Source code for transformers.models.gpt2.tokenization_gpt2

# coding=utf-8
# Copyright 2018 The Open AI Team Authors and The HuggingFace Inc. team.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# See the License for the specific language governing permissions and
# limitations under the License.
"""Tokenization classes for OpenAI GPT."""

import json
import os
from functools import lru_cache
from typing import TYPE_CHECKING, List, Optional, Tuple

import regex as re

from ...tokenization_utils import AddedToken, PreTrainedTokenizer
from ...utils import logging

    from transformers.pipelines.conversational import Conversation

logger = logging.get_logger(__name__)

    "vocab_file": "vocab.json",
    "merges_file": "merges.txt",

    "vocab_file": {
        "gpt2": "",
        "gpt2-medium": "",
        "gpt2-large": "",
        "gpt2-xl": "",
        "distilgpt2": "",
    "merges_file": {
        "gpt2": "",
        "gpt2-medium": "",
        "gpt2-large": "",
        "gpt2-xl": "",
        "distilgpt2": "",

    "gpt2": 1024,
    "gpt2-medium": 1024,
    "gpt2-large": 1024,
    "gpt2-xl": 1024,
    "distilgpt2": 1024,

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:
            cs.append(2 ** 8 + n)
            n += 1
    cs = [chr(n) for n in cs]
    return dict(zip(bs, cs))

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

[docs]class GPT2Tokenizer(PreTrainedTokenizer): """ Construct a GPT-2 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 GPT2Tokenizer >>> tokenizer = GPT2Tokenizer.from_pretrained("gpt2") >>> 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. .. note:: When used with ``is_split_into_words=True``, this tokenizer will add a space before each word (even the first one). This tokenizer inherits from :class:`~transformers.PreTrainedTokenizer` which contains most of the main methods. Users should refer to this superclass for more information regarding those methods. Args: vocab_file (:obj:`str`): Path to the vocabulary file. merges_file (:obj:`str`): Path to the merges file. errors (:obj:`str`, `optional`, defaults to :obj:`"replace"`): Paradigm to follow when decoding bytes to UTF-8. See `bytes.decode <>`__ for more information. unk_token (:obj:`str`, `optional`, defaults to :obj:`<|endoftext|>`): 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. bos_token (:obj:`str`, `optional`, defaults to :obj:`<|endoftext|>`): The beginning of sequence token. eos_token (:obj:`str`, `optional`, defaults to :obj:`<|endoftext|>`): The end of sequence token. add_prefix_space (:obj:`bool`, `optional`, defaults to :obj:`False`): Whether or not to add an initial space to the input. This allows to treat the leading word just as any other word. (GPT2 tokenizer detect beginning of words by the preceding space). """ vocab_files_names = VOCAB_FILES_NAMES pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES model_input_names = ["input_ids", "attention_mask"] def __init__( self, vocab_file, merges_file, errors="replace", unk_token="<|endoftext|>", bos_token="<|endoftext|>", eos_token="<|endoftext|>", add_prefix_space=False, **kwargs ): bos_token = AddedToken(bos_token, lstrip=False, rstrip=False) if isinstance(bos_token, str) else bos_token eos_token = AddedToken(eos_token, lstrip=False, rstrip=False) if isinstance(eos_token, str) else eos_token unk_token = AddedToken(unk_token, lstrip=False, rstrip=False) if isinstance(unk_token, str) else unk_token super().__init__( errors=errors, unk_token=unk_token, bos_token=bos_token, eos_token=eos_token, add_prefix_space=add_prefix_space, **kwargs, ) 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 ="\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 def vocab_size(self): return len(self.encoder) def get_vocab(self): return dict(self.encoder, **self.added_tokens_encoder) 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 _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 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)) def _convert_id_to_token(self, index): """Converts an index (integer) in a token (str) using the vocab.""" return self.decoder.get(index) 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
[docs] 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, ensure_ascii=False)) 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: text = " " + text return (text, kwargs) 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