GPTTokenizer dependency removed from deberta class (#19551)

* GPTTOkenizer dependency removed from deberta class

Fixup

made the Deberta Tokenizer fast independent of GPT-2 tokenizer

Copied annotation added

Done the dependency removal

* Added some missing copied statement

* Added some copied statements

src/transformers/models/deberta/tokenization_deberta.py

@@ -14,13 +14,19 @@
 # limitations under the License.
 """ Tokenization class for model DeBERTa."""
 
-from typing import List, Optional
+import json
+import os
+from typing import TYPE_CHECKING, List, Optional, Tuple
 
-from ...tokenization_utils import AddedToken
+import regex as re
+
+from ...tokenization_utils import AddedToken, PreTrainedTokenizer
 from ...utils import logging
-from ..gpt2.tokenization_gpt2 import GPT2Tokenizer
 
 
+if TYPE_CHECKING:
+    from transformers.pipelines.conversational import Conversation
+
 logger = logging.get_logger(__name__)
 
 VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt"}
@@ -63,30 +69,107 @@ PRETRAINED_INIT_CONFIGURATION = {
 }
 
 
-class DebertaTokenizer(GPT2Tokenizer):
-    r"""
-    Constructs a DeBERTa tokenizer, which runs end-to-end tokenization: punctuation splitting + wordpiece
+# Copied from transformers.models.gpt2.tokenization_gpt2.bytes_to_unicode
+def bytes_to_unicode():
+    """
+    Returns list of utf-8 byte and a mapping to unicode strings. We specifically avoids mapping to whitespace/control
+    characters the bpe code barfs on.
+
+    The reversible bpe codes work on unicode strings. This means you need a large # of unicode characters in your vocab
+    if you want to avoid UNKs. When you're at something like a 10B token dataset you end up needing around 5K for
+    decent coverage. This is a significant percentage of your normal, say, 32K bpe vocab. To avoid that, we want lookup
+    tables between utf-8 bytes and unicode strings.
+    """
+    bs = (
+        list(range(ord("!"), ord("~") + 1)) + list(range(ord("¡"), ord("¬") + 1)) + list(range(ord("®"), ord("ÿ") + 1))
+    )
+    cs = bs[:]
+    n = 0
+    for b in range(2**8):
+        if b not in bs:
+            bs.append(b)
+            cs.append(2**8 + n)
+            n += 1
+    cs = [chr(n) for n in cs]
+    return dict(zip(bs, cs))
+
+
+# Copied from transformers.models.gpt2.tokenization_gpt2.get_pairs
+def get_pairs(word):
+    """
+    Return set of symbol pairs in a word.
+
+    Word is represented as tuple of symbols (symbols being variable-length strings).
+    """
+    pairs = set()
+    prev_char = word[0]
+    for char in word[1:]:
+        pairs.add((prev_char, char))
+        prev_char = char
+    return pairs
+
+
+class DebertaTokenizer(PreTrainedTokenizer):
+    """
+    Construct a DeBERTa tokenizer. Based on byte-level Byte-Pair-Encoding.
+
+    This tokenizer has been trained to treat spaces like parts of the tokens (a bit like sentencepiece) so a word will
+    be encoded differently whether it is at the beginning of the sentence (without space) or not:
+
+    ```
+    >>> from transformers import DebertaTokenizer
+    >>> tokenizer = DebertaTokenizer.from_pretrained("microsoft/deberta-base")
+    >>> tokenizer("Hello world")['input_ids']
+    [15496, 995]
+    >>> tokenizer(" Hello world")['input_ids']
+    [18435, 995]
+    ```
+
+    You can get around that behavior by passing `add_prefix_space=True` when instantiating this tokenizer or when you
+    call it on some text, but since the model was not pretrained this way, it might yield a decrease in performance.
+
+    <Tip>
+
+    When used with `is_split_into_words=True`, this tokenizer will add a space before each word (even the first one).
+
+    </Tip>
+
+    This tokenizer inherits from [`PreTrainedTokenizer`] which contains most of the main methods. Users should refer to
+    this superclass for more information regarding those methods.
 
     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.
+            Path to the vocabulary file.
+        merges_file (`str`):
+            Path to the merges file.
+        errors (`str`, *optional*, defaults to `"replace"`):
+            Paradigm to follow when decoding bytes to UTF-8. See
+            [bytes.decode](https://docs.python.org/3/library/stdtypes.html#bytes.decode) for more information.
+        bos_token (`str`, *optional*, defaults to `"[CLS]"`):
+            The beginning of sequence token.
+        eos_token (`str`, *optional*, defaults to `"[SEP]"`):
+            The end of sequence token.
         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.
+        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.
+        pad_token (`str`, *optional*, defaults to `"[PAD]"`):
+            The token used for padding, for example when batching sequences of different lengths.
         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.
+        add_prefix_space (`bool`, *optional*, defaults to `False`):
+            Whether or not to add an initial space to the input. This allows to treat the leading word just as any
+            other word. (Deberta tokenizer detect beginning of words by the preceding space).
+        add_bos_token (`bool`, *optional*, defaults to `False`):
+            Whether or not to add an initial <|endoftext|> to the input. This allows to treat the leading word just as
+            any other word.
     """
 
     vocab_files_names = VOCAB_FILES_NAMES
@@ -107,6 +190,7 @@ class DebertaTokenizer(GPT2Tokenizer):
         pad_token="[PAD]",
         mask_token="[MASK]",
         add_prefix_space=False,
+        add_bos_token=False,
         **kwargs
     ):
         bos_token = AddedToken(bos_token, lstrip=False, rstrip=False) if isinstance(bos_token, str) else bos_token
@@ -120,8 +204,6 @@ class DebertaTokenizer(GPT2Tokenizer):
         mask_token = AddedToken(mask_token, lstrip=True, rstrip=False) if isinstance(mask_token, str) else mask_token
 
         super().__init__(
-            vocab_file=vocab_file,
-            merges_file=merges_file,
             errors=errors,
             bos_token=bos_token,
             eos_token=eos_token,
@@ -131,8 +213,78 @@ class DebertaTokenizer(GPT2Tokenizer):
             pad_token=pad_token,
             mask_token=mask_token,
             add_prefix_space=add_prefix_space,
+            add_bos_token=add_bos_token,
             **kwargs,
         )
+        self.add_bos_token = add_bos_token
+
+        with open(vocab_file, encoding="utf-8") as vocab_handle:
+            self.encoder = json.load(vocab_handle)
+        self.decoder = {v: k for k, v in self.encoder.items()}
+        self.errors = errors  # how to handle errors in decoding
+        self.byte_encoder = bytes_to_unicode()
+        self.byte_decoder = {v: k for k, v in self.byte_encoder.items()}
+        with open(merges_file, encoding="utf-8") as merges_handle:
+            bpe_merges = merges_handle.read().split("\n")[1:-1]
+        bpe_merges = [tuple(merge.split()) for merge in bpe_merges]
+        self.bpe_ranks = dict(zip(bpe_merges, range(len(bpe_merges))))
+        self.cache = {}
+        self.add_prefix_space = add_prefix_space
+
+        # Should have added re.IGNORECASE so BPE merges can happen for capitalized versions of contractions
+        self.pat = re.compile(r"""'s|'t|'re|'ve|'m|'ll|'d| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+""")
+
+    @property
+    # Copied from transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer.vocab_size
+    def vocab_size(self):
+        return len(self.encoder)
+
+    # Copied from transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer.get_vocab
+    def get_vocab(self):
+        return dict(self.encoder, **self.added_tokens_encoder)
+
+    # Copied from transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer.bpe
+    def bpe(self, token):
+        if token in self.cache:
+            return self.cache[token]
+        word = tuple(token)
+        pairs = get_pairs(word)
+
+        if not pairs:
+            return token
+
+        while True:
+            bigram = min(pairs, key=lambda pair: self.bpe_ranks.get(pair, float("inf")))
+            if bigram not in self.bpe_ranks:
+                break
+            first, second = bigram
+            new_word = []
+            i = 0
+            while i < len(word):
+                try:
+                    j = word.index(first, i)
+                except ValueError:
+                    new_word.extend(word[i:])
+                    break
+                else:
+                    new_word.extend(word[i:j])
+                    i = j
+
+                if word[i] == first and i < len(word) - 1 and word[i + 1] == second:
+                    new_word.append(first + second)
+                    i += 2
+                else:
+                    new_word.append(word[i])
+                    i += 1
+            new_word = tuple(new_word)
+            word = new_word
+            if len(word) == 1:
+                break
+            else:
+                pairs = get_pairs(word)
+        word = " ".join(word)
+        self.cache[token] = word
+        return word
 
     def build_inputs_with_special_tokens(
         self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
@@ -216,8 +368,75 @@ class DebertaTokenizer(GPT2Tokenizer):
             return len(cls + token_ids_0 + sep) * [0]
         return len(cls + token_ids_0 + sep) * [0] + len(token_ids_1 + sep) * [1]
 
+    # Copied from transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer._tokenize
+    def _tokenize(self, text):
+        """Tokenize a string."""
+        bpe_tokens = []
+        for token in re.findall(self.pat, text):
+            token = "".join(
+                self.byte_encoder[b] for b in token.encode("utf-8")
+            )  # Maps all our bytes to unicode strings, avoiding control tokens of the BPE (spaces in our case)
+            bpe_tokens.extend(bpe_token for bpe_token in self.bpe(token).split(" "))
+        return bpe_tokens
+
+    # Copied from transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer._convert_token_to_id
+    def _convert_token_to_id(self, token):
+        """Converts a token (str) in an id using the vocab."""
+        return self.encoder.get(token, self.encoder.get(self.unk_token))
+
+    # Copied from transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer._convert_id_to_token
+    def _convert_id_to_token(self, index):
+        """Converts an index (integer) in a token (str) using the vocab."""
+        return self.decoder.get(index)
+
+    # Copied from transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer.convert_tokens_to_string
+    def convert_tokens_to_string(self, tokens):
+        """Converts a sequence of tokens (string) in a single string."""
+        text = "".join(tokens)
+        text = bytearray([self.byte_decoder[c] for c in text]).decode("utf-8", errors=self.errors)
+        return text
+
+    # Copied from transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer.save_vocabulary
+    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
+        if not os.path.isdir(save_directory):
+            logger.error(f"Vocabulary path ({save_directory}) should be a directory")
+            return
+        vocab_file = os.path.join(
+            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
+        )
+        merge_file = os.path.join(
+            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["merges_file"]
+        )
+
+        with open(vocab_file, "w", encoding="utf-8") as f:
+            f.write(json.dumps(self.encoder, indent=2, sort_keys=True, ensure_ascii=False) + "\n")
+
+        index = 0
+        with open(merge_file, "w", encoding="utf-8") as writer:
+            writer.write("#version: 0.2\n")
+            for bpe_tokens, token_index in sorted(self.bpe_ranks.items(), key=lambda kv: kv[1]):
+                if index != token_index:
+                    logger.warning(
+                        f"Saving vocabulary to {merge_file}: BPE merge indices are not consecutive."
+                        " Please check that the tokenizer is not corrupted!"
+                    )
+                    index = token_index
+                writer.write(" ".join(bpe_tokens) + "\n")
+                index += 1
+
+        return vocab_file, merge_file
+
     def prepare_for_tokenization(self, text, is_split_into_words=False, **kwargs):
         add_prefix_space = kwargs.pop("add_prefix_space", self.add_prefix_space)
         if (is_split_into_words or add_prefix_space) and (len(text) > 0 and not text[0].isspace()):
             text = " " + text
         return (text, kwargs)
+
+    # Copied from transformers.models.gpt2.tokenization_gpt2.GPT2Tokenizer._build_conversation_input_ids
+    def _build_conversation_input_ids(self, conversation: "Conversation") -> List[int]:
+        input_ids = []
+        for is_user, text in conversation.iter_texts():
+            input_ids.extend(self.encode(text, add_special_tokens=False) + [self.eos_token_id])
+        if len(input_ids) > self.model_max_length:
+            input_ids = input_ids[-self.model_max_length :]
+        return input_ids

src/transformers/models/deberta/tokenization_deberta_fast.py

@@ -14,14 +14,21 @@
 # limitations under the License.
 """ Fast Tokenization class for model DeBERTa."""
 
-from typing import List, Optional
+import json
+from typing import TYPE_CHECKING, List, Optional, Tuple
 
-from ...tokenization_utils_base import AddedToken
+from tokenizers import pre_tokenizers
+
+from ...tokenization_utils_base import AddedToken, BatchEncoding
+from ...tokenization_utils_fast import PreTrainedTokenizerFast
 from ...utils import logging
-from ..gpt2.tokenization_gpt2_fast import GPT2TokenizerFast
 from .tokenization_deberta import DebertaTokenizer
 
 
+if TYPE_CHECKING:
+    from transformers.pipelines.conversational import Conversation
+
+
 logger = logging.get_logger(__name__)
 
 VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt", "tokenizer_file": "tokenizer.json"}
@@ -64,31 +71,67 @@ PRETRAINED_INIT_CONFIGURATION = {
 }
 
 
-class DebertaTokenizerFast(GPT2TokenizerFast):
+class DebertaTokenizerFast(PreTrainedTokenizerFast):
     """
-    Constructs a "fast" DeBERTa tokenizer, which runs end-to-end tokenization: punctuation splitting + wordpiece. It is
-    backed by HuggingFace's *tokenizers* library.
+    Construct a "fast" DeBERTa tokenizer (backed by HuggingFace's *tokenizers* library). Based on byte-level
+    Byte-Pair-Encoding.
+
+    This tokenizer has been trained to treat spaces like parts of the tokens (a bit like sentencepiece) so a word will
+    be encoded differently whether it is at the beginning of the sentence (without space) or not:
+
+    ```
+    >>> from transformers import DebertaTokenizerFast
+    >>> tokenizer = DebertaTokenizerFast.from_pretrained("microsoft/deberta-base")
+    >>> tokenizer("Hello world")['input_ids']
+    [15496, 995]
+    >>> tokenizer(" Hello world")['input_ids']
+    [18435, 995]
+    ```
+
+    You can get around that behavior by passing `add_prefix_space=True` when instantiating this tokenizer, but since
+    the model was not pretrained this way, it might yield a decrease in performance.
+
+    <Tip>
+
+    When used with `is_split_into_words=True`, this tokenizer needs to be instantiated with `add_prefix_space=True`.
+
+    </Tip>
+
+    This tokenizer inherits from [`PreTrainedTokenizerFast`] which contains most of the main methods. Users should
+    refer to this superclass for more information regarding those methods.
 
     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.
+            Path to the vocabulary file.
+        merges_file (`str`):
+            Path to the merges file.
+        tokenizer_file (`str`, *optional*):
+            The path to a tokenizer file to use instead of the vocab file.
+        errors (`str`, *optional*, defaults to `"replace"`):
+            Paradigm to follow when decoding bytes to UTF-8. See
+            [bytes.decode](https://docs.python.org/3/library/stdtypes.html#bytes.decode) for more information.
+        bos_token (`str`, *optional*, defaults to `"[CLS]"`):
+            The beginning of sequence token.
+        eos_token (`str`, *optional*, defaults to `"[SEP]"`):
+            The end of sequence token.
         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.
+        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.
+        pad_token (`str`, *optional*, defaults to `"[PAD]"`):
+            The token used for padding, for example when batching sequences of different lengths.
         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.
+        add_prefix_space (`bool`, *optional*, defaults to `False`):
+            Whether or not to add an initial space to the input. This allows to treat the leading word just as any
+            other word. (Deberta tokenizer detect beginning of words by the preceding space).
     """
 
     vocab_files_names = VOCAB_FILES_NAMES
@@ -129,6 +172,15 @@ class DebertaTokenizerFast(GPT2TokenizerFast):
             add_prefix_space=add_prefix_space,
             **kwargs,
         )
+        self.add_bos_token = kwargs.pop("add_bos_token", False)
+
+        pre_tok_state = json.loads(self.backend_tokenizer.pre_tokenizer.__getstate__())
+        if pre_tok_state.get("add_prefix_space", add_prefix_space) != add_prefix_space:
+            pre_tok_class = getattr(pre_tokenizers, pre_tok_state.pop("type"))
+            pre_tok_state["add_prefix_space"] = add_prefix_space
+            self.backend_tokenizer.pre_tokenizer = pre_tok_class(**pre_tok_state)
+
+        self.add_prefix_space = add_prefix_space
 
     @property
     def mask_token(self) -> str:
@@ -209,3 +261,40 @@ class DebertaTokenizerFast(GPT2TokenizerFast):
         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]
+
+    # Copied from transformers.models.gpt2.tokenization_gpt2_fast.GPT2TokenizerFast._batch_encode_plus
+    def _batch_encode_plus(self, *args, **kwargs) -> BatchEncoding:
+        is_split_into_words = kwargs.get("is_split_into_words", False)
+        assert self.add_prefix_space or not is_split_into_words, (
+            f"You need to instantiate {self.__class__.__name__} with add_prefix_space=True "
+            "to use it with pretokenized inputs."
+        )
+
+        return super()._batch_encode_plus(*args, **kwargs)
+
+    # Copied from transformers.models.gpt2.tokenization_gpt2_fast.GPT2TokenizerFast._encode_plus
+    def _encode_plus(self, *args, **kwargs) -> BatchEncoding:
+        is_split_into_words = kwargs.get("is_split_into_words", False)
+
+        assert self.add_prefix_space or not is_split_into_words, (
+            f"You need to instantiate {self.__class__.__name__} with add_prefix_space=True "
+            "to use it with pretokenized inputs."
+        )
+
+        return super()._encode_plus(*args, **kwargs)
+
+    # Copied from transformers.models.gpt2.tokenization_gpt2_fast.GPT2TokenizerFast.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)
+
+    # Copied from transformers.models.gpt2.tokenization_gpt2_fast.GPT2TokenizerFast._build_conversation_input_ids
+    def _build_conversation_input_ids(self, conversation: "Conversation") -> List[int]:
+        """This corresponds to DialoGPT variants of models."""
+        input_ids = []
+        for is_user, text in conversation.iter_texts():
+            input_ids.extend(self.encode(text, add_special_tokens=False) + [self.eos_token_id])
+
+        if len(input_ids) > self.model_max_length:
+            input_ids = input_ids[-self.model_max_length :]
+        return input_ids