File size: 2,332 Bytes
75716d5 | 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 | import os
import shutil
import sentencepiece as spm
from transformers import PreTrainedTokenizer
class SAITokenizer(PreTrainedTokenizer):
vocab_files_names = {"vocab_file": "tokenizer.model"}
model_input_names = ["input_ids", "attention_mask"]
def __init__(
self,
vocab_file,
unk_token="[UNK]",
bos_token="[BOS]",
eos_token="[EOS]",
pad_token="[UNK]",
additional_special_tokens=None,
**kwargs,
):
self.vocab_file = vocab_file
self.sp_model = spm.SentencePieceProcessor(model_file=vocab_file)
if additional_special_tokens is None:
additional_special_tokens = ["<|im_start|>", "<|im_end|>"]
super().__init__(
unk_token=unk_token,
bos_token=bos_token,
eos_token=eos_token,
pad_token=pad_token,
additional_special_tokens=additional_special_tokens,
**kwargs,
)
@property
def vocab_size(self):
return self.sp_model.get_piece_size()
def get_vocab(self):
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, **kwargs):
return self.sp_model.encode(text, out_type=str)
def _convert_token_to_id(self, token):
return self.sp_model.piece_to_id(token)
def _convert_id_to_token(self, index):
return self.sp_model.id_to_piece(int(index))
def convert_tokens_to_string(self, tokens):
return self.sp_model.decode(tokens)
def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
result = [self.bos_token_id] + list(token_ids_0)
if token_ids_1 is not None:
result += list(token_ids_1)
return result + [self.eos_token_id]
def save_vocabulary(self, save_directory, filename_prefix=None):
os.makedirs(save_directory, exist_ok=True)
filename = "tokenizer.model"
if filename_prefix:
filename = f"{filename_prefix}-{filename}"
destination = os.path.join(save_directory, filename)
if os.path.abspath(self.vocab_file) != os.path.abspath(destination):
shutil.copyfile(self.vocab_file, destination)
return (destination,)
|