tokenization_HelpingAI_fast.py

# Made by KingNish

import json
from typing import List, Optional, Tuple

from tokenizers import pre_tokenizers, processors

from transformers.tokenization_utils_fast import PreTrainedTokenizerFast
from transformers.utils import logging


logger = logging.get_logger(__name__)

VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "merges_file": "merges.txt", "tokenizer_file": "tokenizer.json"}


class HelpingAITokenizerFast(PreTrainedTokenizerFast):
    vocab_files_names = VOCAB_FILES_NAMES
    model_input_names = ["input_ids", "attention_mask"]

    def __init__(
        self,
        vocab_file=None,
        merges_file=None,
        tokenizer_file=None,
        unk_token="<|endoftext|>",
        bos_token="<|im_start|>",
        eos_token="<|im_end|>",
        pad_token="<|im_end|>",
        add_bos_token=False,
        add_eos_token=False,
        add_prefix_space=False,
        **kwargs,
    ):
        super().__init__(
            vocab_file,
            merges_file,
            tokenizer_file=tokenizer_file,
            unk_token=unk_token,
            bos_token=bos_token,
            eos_token=eos_token,
            pad_token=pad_token,
            add_bos_token=add_bos_token,
            add_eos_token=add_eos_token,
            add_prefix_space=add_prefix_space,
            **kwargs,
        )

        self._add_bos_token = add_bos_token
        self._add_eos_token = add_eos_token
        self.update_post_processor()

        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 add_eos_token(self):
        return self._add_eos_token

    @property
    def add_bos_token(self):
        return self._add_bos_token

    @add_eos_token.setter
    def add_eos_token(self, value):
        self._add_eos_token = value
        self.update_post_processor()

    @add_bos_token.setter
    def add_bos_token(self, value):
        self._add_bos_token = value
        self.update_post_processor()

    def update_post_processor(self):
        bos = self.bos_token
        bos_token_id = self.bos_token_id
        if bos is None and self.add_bos_token:
            raise ValueError("add_bos_token = True but bos_token = None")

        eos = self.eos_token
        eos_token_id = self.eos_token_id
        if eos is None and self.add_eos_token:
            raise ValueError("add_eos_token = True but eos_token = None")

        single = f"{(bos+':0 ') if self.add_bos_token else ''}$A:0{(' '+eos+':0') if self.add_eos_token else ''}"
        pair = f"{single}{(' '+bos+':1') if self.add_bos_token else ''} $B:1{(' '+eos+':1') if self.add_eos_token else ''}"

        special_tokens = []
        if self.add_bos_token:
            special_tokens.append((bos, bos_token_id))
        if self.add_eos_token:
            special_tokens.append((eos, eos_token_id))
        self._tokenizer.post_processor = processors.TemplateProcessing(
            single=single, pair=pair, special_tokens=special_tokens
        )

    def get_special_tokens_mask(
        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
    ) -> List[int]:
        if already_has_special_tokens:
            return super().get_special_tokens_mask(
                token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
            )

        bos_token_id = [1] if self.add_bos_token else []
        eos_token_id = [1] if self.add_eos_token else []

        if token_ids_1 is None:
            return bos_token_id + ([0] * len(token_ids_0)) + eos_token_id
        return (
            bos_token_id
            + ([0] * len(token_ids_0))
            + eos_token_id
            + bos_token_id
            + ([0] * len(token_ids_1))
            + eos_token_id
        )

    def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
        bos_token_id = [self.bos_token_id] if self.add_bos_token else []
        eos_token_id = [self.eos_token_id] if self.add_eos_token else []

        output = bos_token_id + token_ids_0 + eos_token_id

        if token_ids_1 is not None:
            output = output + bos_token_id + token_ids_1 + eos_token_id

        return output

    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)

    @property
    def default_chat_template(self):
        return "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"