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
    },
    "2": {
      "content": "[CLS]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "[SEP]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "[MASK]",
      "lstrip": true,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64000": {
      "content": "<s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64001": {
      "content": "</s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64002": {
      "content": "<2as>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64003": {
      "content": "<2bn>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64004": {
      "content": "<2en>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64005": {
      "content": "<2gu>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64006": {
      "content": "<2hi>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64007": {
      "content": "<2kn>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64008": {
      "content": "<2ml>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64009": {
      "content": "<2mr>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64010": {
      "content": "<2or>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64011": {
      "content": "<2pa>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64012": {
      "content": "<2ta>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64013": {
      "content": "<2te>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<s>",
    "</s>",
    "<2as>",
    "<2bn>",
    "<2en>",
    "<2gu>",
    "<2hi>",
    "<2kn>",
    "<2ml>",
    "<2mr>",
    "<2or>",
    "<2pa>",
    "<2ta>",
    "<2te>"
  ],
  "bos_token": "[CLS]",
  "clean_up_tokenization_spaces": true,
  "cls_token": "[CLS]",
  "do_lower_case": false,
  "eos_token": "[SEP]",
  "keep_accents": true,
  "mask_token": "[MASK]",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<pad>",
  "remove_space": true,
  "sep_token": "[SEP]",
  "sp_model_kwargs": {},
  "tokenizer_class": "AlbertTokenizer",
  "unk_token": "<unk>",
  "use_fast": false
}