tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "<eos>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<bos>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 4,
      "content": "<mask>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Replace",
    "pattern": {
      "String": " "
    },
    "content": "▁"
  },
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "String": " "
    },
    "behavior": "MergedWithPrevious",
    "invert": false
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {}
  },
  "decoder": {
    "type": "Sequence",
    "decoders": [
      {
        "type": "Replace",
        "pattern": {
          "String": "▁"
        },
        "content": " "
      },
      {
        "type": "ByteFallback"
      },
      {
        "type": "Fuse"
      }
    ]
  },
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": "<unk>",
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": true,
    "byte_fallback": true,
    "ignore_merges": false,
    "vocab": {
      "<pad>": 0,
      "<eos>": 1,
      "<bos>": 2,
      "<unk>": 3,
      "<mask>": 4
    },
    "merges": []
  }
}