genome-bert / tokenizer_config.json
nestorgonzalovich's picture
Training in progress, step 1000
ce028bc
raw
history blame
228 Bytes
{
"cls_token": "[CLS]",
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "[UNK]"
}