tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "</s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57521": {
      "content": "<mask>",
      "lstrip": true,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57522": {
      "content": "<sep/>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "57523": {
      "content": "<s_iitcdip>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57524": {
      "content": "<s_synthdog>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57525": {
      "content": "<s_quarterly_work_plan>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57526": {
      "content": "</s_quarterly_work_plan>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57527": {
      "content": "<s_unit>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57528": {
      "content": "</s_unit>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57529": {
      "content": "<s_quarters>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57530": {
      "content": "</s_quarters>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57531": {
      "content": "<s_Q4>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57532": {
      "content": "</s_Q4>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57533": {
      "content": "<s_Q3>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57534": {
      "content": "</s_Q3>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57535": {
      "content": "<s_Q2>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57536": {
      "content": "</s_Q2>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57537": {
      "content": "<s_Q1>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57538": {
      "content": "</s_Q1>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57539": {
      "content": "<s_item>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57540": {
      "content": "</s_item>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57541": {
      "content": "<s_name_of_the_project>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57542": {
      "content": "</s_name_of_the_project>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57543": {
      "content": "<s_cash_plan>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57544": {
      "content": "</s_cash_plan>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57545": {
      "content": "<s_approved_capital_cost>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "57546": {
      "content": "</s_approved_capital_cost>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<s_quarterly_work_plan>",
    "</s_quarterly_work_plan>",
    "<s_unit>",
    "</s_unit>",
    "<s_quarters>",
    "</s_quarters>",
    "<s_Q4>",
    "</s_Q4>",
    "<s_Q3>",
    "</s_Q3>",
    "<s_Q2>",
    "</s_Q2>",
    "<s_Q1>",
    "</s_Q1>",
    "<s_item>",
    "</s_item>",
    "<s_name_of_the_project>",
    "</s_name_of_the_project>",
    "<s_cash_plan>",
    "</s_cash_plan>",
    "<s_approved_capital_cost>",
    "</s_approved_capital_cost>",
    "<s>",
    "</s>"
  ],
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": false,
  "cls_token": "<s>",
  "eos_token": "</s>",
  "extra_special_tokens": {},
  "mask_token": "<mask>",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<pad>",
  "processor_class": "DonutProcessor",
  "sep_token": "</s>",
  "sp_model_kwargs": {},
  "tokenizer_class": "XLMRobertaTokenizer",
  "unk_token": "<unk>"
}