tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "6": {
      "content": "<s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "7": {
      "content": "</s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "8": {
      "content": "<d>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "9": {
      "content": "</d>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "backend": "custom",
  "bod_token": "<d>",
  "bos_token": "<s>",
  "eod_token": "</d>",
  "eos_token": "</s>",
  "is_local": false,
  "line_token": "</n>",
  "local_files_only": false,
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<pad>",
  "padding_side": "left",
  "space_token": "</_>",
  "tokenizer_class": "CpmAntTokenizer",
  "unk_token": "<unk>"
}