cognitivess_model/tokenization_cognitivess.py

from transformers import PreTrainedTokenizer

class CognitivessTokenizer(PreTrainedTokenizer):
    def __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)

    @property
    def vocab_size(self):
        return len(self.encoder)

    def get_vocab(self):
        return dict(self.encoder)

    def _tokenize(self, text):
        return text.split()

    def _convert_token_to_id(self, token):
        return self.encoder.get(token, self.encoder.get(self.unk_token))

    def _convert_id_to_token(self, index):
        return self.decoder.get(index, self.unk_token)

    def convert_tokens_to_string(self, tokens):
        return " ".join(tokens)

    def save_vocabulary(self, save_directory):
        vocab_file = os.path.join(save_directory, "vocab.json")
        with open(vocab_file, "w", encoding="utf-8") as f:
            json.dump(self.encoder, f, ensure_ascii=False)
        return (vocab_file,)

    def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
        bos_token_id = [self.bos_token_id]
        eos_token_id = [self.eos_token_id]
        return bos_token_id + token_ids_0 + eos_token_id