armanc's picture
add tokenizer
6d4bdba
raw
history blame
430 Bytes
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}, "additional_special_tokens": ["<reserved-0>", "<reserved-1>", "<reserved-2>", "<reserved-3>", "<reserved-4>", "<reserved-5>", "<reserved-6>", "<reserved-7>", "<reserved-8>", "<reserved-9>"]}