herbert-large-cased / tokenizer_config.json
system's picture
system HF staff
Update tokenizer_config.json
308a31b
raw
history blame
229 Bytes
{"do_lowercase_and_remove_accent": false, "unk_token": "<unk>", "bos_token": "<s>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "additional_special_tokens": [], "model_max_length": 512}