Spaces:
Sleeping
Sleeping
File size: 4,134 Bytes
2260825 |
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 |
# coding=utf-8
# Copyright 2021 The Facebook Inc. and The HuggingFace Inc. team. All rights reserved.
#
# 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 class for Blenderbot."""
from typing import TYPE_CHECKING, List
from ...utils import logging
from ..roberta.tokenization_roberta import RobertaTokenizer
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_config_file": "tokenizer_config.json",
}
PRETRAINED_VOCAB_FILES_MAP = {
"vocab_file": {"facebook/blenderbot-3B": "https://huggingface.co/facebook/blenderbot-3B/resolve/main/vocab.json"},
"merges_file": {"facebook/blenderbot-3B": "https://huggingface.co/facebook/blenderbot-3B/resolve/main/merges.txt"},
"tokenizer_config_file": {
"facebook/blenderbot-3B": "https://huggingface.co/facebook/blenderbot-3B/resolve/main/tokenizer_config.json"
},
}
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"facebook/blenderbot-3B": 128}
class BlenderbotTokenizer(RobertaTokenizer):
r"""
Construct a Blenderbot tokenizer.
:class:`~transformers.Blenderbot` is nearly identical to :class:`~transformers.RobertaTokenizer` and runs
end-to-end tokenization: punctuation splitting and wordpiece. The only difference is that it doesn't add BOS token
to the beginning of sequences.
Refer to superclass :class:`~transformers.RobertaTokenizer` for usage examples and documentation concerning
parameters.
"""
vocab_files_names = VOCAB_FILES_NAMES
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
def build_inputs_with_special_tokens(self, token_ids_0: List[int], token_ids_1: List[int] = None):
"""
Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
adding special tokens. A Blenderbot sequence has the following format:
- single sequence: `` X </s>``
Args:
token_ids_0 (:obj:`List[int]`):
List of IDs to which the special tokens will be added
token_ids_1 (:obj:`List[int]`, `optional`):
Will be ignored
Returns:
:obj:`List[int]`: list of `input IDs <../glossary.html#input-ids>`__ with the appropriate special tokens.
"""
return token_ids_0 + [self.eos_token_id]
def _build_conversation_input_ids(self, conversation: "Conversation") -> List[int]:
inputs = []
for is_user, text in conversation.iter_texts():
if is_user:
# We need to space prefix as it's being done within blenderbot
inputs.append(" " + text)
else:
# Generated responses should contain them already.
inputs.append(text)
full_string = " ".join(inputs)
input_ids = self.encode(full_string)
if len(input_ids) > self.model_max_length:
input_ids = input_ids[-self.model_max_length :]
logger.warning(f"Trimmed input from conversation as it was longer than {self.model_max_length} tokens.")
return input_ids
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
pairs = set(pairs)
return pairs
|