Merge master into realm-mlm

tools/openwebtext/blacklist_urls.py

 # coding=utf-8
-# Copyright (c) 2019, NVIDIA CORPORATION.  All rights reserved.
+# Copyright (c) 2020, NVIDIA CORPORATION.  All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

tools/openwebtext/cleanup_dataset.py

 # coding=utf-8
-# Copyright (c) 2019, NVIDIA CORPORATION.  All rights reserved.
+# Copyright (c) 2020, NVIDIA CORPORATION.  All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

tools/openwebtext/find_duplicates.py

 # coding=utf-8
-# Copyright (c) 2019, NVIDIA CORPORATION.  All rights reserved.
+# Copyright (c) 2020, NVIDIA CORPORATION.  All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

tools/openwebtext/group_duplicates_url.py

 # coding=utf-8
-# Copyright (c) 2019, NVIDIA CORPORATION.  All rights reserved.
+# Copyright (c) 2020, NVIDIA CORPORATION.  All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

tools/openwebtext/merge_jsons.py

 # coding=utf-8
-# Copyright (c) 2019, NVIDIA CORPORATION.  All rights reserved.
+# Copyright (c) 2020, NVIDIA CORPORATION.  All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

tools/openwebtext/remove_group_duplicates.py

 # coding=utf-8
-# Copyright (c) 2019, NVIDIA CORPORATION.  All rights reserved.
+# Copyright (c) 2020, NVIDIA CORPORATION.  All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

tools/preprocess_data.py

 # coding=utf-8
-# Copyright (c) 2019, NVIDIA CORPORATION.  All rights reserved.
+# Copyright (c) 2020, NVIDIA CORPORATION.  All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -104,7 +104,7 @@ def get_args():
 
     group = parser.add_argument_group(title='tokenizer')
     group.add_argument('--tokenizer-type', type=str, required=True,
-                       choices=['BertWordPieceLowerCase',
+                       choices=['BertWordPieceLowerCase','BertWordPieceCase',
                                 'GPT2BPETokenizer'],
                        help='What type of tokenizer to use.')
     group.add_argument('--vocab-file', type=str, default=None,