Delete tokenization_qwen.py

tokenization_qwen.py

@@ -1,264 +0,0 @@
-# Copyright (c) Alibaba Cloud.
-#
-# This source code is licensed under the license found in the
-# LICENSE file in the root directory of this source tree.
-
-"""Tokenization classes for QWen."""
-
-import base64
-import logging
-import os
-import unicodedata
-from typing import Collection, Dict, List, Set, Tuple, Union
-
-import tiktoken
-from transformers import PreTrainedTokenizer, AddedToken
-
-logger = logging.getLogger(__name__)
-
-
-VOCAB_FILES_NAMES = {"vocab_file": "qwen.tiktoken"}
-
-PAT_STR = r"""(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+"""
-ENDOFTEXT = "<|endoftext|>"
-IMSTART = "<|im_start|>"
-IMEND = "<|im_end|>"
-# as the default behavior is changed to allow special tokens in
-# regular texts, the surface forms of special tokens need to be
-# as different as possible to minimize the impact
-EXTRAS = tuple((f"<|extra_{i}|>" for i in range(205)))
-SPECIAL_TOKENS = (
-    ENDOFTEXT,
-    IMSTART,
-    IMEND,
-) + EXTRAS
-
-
-def _load_tiktoken_bpe(tiktoken_bpe_file: str) -> Dict[bytes, int]:
-    with open(tiktoken_bpe_file, "rb") as f:
-        contents = f.read()
-    return {
-        base64.b64decode(token): int(rank)
-        for token, rank in (line.split() for line in contents.splitlines() if line)
-    }
-
-class QWenTokenizer(PreTrainedTokenizer):
-    """QWen tokenizer."""
-
-    vocab_files_names = VOCAB_FILES_NAMES
-
-    def __init__(
-        self,
-        vocab_file,
-        errors="replace",
-        image_start_tag='<img>',
-        image_end_tag='</img>',
-        image_pad_tag='<imgpad>',
-        ref_start_tag='<ref>',
-        ref_end_tag='</ref>',
-        box_start_tag='<box>',
-        box_end_tag='</box>',
-        quad_start_tag='<quad>',
-        quad_end_tag='</quad>',
-        **kwargs,
-    ):
-        super().__init__(**kwargs)
-        
-        self.image_start_tag = image_start_tag
-        self.image_end_tag = image_end_tag
-        self.image_pad_tag = image_pad_tag
-        self.ref_start_tag = ref_start_tag
-        self.ref_end_tag = ref_end_tag
-        self.box_start_tag = box_start_tag
-        self.box_end_tag = box_end_tag
-        self.quad_start_tag = quad_start_tag
-        self.quad_end_tag = quad_end_tag
-        self.IMAGE_ST = (
-            ref_start_tag, ref_end_tag,
-            box_start_tag, box_end_tag,
-            quad_start_tag, quad_end_tag,
-            image_start_tag, image_end_tag,
-            image_pad_tag
-        )
-
-        self.errors = errors  # how to handle errors in decoding
-
-        self.mergeable_ranks = _load_tiktoken_bpe(vocab_file)  # type: dict[bytes, int]
-        self.special_tokens = {
-            token: index
-            for index, token in enumerate(
-                SPECIAL_TOKENS + self.IMAGE_ST, start=len(self.mergeable_ranks)
-            )
-        }
-        
-        self.img_start_id = self.special_tokens[self.image_start_tag]
-        self.img_end_id = self.special_tokens[self.image_end_tag]
-        self.img_pad_id = self.special_tokens[self.image_pad_tag]
-        self.ref_start_id = self.special_tokens[self.ref_start_tag]
-        self.ref_end_id = self.special_tokens[self.ref_end_tag]
-        self.box_start_id = self.special_tokens[self.box_start_tag]
-        self.box_end_id = self.special_tokens[self.box_end_tag]
-        self.quad_start_id = self.special_tokens[self.quad_start_tag]
-        self.quad_end_id = self.special_tokens[self.quad_end_tag]
-
-        enc = tiktoken.Encoding(
-            "Qwen",
-            pat_str=PAT_STR,
-            mergeable_ranks=self.mergeable_ranks,
-            special_tokens=self.special_tokens,
-        )
-        assert (
-            len(self.mergeable_ranks) + len(self.special_tokens) == enc.n_vocab
-        ), f"{len(self.mergeable_ranks) + len(self.special_tokens)} != {enc.n_vocab} in encoding"
-
-        self.decoder = {
-            v: k for k, v in self.mergeable_ranks.items()
-        }  # type: dict[int, bytes|str]
-        self.decoder.update({v: k for k, v in self.special_tokens.items()})
-
-        self.tokenizer = enc  # type: tiktoken.Encoding
-
-        self.eod_id = self.tokenizer.eot_token
-        self.im_start_id = self.special_tokens[IMSTART]
-        self.im_end_id = self.special_tokens[IMEND]
-
-    def __len__(self) -> int:
-        return self.tokenizer.n_vocab
-
-    def get_vocab(self) -> Dict[bytes, int]:
-        return self.mergeable_ranks
-
-    def convert_tokens_to_ids(
-        self, tokens: Union[bytes, str, List[Union[bytes, str]]]
-    ) -> List[int]:
-        ids = []
-        if isinstance(tokens, (str, bytes)):
-            if tokens in self.special_tokens:
-                return self.special_tokens[tokens]
-            else:
-                return self.mergeable_ranks.get(tokens)
-        for token in tokens:
-            if token in self.special_tokens:
-                ids.append(self.special_tokens[token])
-            else:
-                ids.append(self.mergeable_ranks.get(token))
-        return ids
-
-    def _add_tokens(self, new_tokens: Union[List[str], List[AddedToken]], special_tokens: bool = False) -> int:
-        if not special_tokens and new_tokens:
-            raise ValueError('Adding regular tokens is not supported')
-        for token in new_tokens:
-            surface_form = token.content if isinstance(token, AddedToken) else token
-            if surface_form not in SPECIAL_TOKENS:
-                raise ValueError('Adding unknown special tokens is not supported')
-        return 0
-
-    def save_vocabulary(self, save_directory: str, **kwargs) -> Tuple[str]:
-        """
-        Save only the vocabulary of the tokenizer (vocabulary).
-
-        Returns:
-            `Tuple(str)`: Paths to the files saved.
-        """
-        file_path = os.path.join(save_directory, "qwen.tiktoken")
-        with open(file_path, "w", encoding="utf8") as w:
-            for k, v in self.mergeable_ranks.items():
-                line = base64.b64encode(k).decode("utf8") + " " + str(v) + "\n"
-                w.write(line)
-        return (file_path,)
-
-    def tokenize(
-        self,
-        text: str,
-        allowed_special: Union[Set, str] = "all",
-        disallowed_special: Union[Collection, str] = (),
-        **kwargs,
-    ) -> List[Union[bytes, str]]:
-        """
-        Converts a string in a sequence of tokens.
-
-        Args:
-            text (`str`):
-                The sequence to be encoded.
-            allowed_special (`Literal["all"]` or `set`):
-                The surface forms of the tokens to be encoded as special tokens in regular texts.
-                Default to "all".
-            disallowed_special (`Literal["all"]` or `Collection`):
-                The surface forms of the tokens that should not be in regular texts and trigger errors.
-                Default to an empty tuple.
-
-            kwargs (additional keyword arguments, *optional*):
-                Will be passed to the underlying model specific encode method.
-
-        Returns:
-            `List[bytes|str]`: The list of tokens.
-        """
-        tokens = []
-        text = unicodedata.normalize("NFC", text)
-
-        # this implementation takes a detour: text -> token id -> token surface forms
-        for t in self.tokenizer.encode(
-            text, allowed_special=allowed_special, disallowed_special=disallowed_special
-        ):
-            tokens.append(self.decoder[t])
-        return tokens
-
-    def convert_tokens_to_string(self, tokens: List[Union[bytes, str]]) -> str:
-        """
-        Converts a sequence of tokens in a single string.
-        """
-        text = ""
-        temp = b""
-        for t in tokens:
-            if isinstance(t, str):
-                if temp:
-                    text += temp.decode("utf-8", errors=self.errors)
-                    temp = b""
-                text += t
-            elif isinstance(t, bytes):
-                temp += t
-            else:
-                raise TypeError("token should only be of type types or str")
-        if temp:
-            text += temp.decode("utf-8", errors=self.errors)
-        return text
-
-    @property
-    def vocab_size(self):
-        return self.tokenizer.n_vocab
-
-    def _convert_id_to_token(self, index: int) -> Union[bytes, str]:
-        """Converts an id to a token, special tokens included"""
-        if index in self.decoder:
-            return self.decoder[index]
-        raise ValueError("unknown ids")
-
-    def _convert_token_to_id(self, token: Union[bytes, str]) -> int:
-        """Converts a token to an id using the vocab, special tokens included"""
-        if token in self.special_tokens:
-            return self.special_tokens[token]
-        if token in self.mergeable_ranks:
-            return self.mergeable_ranks[token]
-        raise ValueError("unknown token")
-
-    def _tokenize(self, text: str, **kwargs):
-        """
-        Converts a string in a sequence of tokens (string), using the tokenizer. Split in words for word-based
-        vocabulary or sub-words for sub-word-based vocabularies (BPE/SentencePieces/WordPieces).
-
-        Do NOT take care of added tokens.
-        """
-        raise NotImplementedError
-
-    def _decode(
-        self,
-        token_ids: Union[int, List[int]],
-        skip_special_tokens: bool = False,
-        errors: str = None,
-        **kwargs,
-    ) -> str:
-        if isinstance(token_ids, int):
-            token_ids = [token_ids]
-        if skip_special_tokens:
-            token_ids = [i for i in token_ids if i < self.eod_id]
-        return self.tokenizer.decode(token_ids, errors=errors or self.errors)