transcriptome-iseeek / tokenizer_config.json

commit from lixc

cc5b5fa over 2 years ago

No virus

158 Bytes

{"mask_token": "[MASK]", "cls_token": "[CLS]", "sep_token": "[SEP]", "pad_token": "[PAD]", "unk_token": "[UNK]", "tokenizer_class": "PreTrainedTokenizerFast"}