chore: import upstream snapshot with attribution

2026-07-13 13:24:13 +08:00
commit 1037506f2e
6050 changed files with 1731598 additions and 0 deletions
@@ -0,0 +1,80 @@
+# coding=utf-8
+# The MIT License (MIT)
+
+# Copyright (c) Microsoft Corporation
+
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+"""Tokenization classes for UniLM."""
+
+from __future__ import absolute_import, division, print_function, unicode_literals
+
+import collections
+import logging
+import os
+import unicodedata
+from io import open
+
+from transformers.tokenization_bert import BertTokenizer, whitespace_tokenize
+
+logger = logging.getLogger(__name__)
+
+VOCAB_FILES_NAMES = {'vocab_file': 'vocab.txt'}
+
+PRETRAINED_VOCAB_FILES_MAP = {
+    'vocab_file':
+    {
+        'unilm-large-cased': "https://conversationhub.blob.core.windows.net/beit-share-public/ckpt/unilm-large-cased-vocab.txt?sv=2021-10-04&st=2023-06-08T11%3A16%3A02Z&se=2033-06-09T11%3A16%3A00Z&sr=c&sp=r&sig=N4pfCVmSeq4L4tS8QbrFVsX6f6q844eft8xSuXdxU48%3D",
+        'unilm-base-cased': "https://conversationhub.blob.core.windows.net/beit-share-public/ckpt/unilm-base-cased-vocab.txt?sv=2021-10-04&st=2023-06-08T11%3A16%3A02Z&se=2033-06-09T11%3A16%3A00Z&sr=c&sp=r&sig=N4pfCVmSeq4L4tS8QbrFVsX6f6q844eft8xSuXdxU48%3D",
+        'unilm1-large-cased': "https://conversationhub.blob.core.windows.net/beit-share-public/ckpt/unilm1-large-cased-vocab.txt?sv=2021-10-04&st=2023-06-08T11%3A16%3A02Z&se=2033-06-09T11%3A16%3A00Z&sr=c&sp=r&sig=N4pfCVmSeq4L4tS8QbrFVsX6f6q844eft8xSuXdxU48%3D",
+        'unilm1-base-cased': "https://conversationhub.blob.core.windows.net/beit-share-public/ckpt/unilm1-base-cased-vocab.txt?sv=2021-10-04&st=2023-06-08T11%3A16%3A02Z&se=2033-06-09T11%3A16%3A00Z&sr=c&sp=r&sig=N4pfCVmSeq4L4tS8QbrFVsX6f6q844eft8xSuXdxU48%3D",
+        'unilm1.2-base-uncased': "https://conversationhub.blob.core.windows.net/beit-share-public/ckpt/unilm1.2-base-uncased-vocab.txt?sv=2021-10-04&st=2023-06-08T11%3A16%3A02Z&se=2033-06-09T11%3A16%3A00Z&sr=c&sp=r&sig=N4pfCVmSeq4L4tS8QbrFVsX6f6q844eft8xSuXdxU48%3D"
+    }
+}
+
+PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
+    'unilm-large-cased': 512,
+    'unilm-base-cased': 512,
+    'unilm1-large-cased': 512,
+    'unilm1-base-cased': 512,
+    'unilm1.2-base-uncased': 512,
+}
+
+
+class UnilmTokenizer(BertTokenizer):
+    r"""
+    Constructs a UnilmTokenizer.
+    :class:`~transformers.UnilmTokenizer` is identical to BertTokenizer and runs end-to-end tokenization: punctuation splitting + wordpiece
+    Args:
+        vocab_file: Path to a one-wordpiece-per-line vocabulary file
+        do_lower_case: Whether to lower case the input. Only has an effect when do_wordpiece_only=False
+        do_basic_tokenize: Whether to do basic tokenization before wordpiece.
+        max_len: An artificial maximum length to truncate tokenized sequences to; Effective maximum length is always the
+            minimum of this value (if specified) and the underlying BERT model's sequence length.
+        never_split: List of tokens which will never be split during tokenization. Only has an effect when
+            do_wordpiece_only=False
+    """
+
+    vocab_files_names = VOCAB_FILES_NAMES
+    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
+    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
+
+
+class WhitespaceTokenizer(object):
+    def tokenize(self, text):
+        return whitespace_tokenize(text)