Make `MobileBert` tokenizers independent from `Bert` (#19531)

* Make `MobileBert` tokenizers independent from `Bert`

* Update src/transformers/models/mobilebert/tokenization_mobilebert.py
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Fixed the name in the error message

* Update src/transformers/models/mobilebert/tokenization_mobilebert.py
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Removed extra space from the "copied" comment
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

src/transformers/models/mobilebert/tokenization_mobilebert_fast.py

@@ -15,8 +15,13 @@
 # limitations under the License.
 """Tokenization classes for MobileBERT."""
 
+import json
+from typing import List, Optional, Tuple
+
+from tokenizers import normalizers
+
+from ...tokenization_utils_fast import PreTrainedTokenizerFast
 from ...utils import logging
-from ..bert.tokenization_bert_fast import BertTokenizerFast
 from .tokenization_mobilebert import MobileBertTokenizer
 
 
@@ -37,18 +42,148 @@ PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"mobilebert-uncased": 512}
 PRETRAINED_INIT_CONFIGURATION = {}
 
 
-class MobileBertTokenizerFast(BertTokenizerFast):
+# Copied from transformers.models.bert.tokenization_bert_fast.BertTokenizerFast with BERT->MobileBERT,Bert->MobileBert
+class MobileBertTokenizerFast(PreTrainedTokenizerFast):
     r"""
-    Construct a "fast" MobileBERT tokenizer (backed by HuggingFace's *tokenizers* library).
+    Construct a "fast" MobileBERT tokenizer (backed by HuggingFace's *tokenizers* library). Based on WordPiece.
 
-    [`MobileBertTokenizerFast`] is identical to [`BertTokenizerFast`] and runs end-to-end tokenization: punctuation
-    splitting and wordpiece.
+    This tokenizer inherits from [`PreTrainedTokenizerFast`] which contains most of the main methods. Users should
+    refer to this superclass for more information regarding those methods.
 
-    Refer to superclass [`BertTokenizerFast`] for usage examples and documentation concerning parameters.
+    Args:
+        vocab_file (`str`):
+            File containing the vocabulary.
+        do_lower_case (`bool`, *optional*, defaults to `True`):
+            Whether or not to lowercase the input when tokenizing.
+        unk_token (`str`, *optional*, defaults to `"[UNK]"`):
+            The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
+            token instead.
+        sep_token (`str`, *optional*, defaults to `"[SEP]"`):
+            The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for
+            sequence classification or for a text and a question for question answering. It is also used as the last
+            token of a sequence built with special tokens.
+        pad_token (`str`, *optional*, defaults to `"[PAD]"`):
+            The token used for padding, for example when batching sequences of different lengths.
+        cls_token (`str`, *optional*, defaults to `"[CLS]"`):
+            The classifier token which is used when doing sequence classification (classification of the whole sequence
+            instead of per-token classification). It is the first token of the sequence when built with special tokens.
+        mask_token (`str`, *optional*, defaults to `"[MASK]"`):
+            The token used for masking values. This is the token used when training this model with masked language
+            modeling. This is the token which the model will try to predict.
+        clean_text (`bool`, *optional*, defaults to `True`):
+            Whether or not to clean the text before tokenization by removing any control characters and replacing all
+            whitespaces by the classic one.
+        tokenize_chinese_chars (`bool`, *optional*, defaults to `True`):
+            Whether or not to tokenize Chinese characters. This should likely be deactivated for Japanese (see [this
+            issue](https://github.com/huggingface/transformers/issues/328)).
+        strip_accents (`bool`, *optional*):
+            Whether or not to strip all accents. If this option is not specified, then it will be determined by the
+            value for `lowercase` (as in the original MobileBERT).
+        wordpieces_prefix (`str`, *optional*, defaults to `"##"`):
+            The prefix for subwords.
     """
 
     vocab_files_names = VOCAB_FILES_NAMES
     pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
-    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
     pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION
+    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
     slow_tokenizer_class = MobileBertTokenizer
+
+    def __init__(
+        self,
+        vocab_file=None,
+        tokenizer_file=None,
+        do_lower_case=True,
+        unk_token="[UNK]",
+        sep_token="[SEP]",
+        pad_token="[PAD]",
+        cls_token="[CLS]",
+        mask_token="[MASK]",
+        tokenize_chinese_chars=True,
+        strip_accents=None,
+        **kwargs
+    ):
+        super().__init__(
+            vocab_file,
+            tokenizer_file=tokenizer_file,
+            do_lower_case=do_lower_case,
+            unk_token=unk_token,
+            sep_token=sep_token,
+            pad_token=pad_token,
+            cls_token=cls_token,
+            mask_token=mask_token,
+            tokenize_chinese_chars=tokenize_chinese_chars,
+            strip_accents=strip_accents,
+            **kwargs,
+        )
+
+        normalizer_state = json.loads(self.backend_tokenizer.normalizer.__getstate__())
+        if (
+            normalizer_state.get("lowercase", do_lower_case) != do_lower_case
+            or normalizer_state.get("strip_accents", strip_accents) != strip_accents
+            or normalizer_state.get("handle_chinese_chars", tokenize_chinese_chars) != tokenize_chinese_chars
+        ):
+            normalizer_class = getattr(normalizers, normalizer_state.pop("type"))
+            normalizer_state["lowercase"] = do_lower_case
+            normalizer_state["strip_accents"] = strip_accents
+            normalizer_state["handle_chinese_chars"] = tokenize_chinese_chars
+            self.backend_tokenizer.normalizer = normalizer_class(**normalizer_state)
+
+        self.do_lower_case = do_lower_case
+
+    def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
+        """
+        Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
+        adding special tokens. A MobileBERT sequence has the following format:
+
+        - single sequence: `[CLS] X [SEP]`
+        - pair of sequences: `[CLS] A [SEP] B [SEP]`
+
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs to which the special tokens will be added.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+
+        Returns:
+            `List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
+        """
+        output = [self.cls_token_id] + token_ids_0 + [self.sep_token_id]
+
+        if token_ids_1:
+            output += token_ids_1 + [self.sep_token_id]
+
+        return output
+
+    def create_token_type_ids_from_sequences(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Create a mask from the two sequences passed to be used in a sequence-pair classification task. A MobileBERT
+        sequence pair mask has the following format:
+
+        ```
+        0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
+        | first sequence    | second sequence |
+        ```
+
+        If `token_ids_1` is `None`, this method only returns the first portion of the mask (0s).
+
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+
+        Returns:
+            `List[int]`: List of [token type IDs](../glossary#token-type-ids) according to the given sequence(s).
+        """
+        sep = [self.sep_token_id]
+        cls = [self.cls_token_id]
+        if token_ids_1 is None:
+            return len(cls + token_ids_0 + sep) * [0]
+        return len(cls + token_ids_0 + sep) * [0] + len(token_ids_1 + sep) * [1]
+
+    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
+        files = self._tokenizer.model.save(save_directory, name=filename_prefix)
+        return tuple(files)