tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<|endoftext|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "<|quantum|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<|classical|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "NFC"
      },
      {
        "type": "Prepend",
        "prepend": "▁"
      }
    ]
  },
  "pre_tokenizer": {
    "type": "Sequence",
    "pretokenizers": [
      {
        "type": "Split",
        "pattern": {
          "Regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
        },
        "behavior": "Isolated",
        "invert": false
      }
    ]
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "<|endoftext|>",
          "ids": [0]
        }
      }
    ],
    "pair": [
      {
        "SpecialToken": {
          "id": "<|endoftext|>",
          "ids": [0]
        }
      }
    ],
    "special_tokens": {
      "<|endoftext|>": {
        "id": 0,
        "ids": [0]
      },
      "<|quantum|>": {
        "id": 1,
        "ids": [1]
      },
      "<|classical|>": {
        "id": 2,
        "ids": [2]
      }
    }
  },
  "decoder": {
    "type": "Sequence",
    "decoders": [
      {
        "type": "Replace",
        "pattern": {
          "String": "▁"
        },
        "content": " "
      }
    ]
  },
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": null,
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "vocab": {},
    "merges": []
  }
}