new-tokenizer-roberta-2 / tokenizer_config.json
SaulLu's picture
add tokenizer
2b9c5f3
raw
history blame
221 Bytes
{"model_max_length": 512, "bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "tokenizer_class": "PreTrainedTokenizerFast"}