Removed Bert interdependency from Funnel transformer (#19655)

* Removed Bert interdependency from Funnel transformer

* passed consistency check

* Revert "passed consistency check"

This reverts commit ba55a0813549938fc54626794e666ee13a85c2d8.

* Fixed docstrings
Co-authored-by: mukesh663 <mukesh13034@gmail.com>

src/transformers/models/funnel/tokenization_funnel.py

@@ -14,10 +14,13 @@
 # limitations under the License.
 """ Tokenization class for Funnel Transformer."""
 
-from typing import List, Optional
+import collections
+import os
+import unicodedata
+from typing import List, Optional, Tuple
 
+from ...tokenization_utils import PreTrainedTokenizer, _is_control, _is_punctuation, _is_whitespace
 from ...utils import logging
-from ..bert.tokenization_bert import BertTokenizer
 
 
 logger = logging.get_logger(__name__)
@@ -63,20 +66,78 @@ PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {f"funnel-transformer/{name}": 512 for
 PRETRAINED_INIT_CONFIGURATION = {f"funnel-transformer/{name}": {"do_lower_case": True} for name in _model_names}
 
 
-class FunnelTokenizer(BertTokenizer):
+# Copied from transformers.models.bert.tokenization_bert.load_vocab
+def load_vocab(vocab_file):
+    """Loads a vocabulary file into a dictionary."""
+    vocab = collections.OrderedDict()
+    with open(vocab_file, "r", encoding="utf-8") as reader:
+        tokens = reader.readlines()
+    for index, token in enumerate(tokens):
+        token = token.rstrip("\n")
+        vocab[token] = index
+    return vocab
+
+
+# Copied from transformers.models.bert.tokenization_bert.whitespace_tokenize
+def whitespace_tokenize(text):
+    """Runs basic whitespace cleaning and splitting on a piece of text."""
+    text = text.strip()
+    if not text:
+        return []
+    tokens = text.split()
+    return tokens
+
+
+class FunnelTokenizer(PreTrainedTokenizer):
     r"""
-    Construct a Funnel Transformer tokenizer.
+    Construct a Funnel Transformer tokenizer. Based on WordPiece.
+
+    This tokenizer inherits from [`PreTrainedTokenizer`] which contains most of the main methods. Users should refer to
+    this superclass for more information regarding those methods.
 
-    [`FunnelTokenizer`] is identical to [`BertTokenizer`] and runs end-to-end tokenization: punctuation splitting and
-    wordpiece.
+    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.
+        do_basic_tokenize (`bool`, *optional*, defaults to `True`):
+            Whether or not to do basic tokenization before WordPiece.
+        never_split (`Iterable`, *optional*):
+            Collection of tokens which will never be split during tokenization. Only has an effect when
+            `do_basic_tokenize=True`
+        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.
+        bos_token (`str`, `optional`, defaults to `"<s>"`):
+            The beginning of sentence token.
+        eos_token (`str`, `optional`, defaults to `"</s>"`):
+            The end of sentence token.
+        tokenize_chinese_chars (`bool`, *optional*, defaults to `True`):
+            Whether or not to tokenize Chinese characters.
 
-    Refer to superclass [`BertTokenizer`] for usage examples and documentation concerning parameters.
+            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 BERT).
     """
 
     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
     cls_token_type_id: int = 2
 
     def __init__(
@@ -97,7 +158,6 @@ class FunnelTokenizer(BertTokenizer):
         **kwargs
     ):
         super().__init__(
-            vocab_file,
             do_lower_case=do_lower_case,
             do_basic_tokenize=do_basic_tokenize,
             never_split=never_split,
@@ -113,6 +173,123 @@ class FunnelTokenizer(BertTokenizer):
             **kwargs,
         )
 
+        if not os.path.isfile(vocab_file):
+            raise ValueError(
+                f"Can't find a vocabulary file at path '{vocab_file}'. To load the vocabulary from a Google pretrained"
+                " model use `tokenizer = FunnelTokenizer.from_pretrained(PRETRAINED_MODEL_NAME)`"
+            )
+        self.vocab = load_vocab(vocab_file)
+        self.ids_to_tokens = collections.OrderedDict([(ids, tok) for tok, ids in self.vocab.items()])
+        self.do_basic_tokenize = do_basic_tokenize
+        if do_basic_tokenize:
+            self.basic_tokenizer = BasicTokenizer(
+                do_lower_case=do_lower_case,
+                never_split=never_split,
+                tokenize_chinese_chars=tokenize_chinese_chars,
+                strip_accents=strip_accents,
+            )
+        self.wordpiece_tokenizer = WordpieceTokenizer(vocab=self.vocab, unk_token=self.unk_token)
+
+    @property
+    # Copied from transformers.models.bert.tokenization_bert.BertTokenizer.do_lower_case
+    def do_lower_case(self):
+        return self.basic_tokenizer.do_lower_case
+
+    @property
+    # Copied from transformers.models.bert.tokenization_bert.BertTokenizer.vocab_size
+    def vocab_size(self):
+        return len(self.vocab)
+
+    # Copied from transformers.models.bert.tokenization_bert.BertTokenizer.get_vocab
+    def get_vocab(self):
+        return dict(self.vocab, **self.added_tokens_encoder)
+
+    # Copied from transformers.models.bert.tokenization_bert.BertTokenizer._tokenize
+    def _tokenize(self, text):
+        split_tokens = []
+        if self.do_basic_tokenize:
+            for token in self.basic_tokenizer.tokenize(text, never_split=self.all_special_tokens):
+
+                # If the token is part of the never_split set
+                if token in self.basic_tokenizer.never_split:
+                    split_tokens.append(token)
+                else:
+                    split_tokens += self.wordpiece_tokenizer.tokenize(token)
+        else:
+            split_tokens = self.wordpiece_tokenizer.tokenize(text)
+        return split_tokens
+
+    # Copied from transformers.models.bert.tokenization_bert.BertTokenizer._convert_token_to_id
+    def _convert_token_to_id(self, token):
+        """Converts a token (str) in an id using the vocab."""
+        return self.vocab.get(token, self.vocab.get(self.unk_token))
+
+    # Copied from transformers.models.bert.tokenization_bert.BertTokenizer._convert_id_to_token
+    def _convert_id_to_token(self, index):
+        """Converts an index (integer) in a token (str) using the vocab."""
+        return self.ids_to_tokens.get(index, self.unk_token)
+
+    # Copied from transformers.models.bert.tokenization_bert.BertTokenizer.convert_tokens_to_string
+    def convert_tokens_to_string(self, tokens):
+        """Converts a sequence of tokens (string) in a single string."""
+        out_string = " ".join(tokens).replace(" ##", "").strip()
+        return out_string
+
+    # Copied from transformers.models.bert.tokenization_bert.BertTokenizer.build_inputs_with_special_tokens
+    def build_inputs_with_special_tokens(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
+        adding special tokens. A BERT 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.
+        """
+        if token_ids_1 is None:
+            return [self.cls_token_id] + token_ids_0 + [self.sep_token_id]
+        cls = [self.cls_token_id]
+        sep = [self.sep_token_id]
+        return cls + token_ids_0 + sep + token_ids_1 + sep
+
+    # Copied from transformers.models.bert.tokenization_bert.BertTokenizer.get_special_tokens_mask
+    def get_special_tokens_mask(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
+    ) -> List[int]:
+        """
+        Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
+        special tokens using the tokenizer `prepare_for_model` method.
+
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+            already_has_special_tokens (`bool`, *optional*, defaults to `False`):
+                Whether or not the token list is already formatted with special tokens for the model.
+
+        Returns:
+            `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
+        """
+
+        if already_has_special_tokens:
+            return super().get_special_tokens_mask(
+                token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
+            )
+
+        if token_ids_1 is not None:
+            return [1] + ([0] * len(token_ids_0)) + [1] + ([0] * len(token_ids_1)) + [1]
+        return [1] + ([0] * len(token_ids_0)) + [1]
+
     def create_token_type_ids_from_sequences(
         self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
     ) -> List[int]:
@@ -141,3 +318,232 @@ class FunnelTokenizer(BertTokenizer):
         if token_ids_1 is None:
             return len(cls) * [self.cls_token_type_id] + len(token_ids_0 + sep) * [0]
         return len(cls) * [self.cls_token_type_id] + len(token_ids_0 + sep) * [0] + len(token_ids_1 + sep) * [1]
+
+    # Copied from transformers.models.bert.tokenization_bert.BertTokenizer.save_vocabulary
+    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
+        index = 0
+        if os.path.isdir(save_directory):
+            vocab_file = os.path.join(
+                save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
+            )
+        else:
+            vocab_file = (filename_prefix + "-" if filename_prefix else "") + save_directory
+        with open(vocab_file, "w", encoding="utf-8") as writer:
+            for token, token_index in sorted(self.vocab.items(), key=lambda kv: kv[1]):
+                if index != token_index:
+                    logger.warning(
+                        f"Saving vocabulary to {vocab_file}: vocabulary indices are not consecutive."
+                        " Please check that the vocabulary is not corrupted!"
+                    )
+                    index = token_index
+                writer.write(token + "\n")
+                index += 1
+        return (vocab_file,)
+
+
+# Copied from transformers.models.bert.tokenization_bert.BasicTokenizer
+class BasicTokenizer(object):
+    """
+    Constructs a BasicTokenizer that will run basic tokenization (punctuation splitting, lower casing, etc.).
+
+    Args:
+        do_lower_case (`bool`, *optional*, defaults to `True`):
+            Whether or not to lowercase the input when tokenizing.
+        never_split (`Iterable`, *optional*):
+            Collection of tokens which will never be split during tokenization. Only has an effect when
+            `do_basic_tokenize=True`
+        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 BERT).
+    """
+
+    def __init__(self, do_lower_case=True, never_split=None, tokenize_chinese_chars=True, strip_accents=None):
+        if never_split is None:
+            never_split = []
+        self.do_lower_case = do_lower_case
+        self.never_split = set(never_split)
+        self.tokenize_chinese_chars = tokenize_chinese_chars
+        self.strip_accents = strip_accents
+
+    def tokenize(self, text, never_split=None):
+        """
+        Basic Tokenization of a piece of text. Split on "white spaces" only, for sub-word tokenization, see
+        WordPieceTokenizer.
+
+        Args:
+            never_split (`List[str]`, *optional*)
+                Kept for backward compatibility purposes. Now implemented directly at the base class level (see
+                [`PreTrainedTokenizer.tokenize`]) List of token not to split.
+        """
+        # union() returns a new set by concatenating the two sets.
+        never_split = self.never_split.union(set(never_split)) if never_split else self.never_split
+        text = self._clean_text(text)
+
+        # This was added on November 1st, 2018 for the multilingual and Chinese
+        # models. This is also applied to the English models now, but it doesn't
+        # matter since the English models were not trained on any Chinese data
+        # and generally don't have any Chinese data in them (there are Chinese
+        # characters in the vocabulary because Wikipedia does have some Chinese
+        # words in the English Wikipedia.).
+        if self.tokenize_chinese_chars:
+            text = self._tokenize_chinese_chars(text)
+        orig_tokens = whitespace_tokenize(text)
+        split_tokens = []
+        for token in orig_tokens:
+            if token not in never_split:
+                if self.do_lower_case:
+                    token = token.lower()
+                    if self.strip_accents is not False:
+                        token = self._run_strip_accents(token)
+                elif self.strip_accents:
+                    token = self._run_strip_accents(token)
+            split_tokens.extend(self._run_split_on_punc(token, never_split))
+
+        output_tokens = whitespace_tokenize(" ".join(split_tokens))
+        return output_tokens
+
+    def _run_strip_accents(self, text):
+        """Strips accents from a piece of text."""
+        text = unicodedata.normalize("NFD", text)
+        output = []
+        for char in text:
+            cat = unicodedata.category(char)
+            if cat == "Mn":
+                continue
+            output.append(char)
+        return "".join(output)
+
+    def _run_split_on_punc(self, text, never_split=None):
+        """Splits punctuation on a piece of text."""
+        if never_split is not None and text in never_split:
+            return [text]
+        chars = list(text)
+        i = 0
+        start_new_word = True
+        output = []
+        while i < len(chars):
+            char = chars[i]
+            if _is_punctuation(char):
+                output.append([char])
+                start_new_word = True
+            else:
+                if start_new_word:
+                    output.append([])
+                start_new_word = False
+                output[-1].append(char)
+            i += 1
+
+        return ["".join(x) for x in output]
+
+    def _tokenize_chinese_chars(self, text):
+        """Adds whitespace around any CJK character."""
+        output = []
+        for char in text:
+            cp = ord(char)
+            if self._is_chinese_char(cp):
+                output.append(" ")
+                output.append(char)
+                output.append(" ")
+            else:
+                output.append(char)
+        return "".join(output)
+
+    def _is_chinese_char(self, cp):
+        """Checks whether CP is the codepoint of a CJK character."""
+        # This defines a "chinese character" as anything in the CJK Unicode block:
+        #   https://en.wikipedia.org/wiki/CJK_Unified_Ideographs_(Unicode_block)
+        #
+        # Note that the CJK Unicode block is NOT all Japanese and Korean characters,
+        # despite its name. The modern Korean Hangul alphabet is a different block,
+        # as is Japanese Hiragana and Katakana. Those alphabets are used to write
+        # space-separated words, so they are not treated specially and handled
+        # like the all of the other languages.
+        if (
+            (cp >= 0x4E00 and cp <= 0x9FFF)
+            or (cp >= 0x3400 and cp <= 0x4DBF)  #
+            or (cp >= 0x20000 and cp <= 0x2A6DF)  #
+            or (cp >= 0x2A700 and cp <= 0x2B73F)  #
+            or (cp >= 0x2B740 and cp <= 0x2B81F)  #
+            or (cp >= 0x2B820 and cp <= 0x2CEAF)  #
+            or (cp >= 0xF900 and cp <= 0xFAFF)
+            or (cp >= 0x2F800 and cp <= 0x2FA1F)  #
+        ):  #
+            return True
+
+        return False
+
+    def _clean_text(self, text):
+        """Performs invalid character removal and whitespace cleanup on text."""
+        output = []
+        for char in text:
+            cp = ord(char)
+            if cp == 0 or cp == 0xFFFD or _is_control(char):
+                continue
+            if _is_whitespace(char):
+                output.append(" ")
+            else:
+                output.append(char)
+        return "".join(output)
+
+
+# Copied from transformers.models.bert.tokenization_bert.WordpieceTokenizer
+class WordpieceTokenizer(object):
+    """Runs WordPiece tokenization."""
+
+    def __init__(self, vocab, unk_token, max_input_chars_per_word=100):
+        self.vocab = vocab
+        self.unk_token = unk_token
+        self.max_input_chars_per_word = max_input_chars_per_word
+
+    def tokenize(self, text):
+        """
+        Tokenizes a piece of text into its word pieces. This uses a greedy longest-match-first algorithm to perform
+        tokenization using the given vocabulary.
+
+        For example, `input = "unaffable"` wil return as output `["un", "##aff", "##able"]`.
+
+        Args:
+            text: A single token or whitespace separated tokens. This should have
+                already been passed through *BasicTokenizer*.
+
+        Returns:
+            A list of wordpiece tokens.
+        """
+
+        output_tokens = []
+        for token in whitespace_tokenize(text):
+            chars = list(token)
+            if len(chars) > self.max_input_chars_per_word:
+                output_tokens.append(self.unk_token)
+                continue
+
+            is_bad = False
+            start = 0
+            sub_tokens = []
+            while start < len(chars):
+                end = len(chars)
+                cur_substr = None
+                while start < end:
+                    substr = "".join(chars[start:end])
+                    if start > 0:
+                        substr = "##" + substr
+                    if substr in self.vocab:
+                        cur_substr = substr
+                        break
+                    end -= 1
+                if cur_substr is None:
+                    is_bad = True
+                    break
+                sub_tokens.append(cur_substr)
+                start = end
+
+            if is_bad:
+                output_tokens.append(self.unk_token)
+            else:
+                output_tokens.extend(sub_tokens)
+        return output_tokens

src/transformers/models/funnel/tokenization_funnel_fast.py

@@ -14,10 +14,13 @@
 # limitations under the License.
 """ Tokenization class for Funnel Transformer."""
 
-from typing import List, Optional
+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_funnel import FunnelTokenizer
 
 
@@ -88,21 +91,55 @@ PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {f"funnel-transformer/{name}": 512 for
 PRETRAINED_INIT_CONFIGURATION = {f"funnel-transformer/{name}": {"do_lower_case": True} for name in _model_names}
 
 
-class FunnelTokenizerFast(BertTokenizerFast):
+class FunnelTokenizerFast(PreTrainedTokenizerFast):
     r"""
-    Construct a "fast" Funnel Transformer tokenizer (backed by HuggingFace's *tokenizers* library).
+    Construct a "fast" Funnel Transformer tokenizer (backed by HuggingFace's *tokenizers* library). Based on WordPiece.
 
-    [`FunnelTokenizerFast`] 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)).
+        bos_token (`str`, `optional`, defaults to `"<s>"`):
+            The beginning of sentence token.
+        eos_token (`str`, `optional`, defaults to `"</s>"`):
+            The end of sentence token.
+        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 BERT).
+        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
     slow_tokenizer_class = FunnelTokenizer
+    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
     cls_token_type_id: int = 2
 
     def __init__(
@@ -141,6 +178,45 @@ class FunnelTokenizerFast(BertTokenizerFast):
             **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
+
+    # Copied from transformers.models.bert.tokenization_bert_fast.BertTokenizerFast.build_inputs_with_special_tokens with BERT->Funnel
+    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 Funnel 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]:
@@ -169,3 +245,8 @@ class FunnelTokenizerFast(BertTokenizerFast):
         if token_ids_1 is None:
             return len(cls) * [self.cls_token_type_id] + len(token_ids_0 + sep) * [0]
         return len(cls) * [self.cls_token_type_id] + len(token_ids_0 + sep) * [0] + len(token_ids_1 + sep) * [1]
+
+    # Copied from transformers.models.bert.tokenization_bert_fast.BertTokenizerFast.save_vocabulary
+    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)