File size: 2,467 Bytes
36e7c6e | 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 | import json
import os
from transformers import PreTrainedTokenizer
class ChessTokenizer(PreTrainedTokenizer):
model_input_names = ["input_ids", "attention_mask"]
vocab_files_names = {"vocab_file": "vocab.json"}
PAD_TOKEN = "[PAD]"
BOS_TOKEN = "[BOS]"
EOS_TOKEN = "[EOS]"
UNK_TOKEN = "[UNK]"
def __init__(self, vocab_file=None, vocab=None, **kwargs):
self._pad_token = self.PAD_TOKEN
self._bos_token = self.BOS_TOKEN
self._eos_token = self.EOS_TOKEN
self._unk_token = self.UNK_TOKEN
kwargs.pop("pad_token", None)
kwargs.pop("bos_token", None)
kwargs.pop("eos_token", None)
kwargs.pop("unk_token", None)
if vocab is not None:
self._vocab = vocab
elif vocab_file is not None and os.path.exists(vocab_file):
with open(vocab_file, "r", encoding="utf-8") as f:
self._vocab = json.load(f)
else:
self._vocab = self._create_default_vocab()
self._ids_to_tokens = {v: k for k, v in self._vocab.items()}
super().__init__(pad_token=self._pad_token, bos_token=self._bos_token, eos_token=self._eos_token, unk_token=self._unk_token, **kwargs)
def _create_default_vocab(self):
special_tokens = [self.PAD_TOKEN, self.BOS_TOKEN, self.EOS_TOKEN, self.UNK_TOKEN]
return {token: idx for idx, token in enumerate(special_tokens)}
@property
def vocab_size(self):
return len(self._vocab)
def get_vocab(self):
return dict(self._vocab)
def _tokenize(self, text):
return text.strip().split()
def _convert_token_to_id(self, token):
return self._vocab.get(token, self._vocab.get(self.UNK_TOKEN, 0))
def _convert_id_to_token(self, index):
return self._ids_to_tokens.get(index, self.UNK_TOKEN)
def convert_tokens_to_string(self, tokens):
special = {self.PAD_TOKEN, self.BOS_TOKEN, self.EOS_TOKEN, self.UNK_TOKEN}
return " ".join(t for t in tokens if t not in special)
def save_vocabulary(self, save_directory, filename_prefix=None):
if not os.path.isdir(save_directory):
os.makedirs(save_directory, exist_ok=True)
vocab_file = os.path.join(save_directory, (filename_prefix + "-" if filename_prefix else "") + "vocab.json")
with open(vocab_file, "w", encoding="utf-8") as f:
json.dump(self._vocab, f, ensure_ascii=False, indent=2)
return (vocab_file,)
|