tokenizer_config.json

{
  "bos_token": "<s>",
  "clean_text": true,
  "clean_up_tokenization_spaces": true,
  "cls_token": "<cls>",
  "do_basic_tokenize": true,
  "do_lower_case": true,
  "eos_token": "</s>",
  "mask_token": "<mask>",
  "model_max_length": 512,
  "never_split": null,
  "pad_token": "<pad>",
  "sep_token": "<sep>",
  "strip_accents": false,
  "tokenize_chinese_chars": true,
  "tokenizer_class": "FunnelTokenizer",
  "unk_token": "<unk>",
  "wordpieces_prefix": "##"
}