query_tokenizer/tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "[PAD]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100": {
      "content": "[UNK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "101": {
      "content": "[CLS]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "102": {
      "content": "[SEP]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "103": {
      "content": "[MASK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "30522": {
      "content": "<BOV>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "30523": {
      "content": "<SOV>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "30524": {
      "content": "<EOV>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "30525": {
      "content": "<BOQ>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "30526": {
      "content": "<EOQ>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "30527": {
      "content": "<BOC>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "30528": {
      "content": "<EOC>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "30529": {
      "content": "<BOK>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "30530": {
      "content": "<EOK>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<BOV>",
    "<SOV>",
    "<EOV>",
    "<BOQ>",
    "<EOQ>",
    "<BOC>",
    "<EOC>",
    "<BOK>",
    "<EOK>"
  ],
  "attend_to_mask_tokens": false,
  "auto_map": {
    "AutoTokenizer": [
      "tokenization_flmr.FLMRQueryEncoderTokenizer",
      null
    ]
  },
  "clean_up_tokenization_spaces": true,
  "cls_token": "[CLS]",
  "do_basic_tokenize": true,
  "do_lower_case": true,
  "mask_token": "[MASK]",
  "model_max_length": 1000000000000000019884624838656,
  "never_split": null,
  "pad_token": "[PAD]",
  "query_maxlen": 512,
  "sep_token": "[SEP]",
  "strip_accents": null,
  "tokenize_chinese_chars": true,
  "tokenizer_class": "FLMRQueryEncoderTokenizer",
  "unk_token": "[UNK]"
}