Spaces:
Runtime error
Runtime error
File size: 7,793 Bytes
c5ca37a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 |
# 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
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Tokenization classes for OpenAI GPT."""
from __future__ import (absolute_import, division, print_function,
unicode_literals)
import json
import logging
import os
import re
from io import open
from .tokenization_utils import PreTrainedTokenizer
from .tokenization_bert import BasicTokenizer
logger = logging.getLogger(__name__)
VOCAB_FILES_NAMES = {
'vocab_file': 'vocab.json',
'merges_file': 'merges.txt',
}
PRETRAINED_VOCAB_FILES_MAP = {
'vocab_file':
{
'openai-gpt': "https://s3.amazonaws.com/models.huggingface.co/bert/openai-gpt-vocab.json",
},
'merges_file':
{
'openai-gpt': "https://s3.amazonaws.com/models.huggingface.co/bert/openai-gpt-merges.txt",
},
}
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
'openai-gpt': 512,
}
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
def text_standardize(text):
"""
fixes some issues the spacy tokenizer had on books corpus
also does some whitespace standardization
"""
text = text.replace('—', '-')
text = text.replace('–', '-')
text = text.replace('―', '-')
text = text.replace('…', '...')
text = text.replace('´', "'")
text = re.sub(r'''(-+|~+|!+|"+|;+|\?+|\++|,+|\)+|\(+|\\+|\/+|\*+|\[+|\]+|}+|{+|\|+|_+)''', r' \1 ', text)
text = re.sub(r'\s*\n\s*', ' \n ', text)
text = re.sub(r'[^\S\n]+', ' ', text)
return text.strip()
class OpenAIGPTTokenizer(PreTrainedTokenizer):
"""
BPE tokenizer. Peculiarities:
- lower case all inputs
- uses SpaCy tokenizer and ftfy for pre-BPE tokenization if they are installed, fallback to BERT's BasicTokenizer if not.
"""
vocab_files_names = VOCAB_FILES_NAMES
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
def __init__(self, vocab_file, merges_file, unk_token="<unk>", **kwargs):
super(OpenAIGPTTokenizer, self).__init__(unk_token=unk_token, **kwargs)
self.max_len_single_sentence = self.max_len # no default special tokens - you can update this value if you add special tokens
self.max_len_sentences_pair = self.max_len # no default special tokens - you can update this value if you add special tokens
try:
import ftfy
from spacy.lang.en import English
_nlp = English()
self.nlp = _nlp.Defaults.create_tokenizer(_nlp)
self.fix_text = ftfy.fix_text
except ImportError:
logger.warning("ftfy or spacy is not installed using BERT BasicTokenizer instead of SpaCy & ftfy.")
self.nlp = BasicTokenizer(do_lower_case=True)
self.fix_text = None
self.encoder = json.load(open(vocab_file, encoding="utf-8"))
self.decoder = {v:k for k,v in self.encoder.items()}
merges = open(merges_file, encoding='utf-8').read().split('\n')[1:-1]
merges = [tuple(merge.split()) for merge in merges]
self.bpe_ranks = dict(zip(merges, range(len(merges))))
self.cache = {}
@property
def vocab_size(self):
return len(self.encoder)
def bpe(self, token):
word = tuple(token[:-1]) + (token[-1] + '</w>',)
if token in self.cache:
return self.cache[token]
pairs = get_pairs(word)
if not pairs:
return token+'</w>'
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)
new_word.extend(word[i:j])
i = j
except:
new_word.extend(word[i:])
break
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)
if word == '\n </w>':
word = '\n</w>'
self.cache[token] = word
return word
def _tokenize(self, text):
""" Tokenize a string. """
split_tokens = []
if self.fix_text is None:
# Using BERT's BasicTokenizer
text = self.nlp.tokenize(text)
for token in text:
split_tokens.extend([t for t in self.bpe(token).split(' ')])
else:
# Using SpaCy & ftfy (original tokenization process of OpenAI GPT)
text = self.nlp(text_standardize(self.fix_text(text)))
for token in text:
split_tokens.extend([t for t in self.bpe(token.text.lower()).split(' ')])
return split_tokens
def _convert_token_to_id(self, token):
""" Converts a token (str/unicode) 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 id in a token (BPE) using the vocab."""
return self.decoder.get(index, self.unk_token)
def convert_tokens_to_string(self, tokens):
""" Converts a sequence of tokens (string) in a single string. """
out_string = ''.join(tokens).replace('</w>', ' ').strip()
return out_string
def save_vocabulary(self, save_directory):
"""Save the tokenizer vocabulary and merge files to a directory."""
if not os.path.isdir(save_directory):
logger.error("Vocabulary path ({}) should be a directory".format(save_directory))
return
vocab_file = os.path.join(save_directory, VOCAB_FILES_NAMES['vocab_file'])
merge_file = os.path.join(save_directory, 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(u'#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("Saving vocabulary to {}: BPE merge indices are not consecutive."
" Please check that the tokenizer is not corrupted!".format(merge_file))
index = token_index
writer.write(' '.join(bpe_tokens) + u'\n')
index += 1
return vocab_file, merge_file
|