from __future__ import annotations import os import shutil from typing import Dict, List, Optional, Tuple import sentencepiece as spm from transformers import PreTrainedTokenizer VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model"} class ThoxMicroprocessorTokenizer(PreTrainedTokenizer): vocab_files_names = VOCAB_FILES_NAMES model_input_names = ["input_ids", "attention_mask"] def __init__( self, vocab_file: str, unk_token: str = "", bos_token: str = "", eos_token: str = "", pad_token: str = "", **kwargs, ) -> None: self.vocab_file = vocab_file self.sp_model = spm.SentencePieceProcessor(model_file=vocab_file) super().__init__( unk_token=unk_token, bos_token=bos_token, eos_token=eos_token, pad_token=pad_token, **kwargs, ) @property def vocab_size(self) -> int: return int(self.sp_model.vocab_size()) def get_vocab(self) -> Dict[str, int]: vocab = {self.sp_model.id_to_piece(i): i for i in range(self.vocab_size)} vocab.update(self.added_tokens_encoder) return vocab def _tokenize(self, text: str) -> List[str]: return list(self.sp_model.encode(text, out_type=str)) def _convert_token_to_id(self, token: str) -> int: return int(self.sp_model.piece_to_id(token)) def _convert_id_to_token(self, index: int) -> str: return str(self.sp_model.id_to_piece(int(index))) def convert_tokens_to_string(self, tokens: List[str]) -> str: return self.sp_model.decode(tokens) def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]: if not os.path.isdir(save_directory): os.makedirs(save_directory, exist_ok=True) name = (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"] out = os.path.join(save_directory, name) if os.path.abspath(self.vocab_file) != os.path.abspath(out): shutil.copyfile(self.vocab_file, out) return (out,)