bbert_checkpoint-32500/tokenizer.json

{
  "version": "1.0",
  "truncation": {
    "direction": "Right",
    "max_length": 102,
    "strategy": "LongestFirst",
    "stride": 0
  },
  "padding": {
    "strategy": {
      "Fixed": 102
    },
    "direction": "Right",
    "pad_to_multiple_of": null,
    "pad_id": 3,
    "pad_type_id": 0,
    "pad_token": "<pad>"
  },
  "added_tokens": [
    {
      "id": 0,
      "content": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "</s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 4,
      "content": "<cls>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 5,
      "content": "<sep>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 6,
      "content": "<msk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 7,
      "content": "T",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 8,
      "content": "C",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 9,
      "content": "A",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 10,
      "content": "G",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 11,
      "content": "N",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "<cls>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "<sep>",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "SpecialToken": {
          "id": "<cls>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "<sep>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      },
      {
        "SpecialToken": {
          "id": "<sep>",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "<cls>": {
        "id": "<cls>",
        "ids": [
          4
        ],
        "tokens": [
          "<cls>"
        ]
      },
      "<sep>": {
        "id": "<sep>",
        "ids": [
          5
        ],
        "tokens": [
          "<sep>"
        ]
      }
    }
  },
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {},
    "unk_token": "<unk>"
  }
}