tokenizer_config.json

{
  "add_prefix_space": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "</s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "50264": {
      "content": "<mask>",
      "lstrip": true,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": true,
  "cls_token": "<s>",
  "eos_token": "</s>",
  "errors": "replace",
  "id2label": {
    "0": "C1",
    "1": "C13",
    "2": "C17",
    "3": "C22",
    "4": "C28",
    "5": "C33",
    "6": "C38",
    "7": "C46",
    "8": "C52",
    "9": "C7"
  },
  "label2id": {
    "C1": 0,
    "C13": 1,
    "C17": 2,
    "C22": 3,
    "C28": 4,
    "C33": 5,
    "C38": 6,
    "C46": 7,
    "C52": 8,
    "C7": 9
  },
  "mask_token": "<mask>",
  "max_length": 512,
  "model_max_length": 512,
  "num_labels": 10,
  "pad_to_multiple_of": null,
  "pad_token": "<pad>",
  "pad_token_type_id": 0,
  "padding_side": "right",
  "sep_token": "</s>",
  "stride": 0,
  "tokenizer_class": "RobertaTokenizer",
  "trim_offsets": true,
  "truncation_side": "right",
  "truncation_strategy": "longest_first",
  "unk_token": "<unk>"
}