters.                                               |
+|                   |                                                            | (see `details on cl-tohoku repository <https://github.com/cl-tohoku/bert-japanese>`__).                                               |
 +-------------------+------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
 | GPT               | ``openai-gpt``                                             | | 12-layer, 768-hidden, 12-heads, 110M parameters.                                                                                    |
 |                   |                                                            | | OpenAI GPT English model                                                                                                            |

examples/run_glue.py

@@ -380,7 +380,7 @@ def main():
     parser.add_argument("--learning_rate", default=5e-5, type=float,
                         help="The initial learning rate for Adam.")
     parser.add_argument("--weight_decay", default=0.0, type=float,
-                        help="Weight deay if we apply some.")
+                        help="Weight decay if we apply some.")
     parser.add_argument("--adam_epsilon", default=1e-8, type=float,
                         help="Epsilon for Adam optimizer.")
     parser.add_argument("--max_grad_norm", default=1.0, type=float,

examples/run_squad.py

@@ -299,10 +299,13 @@ def evaluate(args, model, tokenizer, prefix=""):
 
     # XLNet and XLM use a more complex post-processing procedure
     if args.model_type in ['xlnet', 'xlm']:
+        start_n_top = model.config.start_n_top if hasattr(model, "config") else model.module.config.start_n_top
+        end_n_top = model.config.end_n_top if hasattr(model, "config") else model.module.config.end_n_top
+
         predictions = compute_predictions_log_probs(examples, features, all_results, args.n_best_size,
                         args.max_answer_length, output_prediction_file,
                         output_nbest_file, output_null_log_odds_file,
-                        model.config.start_n_top, model.config.end_n_top,
+                        start_n_top, end_n_top,
                         args.version_2_with_negative, tokenizer, args.verbose_logging)
     else:
         predictions = compute_predictions_logits(examples, features, all_results, args.n_best_size,
@@ -334,7 +337,7 @@ def load_and_cache_examples(args, tokenizer, evaluate=False, output_examples=Fal
     else:
         logger.info("Creating features from dataset file at %s", input_dir)
 
-        if not args.data_dir:
+        if not args.data_dir and ((evaluate and not args.predict_file) or (not evaluate and not args.train_file)):
             try:
                 import tensorflow_datasets as tfds
             except ImportError:
@@ -347,7 +350,11 @@ def load_and_cache_examples(args, tokenizer, evaluate=False, output_examples=Fal
             examples = SquadV1Processor().get_examples_from_dataset(tfds_examples, evaluate=evaluate)
         else:
             processor = SquadV2Processor() if args.version_2_with_negative else SquadV1Processor()
-            examples = processor.get_dev_examples(args.data_dir) if evaluate else processor.get_train_examples(args.data_dir)
+
+            if evaluate:
+                examples = processor.get_dev_examples(args.data_dir, filename=args.predict_file)
+            else:
+                examples = processor.get_train_examples(args.data_dir, filename=args.train_file)
 
         features, dataset = squad_convert_examples_to_features( 
             examples=examples,
@@ -384,7 +391,14 @@ def main():
 
     ## Other parameters
     parser.add_argument("--data_dir", default=None, type=str,
-                        help="The input data dir. Should contain the .json files for the task. If not specified, will run with tensorflow_datasets.")
+                        help="The input data dir. Should contain the .json files for the task." +
+                             "If no data dir or train/predict files are specified, will run with tensorflow_datasets.")
+    parser.add_argument("--train_file", default=None, type=str,
+                        help="The input training file. If a data dir is specified, will look for the file there" +
+                             "If no data dir or train/predict files are specified, will run with tensorflow_datasets.")
+    parser.add_argument("--predict_file", default=None, type=str,
+                        help="The input evaluation file. If a data dir is specified, will look for the file there" +
+                             "If no data dir or train/predict files are specified, will run with tensorflow_datasets.")
     parser.add_argument("--config_name", default="", type=str,
                         help="Pretrained config name or path if not the same as model_name")
     parser.add_argument("--tokenizer_name", default="", type=str,
@@ -469,11 +483,6 @@ def main():
     parser.add_argument('--server_port', type=str, default='', help="Can be used for distant debugging.")
     args = parser.parse_args()
 
-    args.predict_file = os.path.join(args.output_dir, 'predictions_{}_{}.txt'.format(
-        list(filter(None, args.model_name_or_path.split('/'))).pop(),
-        str(args.max_seq_length))
-    )
-
     if os.path.exists(args.output_dir) and os.listdir(args.output_dir) and args.do_train and not args.overwrite_output_dir:
         raise ValueError("Output directory ({}) already exists and is not empty. Use --overwrite_output_dir to overcome.".format(args.output_dir))
 

transformers/__init__.py

@@ -37,6 +37,7 @@ if is_sklearn_available():
 from .tokenization_utils import (PreTrainedTokenizer)
 from .tokenization_auto import AutoTokenizer
 from .tokenization_bert import BertTokenizer, BasicTokenizer, WordpieceTokenizer
+from .tokenization_bert_japanese import BertJapaneseTokenizer, MecabTokenizer, CharacterTokenizer
 from .tokenization_openai import OpenAIGPTTokenizer
 from .tokenization_transfo_xl import (TransfoXLTokenizer, TransfoXLCorpus)
 from .tokenization_gpt2 import GPT2Tokenizer

transformers/configuration_auto.py

@@ -85,6 +85,7 @@ 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 string with the `identifier name` of a pre-trained model configuration that was user-uploaded to our S3, e.g.: ``dbmdz/bert-base-german-cased``.
                 - 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``.
 

transformers/configuration_bert.py

@@ -42,6 +42,10 @@ BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
     'bert-base-cased-finetuned-mrpc': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-finetuned-mrpc-config.json",
     'bert-base-german-dbmdz-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-cased-config.json",
     'bert-base-german-dbmdz-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-uncased-config.json",
+    'bert-base-japanese': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-config.json",
+    'bert-base-japanese-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-whole-word-masking-config.json",
+    'bert-base-japanese-char': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-config.json",
+    'bert-base-japanese-char-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-whole-word-masking-config.json"
 }
 
 

transformers/configuration_utils.py

@@ -24,7 +24,7 @@ import logging
 import os
 from io import open
 
-from .file_utils import cached_path, CONFIG_NAME
+from .file_utils import CONFIG_NAME, cached_path, is_remote_url, hf_bucket_url
 
 logger = logging.getLogger(__name__)
 
@@ -79,6 +79,7 @@ class PretrainedConfig(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 string with the `identifier name` of a pre-trained model configuration that was user-uploaded to our S3, e.g.: ``dbmdz/bert-base-german-cased``.
                 - 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``.
 
@@ -131,8 +132,10 @@ class PretrainedConfig(object):
             config_file = cls.pretrained_config_archive_map[pretrained_model_name_or_path]
         elif os.path.isdir(pretrained_model_name_or_path):
             config_file = os.path.join(pretrained_model_name_or_path, CONFIG_NAME)
-        else:
+        elif os.path.isfile(pretrained_model_name_or_path) or is_remote_url(pretrained_model_name_or_path):
             config_file = pretrained_model_name_or_path
+        else:
+            config_file = hf_bucket_url(pretrained_model_name_or_path, postfix=CONFIG_NAME)
         # redirect to the cache, if necessary
         try:
             resolved_config_file = cached_path(config_file, cache_dir=cache_dir, force_download=force_download,
@@ -187,7 +190,7 @@ class PretrainedConfig(object):
 
     @classmethod
     def from_json_file(cls, json_file):
-        """Constructs a `BertConfig` from a json file of parameters."""
+        """Constructs a `Config` from a json file of parameters."""
         with open(json_file, "r", encoding='utf-8') as reader:
             text = reader.read()
         return cls.from_dict(json.loads(text))

transformers/data/metrics/squad_metrics.py

@@ -695,7 +695,12 @@ def compute_predictions_log_probs(
             tok_text = " ".join(tok_text.split())
             orig_text = " ".join(orig_tokens)
 
-            final_text = get_final_text(tok_text, orig_text, tokenizer.do_lower_case,
+            if hasattr(tokenizer, "do_lower_case"):
+                do_lower_case = tokenizer.do_lower_case
+            else:
+                do_lower_case = tokenizer.do_lowercase_and_remove_accent
+
+            final_text = get_final_text(tok_text, orig_text, do_lower_case,
                                         verbose_logging)
 
             if final_text in seen_predictions:

transformers/data/processors/squad.py

@@ -373,6 +373,9 @@ class SquadProcessor(DataProcessor):
                 which is `train-v1.1.json` and `train-v2.0.json` for squad versions 1.1 and 2.0 respectively.
 
         """
+        if data_dir is None:
+            data_dir = ""
+
         if self.train_file is None:
             raise ValueError("SquadProcessor should be instantiated via SquadV1Processor or SquadV2Processor")
 
@@ -389,6 +392,9 @@ class SquadProcessor(DataProcessor):
             filename: None by default, specify this if the evaluation file has a different name than the original one
                 which is `train-v1.1.json` and `train-v2.0.json` for squad versions 1.1 and 2.0 respectively.
         """
+        if data_dir is None:
+            data_dir = ""
+
         if self.dev_file is None:
             raise ValueError("SquadProcessor should be instantiated via SquadV1Processor or SquadV2Processor")
         

transformers/file_utils.py

@@ -21,7 +21,7 @@ import boto3
 from botocore.config import Config
 from botocore.exceptions import ClientError
 import requests
-from tqdm import tqdm
+from tqdm.auto import tqdm
 from contextlib import contextmanager
 
 logger = logging.getLogger(__name__)  # pylint: disable=invalid-name
@@ -73,9 +73,13 @@ TF2_WEIGHTS_NAME = 'tf_model.h5'
 TF_WEIGHTS_NAME = 'model.ckpt'
 CONFIG_NAME = "config.json"
 
+
 DUMMY_INPUTS = [[7, 6, 0, 0, 1], [1, 2, 3, 0, 0], [0, 0, 0, 4, 5]]
 DUMMY_MASK = [[1, 1, 1, 1, 1], [1, 1, 1, 0, 0], [0, 0, 0, 1, 1]]
 
+S3_BUCKET_PREFIX = "https://s3.amazonaws.com/models.huggingface.co/bert"
+
+
 def is_torch_available():
     return _torch_available
 
@@ -106,6 +110,18 @@ else:
             return fn
         return docstring_decorator
 
+
+def is_remote_url(url_or_filename):
+    parsed = urlparse(url_or_filename)
+    return parsed.scheme in ('http', 'https', 's3')
+
+def hf_bucket_url(identifier, postfix=None):
+    if postfix is None:
+        return "/".join((S3_BUCKET_PREFIX, identifier))
+    else:
+        return "/".join((S3_BUCKET_PREFIX, identifier, postfix))
+
+
 def url_to_filename(url, etag=None):
     """
     Convert `url` into a hashed filename in a repeatable way.
@@ -174,9 +190,7 @@ def cached_path(url_or_filename, cache_dir=None, force_download=False, proxies=N
     if sys.version_info[0] == 3 and isinstance(cache_dir, Path):
         cache_dir = str(cache_dir)
 
-    parsed = urlparse(url_or_filename)
-
-    if parsed.scheme in ('http', 'https', 's3'):
+    if is_remote_url(url_or_filename):
         # URL, so get it from the cache (downloading if necessary)
         return get_from_cache(url_or_filename, cache_dir=cache_dir,
             force_download=force_download, proxies=proxies,
@@ -184,7 +198,7 @@ def cached_path(url_or_filename, cache_dir=None, force_download=False, proxies=N
     elif os.path.exists(url_or_filename):
         # File, and it exists.
         return url_or_filename
-    elif parsed.scheme == '':
+    elif urlparse(url_or_filename).scheme == '':
         # File, but it doesn't exist.
         raise EnvironmentError("file {} not found".format(url_or_filename))
     else:
@@ -248,7 +262,7 @@ def http_get(url, temp_file, proxies=None, resume_size=0):
         return
     content_length = response.headers.get('Content-Length')
     total = resume_size + int(content_length) if content_length is not None else None
-    progress = tqdm(unit="B", total=total, initial=resume_size)
+    progress = tqdm(unit="B", unit_scale=True, total=total, initial=resume_size, desc="Downloading")
     for chunk in response.iter_content(chunk_size=1024):
         if chunk: # filter out keep-alive new chunks
             progress.update(len(chunk))

transformers/modeling_auto.py

@@ -28,7 +28,6 @@ from .modeling_xlm import XLMModel, XLMWithLMHeadModel, XLMForSequenceClassifica
 from .modeling_roberta import RobertaModel, RobertaForMaskedLM, RobertaForSequenceClassification
 from .modeling_distilbert import DistilBertModel, DistilBertForQuestionAnswering, DistilBertForMaskedLM, DistilBertForSequenceClassification
 from .modeling_camembert import CamembertModel, CamembertForMaskedLM, CamembertForSequenceClassification, CamembertForMultipleChoice
-from .modeling_camembert import CamembertModel, CamembertForMaskedLM, CamembertForSequenceClassification, CamembertForMultipleChoice
 from .modeling_albert import AlbertModel, AlbertForMaskedLM, AlbertForSequenceClassification, AlbertForQuestionAnswering
 from .modeling_t5 import T5Model, T5WithLMHeadModel
 
@@ -97,6 +96,7 @@ class AutoModel(object):
             pretrained_model_name_or_path: either:
 
                 - a string with the `shortcut name` of a pre-trained model to load from cache or download, e.g.: ``bert-base-uncased``.
+                - a string with the `identifier name` of a pre-trained model that was user-uploaded to our S3, e.g.: ``dbmdz/bert-base-german-cased``.
                 - a path to a `directory` containing model weights saved using :func:`~transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/``.
                 - a path or url to a `tensorflow index checkpoint file` (e.g. `./tf_model/model.ckpt.index`). In this case, ``from_tf`` should be set to True and a configuration object should be provided as ``config`` argument. This loading path is slower than converting the TensorFlow checkpoint in a PyTorch model using the provided conversion scripts and loading the PyTorch model afterwards.
 
@@ -239,6 +239,7 @@ class AutoModelWithLMHead(object):
             pretrained_model_name_or_path: either:
 
                 - a string with the `shortcut name` of a pre-trained model to load from cache or download, e.g.: ``bert-base-uncased``.
+                - a string with the `identifier name` of a pre-trained model that was user-uploaded to our S3, e.g.: ``dbmdz/bert-base-german-cased``.
                 - a path to a `directory` containing model weights saved using :func:`~transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/``.
                 - a path or url to a `tensorflow index checkpoint file` (e.g. `./tf_model/model.ckpt.index`). In this case, ``from_tf`` should be set to True and a configuration object should be provided as ``config`` argument. This loading path is slower than converting the TensorFlow checkpoint in a PyTorch model using the provided conversion scripts and loading the PyTorch model afterwards.
 
@@ -370,6 +371,7 @@ class AutoModelForSequenceClassification(object):
             pretrained_model_name_or_path: either:
 
                 - a string with the `shortcut name` of a pre-trained model to load from cache or download, e.g.: ``bert-base-uncased``.
+                - a string with the `identifier name` of a pre-trained model that was user-uploaded to our S3, e.g.: ``dbmdz/bert-base-german-cased``.
                 - a path to a `directory` containing model weights saved using :func:`~transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/``.
                 - a path or url to a `tensorflow index checkpoint file` (e.g. `./tf_model/model.ckpt.index`). In this case, ``from_tf`` should be set to True and a configuration object should be provided as ``config`` argument. This loading path is slower than converting the TensorFlow checkpoint in a PyTorch model using the provided conversion scripts and loading the PyTorch model afterwards.
 
@@ -488,6 +490,7 @@ class AutoModelForQuestionAnswering(object):
             pretrained_model_name_or_path: either:
 
                 - a string with the `shortcut name` of a pre-trained model to load from cache or download, e.g.: ``bert-base-uncased``.
+                - a string with the `identifier name` of a pre-trained model that was user-uploaded to our S3, e.g.: ``dbmdz/bert-base-german-cased``.
                 - a path to a `directory` containing model weights saved using :func:`~transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/``.
                 - a path or url to a `tensorflow index checkpoint file` (e.g. `./tf_model/model.ckpt.index`). In this case, ``from_tf`` should be set to True and a configuration object should be provided as ``config`` argument. This loading path is slower than converting the TensorFlow checkpoint in a PyTorch model using the provided conversion scripts and loading the PyTorch model afterwards.
 

transformers/modeling_bert.py

@@ -48,6 +48,10 @@ BERT_PRETRAINED_MODEL_ARCHIVE_MAP = {
     'bert-base-cased-finetuned-mrpc': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-finetuned-mrpc-pytorch_model.bin",
     'bert-base-german-dbmdz-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-cased-pytorch_model.bin",
     'bert-base-german-dbmdz-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-uncased-pytorch_model.bin",
+    'bert-base-japanese': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-pytorch_model.bin",
+    'bert-base-japanese-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-whole-word-masking-pytorch_model.bin",
+    'bert-base-japanese-char': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-pytorch_model.bin",
+    'bert-base-japanese-char-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-whole-word-masking-pytorch_model.bin"
 }
 
 

transformers/modeling_encoder_decoder.py

@@ -59,12 +59,14 @@ class PreTrainedEncoderDecoder(nn.Module):
             encoder_pretrained_model_name_or_path: information necessary to initiate the encoder. Either:
 
                 - a string with the `shortcut name` of a pre-trained model to load from cache or download, e.g.: ``bert-base-uncased``.
+                - a string with the `identifier name` of a pre-trained model that was user-uploaded to our S3, e.g.: ``dbmdz/bert-base-german-cased``.
                 - a path to a `directory` containing model weights saved using :func:`~transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/encoder``.
                 - a path or url to a `tensorflow index checkpoint file` (e.g. `./tf_model/model.ckpt.index`). In this case, ``from_tf`` should be set to True and a configuration object should be provided as ``config`` argument. This loading path is slower than converting the TensorFlow checkpoint in a PyTorch model using the provided conversion scripts and loading the PyTorch model afterwards.
 
             decoder_pretrained_model_name_or_path: information necessary to initiate the decoder. Either:
 
                 - a string with the `shortcut name` of a pre-trained model to load from cache or download, e.g.: ``bert-base-uncased``.
+                - a string with the `identifier name` of a pre-trained model that was user-uploaded to our S3, e.g.: ``dbmdz/bert-base-german-cased``.
                 - a path to a `directory` containing model weights saved using :func:`~transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/decoder``.
                 - a path or url to a `tensorflow index checkpoint file` (e.g. `./tf_model/model.ckpt.index`). In this case, ``from_tf`` should be set to True and a configuration object should be provided as ``config`` argument. This loading path is slower than converting the TensorFlow checkpoint in a PyTorch model using the provided conversion scripts and loading the PyTorch model afterwards.
 

transformers/modeling_tf_auto.py

@@ -84,6 +84,7 @@ class TFAutoModel(object):
             pretrained_model_name_or_path: either:
 
                 - a string with the `shortcut name` of a pre-trained model to load from cache or download, e.g.: ``bert-base-uncased``.
+                - a string with the `identifier name` of a pre-trained model that was user-uploaded to our S3, e.g.: ``dbmdz/bert-base-german-cased``.
                 - a path to a `directory` containing model weights saved using :func:`~transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/``.
                 - a path or url to a `PyTorch, TF 1.X or TF 2.0 checkpoint file` (e.g. `./tf_model/model.ckpt.index`). In the case of a PyTorch checkpoint, ``from_pt`` should be set to True and a configuration object should be provided as ``config`` argument.
 
@@ -219,6 +220,7 @@ class TFAutoModelWithLMHead(object):
             pretrained_model_name_or_path: either:
 
                 - a string with the `shortcut name` of a pre-trained model to load from cache or download, e.g.: ``bert-base-uncased``.
+                - a string with the `identifier name` of a pre-trained model that was user-uploaded to our S3, e.g.: ``dbmdz/bert-base-german-cased``.
                 - a path to a `directory` containing model weights saved using :func:`~transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/``.
                 - a path or url to a `PyTorch, TF 1.X or TF 2.0 checkpoint file` (e.g. `./tf_model/model.ckpt.index`). In the case of a PyTorch checkpoint, ``from_pt`` should be set to True and a configuration object should be provided as ``config`` argument.
 
@@ -347,6 +349,7 @@ class TFAutoModelForSequenceClassification(object):
             pretrained_model_name_or_path: either:
 
                 - a string with the `shortcut name` of a pre-trained model to load from cache or download, e.g.: ``bert-base-uncased``.
+                - a string with the `identifier name` of a pre-trained model that was user-uploaded to our S3, e.g.: ``dbmdz/bert-base-german-cased``.
                 - a path to a `directory` containing model weights saved using :func:`~transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/``.
                 - a path or url to a `PyTorch, TF 1.X or TF 2.0 checkpoint file` (e.g. `./tf_model/model.ckpt.index`). In the case of a PyTorch checkpoint, ``from_pt`` should be set to True and a configuration object should be provided as ``config`` argument.
 
@@ -462,6 +465,7 @@ class TFAutoModelForQuestionAnswering(object):
             pretrained_model_name_or_path: either:
 
                 - a string with the `shortcut name` of a pre-trained model to load from cache or download, e.g.: ``bert-base-uncased``.
+                - a string with the `identifier name` of a pre-trained model that was user-uploaded to our S3, e.g.: ``dbmdz/bert-base-german-cased``.
                 - a path to a `directory` containing model weights saved using :func:`~transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/``.
                 - a path or url to a `PyTorch, TF 1.X or TF 2.0 checkpoint file` (e.g. `./tf_model/model.ckpt.index`). In the case of a PyTorch checkpoint, ``from_pt`` should be set to True and a configuration object should be provided as ``config`` argument.
 

transformers/modeling_tf_bert.py

@@ -48,6 +48,10 @@ TF_BERT_PRETRAINED_MODEL_ARCHIVE_MAP = {
     'bert-large-uncased-whole-word-masking-finetuned-squad': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-finetuned-squad-tf_model.h5",
     'bert-large-cased-whole-word-masking-finetuned-squad': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-whole-word-masking-finetuned-squad-tf_model.h5",
     'bert-base-cased-finetuned-mrpc': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-finetuned-mrpc-tf_model.h5",
+    'bert-base-japanese': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-tf_model.h5",
+    'bert-base-japanese-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-whole-word-masking-tf_model.h5",
+    'bert-base-japanese-char': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-tf_model.h5",
+    'bert-base-japanese-char-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-whole-word-masking-tf_model.h5"
 }
 
 

transformers/modeling_tf_utils.py

@@ -24,7 +24,8 @@ import os
 import tensorflow as tf
 
 from .configuration_utils import PretrainedConfig
-from .file_utils import cached_path, WEIGHTS_NAME, TF_WEIGHTS_NAME, TF2_WEIGHTS_NAME, DUMMY_INPUTS
+from .file_utils import (TF2_WEIGHTS_NAME, TF_WEIGHTS_NAME, WEIGHTS_NAME, DUMMY_INPUTS,
+                         cached_path, hf_bucket_url, is_remote_url)
 from .modeling_tf_pytorch_utils import load_pytorch_checkpoint_in_tf2_model
 
 logger = logging.getLogger(__name__)
@@ -174,6 +175,7 @@ class TFPreTrainedModel(tf.keras.Model):
             pretrained_model_name_or_path: either:
 
                 - a string with the `shortcut name` of a pre-trained model to load from cache or download, e.g.: ``bert-base-uncased``.
+                - a string with the `identifier name` of a pre-trained model that was user-uploaded to our S3, e.g.: ``dbmdz/bert-base-german-cased``.
                 - a path to a `directory` containing model weights saved using :func:`~transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/``.
                 - a path or url to a `PyTorch state_dict save file` (e.g. `./pt_model/pytorch_model.bin`). In this case, ``from_pt`` should be set to True and a configuration object should be provided as ``config`` argument. This loading path is slower than converting the PyTorch checkpoint in a TensorFlow model using the provided conversion scripts and loading the TensorFlow model afterwards.
 
@@ -255,10 +257,14 @@ class TFPreTrainedModel(tf.keras.Model):
                     raise EnvironmentError("Error no file named {} found in directory {} or `from_pt` set to False".format(
                         [WEIGHTS_NAME, TF2_WEIGHTS_NAME],
                         pretrained_model_name_or_path))
-            elif os.path.isfile(pretrained_model_name_or_path):
+            elif os.path.isfile(pretrained_model_name_or_path) or is_remote_url(pretrained_model_name_or_path):
                 archive_file = pretrained_model_name_or_path
+            elif os.path.isfile(pretrained_model_name_or_path + ".index"):
+                archive_file = pretrained_model_name_or_path + ".index"
             else:
-                raise EnvironmentError("Error file {} not found".format(pretrained_model_name_or_path))
+                archive_file = hf_bucket_url(pretrained_model_name_or_path, postfix=TF2_WEIGHTS_NAME)
+                if from_pt:
+                    raise EnvironmentError("Loading a TF model from a PyTorch checkpoint is not supported when using a model identifier name.")
 
             # redirect to the cache, if necessary
             try:

transformers/modeling_utils.py

@@ -31,7 +31,8 @@ from torch.nn import CrossEntropyLoss
 from torch.nn import functional as F
 
 from .configuration_utils import PretrainedConfig
-from .file_utils import cached_path, WEIGHTS_NAME, TF_WEIGHTS_NAME, TF2_WEIGHTS_NAME, DUMMY_INPUTS
+from .file_utils import (TF2_WEIGHTS_NAME, TF_WEIGHTS_NAME, WEIGHTS_NAME, DUMMY_INPUTS,
+                         cached_path, hf_bucket_url, is_remote_url)
 
 logger = logging.getLogger(__name__)
 
@@ -272,6 +273,7 @@ class PreTrainedModel(nn.Module):
             pretrained_model_name_or_path: either:
 
                 - a string with the `shortcut name` of a pre-trained model to load from cache or download, e.g.: ``bert-base-uncased``.
+                - a string with the `identifier name` of a pre-trained model that was user-uploaded to our S3, e.g.: ``dbmdz/bert-base-german-cased``.
                 - a path to a `directory` containing model weights saved using :func:`~transformers.PreTrainedModel.save_pretrained`, e.g.: ``./my_model_directory/``.
                 - a path or url to a `tensorflow index checkpoint file` (e.g. `./tf_model/model.ckpt.index`). In this case, ``from_tf`` should be set to True and a configuration object should be provided as ``config`` argument. This loading path is slower than converting the TensorFlow checkpoint in a PyTorch model using the provided conversion scripts and loading the PyTorch model afterwards.
                 - None if you are both providing the configuration and state dictionary (resp. with keyword arguments ``config`` and ``state_dict``)
@@ -370,11 +372,16 @@ class PreTrainedModel(nn.Module):
                     raise EnvironmentError("Error no file named {} found in directory {} or `from_tf` set to False".format(
                         [WEIGHTS_NAME, TF2_WEIGHTS_NAME, TF_WEIGHTS_NAME + ".index"],
                         pretrained_model_name_or_path))
-            elif os.path.isfile(pretrained_model_name_or_path):
+            elif os.path.isfile(pretrained_model_name_or_path) or is_remote_url(pretrained_model_name_or_path):
                 archive_file = pretrained_model_name_or_path
-            else:
-                assert from_tf, "Error finding file {}, no file or TF 1.X checkpoint found".format(pretrained_model_name_or_path)
+            elif os.path.isfile(pretrained_model_name_or_path + ".index"):
+                assert from_tf, "We found a TensorFlow checkpoint at {}, please set from_tf to True to load from this checkpoint".format(
+                    pretrained_model_name_or_path + ".index")
                 archive_file = pretrained_model_name_or_path + ".index"
+            else:
+                archive_file = hf_bucket_url(pretrained_model_name_or_path, postfix=WEIGHTS_NAME)
+                if from_tf:
+                    raise EnvironmentError("Loading a PyTorch model from a TF checkpoint is not supported when using a model identifier name.")
 
             # redirect to the cache, if necessary
             try:

transformers/tests/modeling_auto_test.py

@@ -22,7 +22,7 @@ import logging
 
 from transformers import is_torch_available
 
-from .utils import require_torch, slow
+from .utils import require_torch, slow, SMALL_MODEL_IDENTIFIER
 
 if is_torch_available():
     from transformers import (AutoConfig, BertConfig,
@@ -92,6 +92,11 @@ class AutoModelTest(unittest.TestCase):
             self.assertIsNotNone(model)
             self.assertIsInstance(model, BertForQuestionAnswering)
 
+    def test_from_pretrained_identifier(self):
+        logging.basicConfig(level=logging.INFO)
+        model = AutoModelWithLMHead.from_pretrained(SMALL_MODEL_IDENTIFIER)
+        self.assertIsInstance(model, BertForMaskedLM)
+
 
 if __name__ == "__main__":
     unittest.main()

transformers/tests/modeling_tf_auto_test.py

@@ -22,7 +22,7 @@ import logging
 
 from transformers import is_tf_available
 
-from .utils import require_tf, slow
+from .utils import require_tf, slow, SMALL_MODEL_IDENTIFIER
 
 if is_tf_available():
     from transformers import (AutoConfig, BertConfig,
@@ -93,6 +93,11 @@ class TFAutoModelTest(unittest.TestCase):
             self.assertIsNotNone(model)
             self.assertIsInstance(model, TFBertForQuestionAnswering)
 
+    def test_from_pretrained_identifier(self):
+        logging.basicConfig(level=logging.INFO)
+        model = TFAutoModelWithLMHead.from_pretrained(SMALL_MODEL_IDENTIFIER, force_download=True)
+        self.assertIsInstance(model, TFBertForMaskedLM)
+
 
 if __name__ == "__main__":
     unittest.main()