File size: 2,151 Bytes
7496ed2 | 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 | 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 = "<unk>",
bos_token: str = "<s>",
eos_token: str = "</s>",
pad_token: str = "<pad>",
**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,)
|