tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<unk>",
      "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": "</s>",
      "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": 96,
      "content": "<|im_start|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 97,
      "content": "<|im_end|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 98,
      "content": "<|system|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 99,
      "content": "<|user|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 100,
      "content": "<|assistant|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 101,
      "content": "<|tool|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 102,
      "content": "<|assistant_reasoning|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 103,
      "content": "<|assistant_reasoning_end|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "Prepend",
        "prepend": "▁"
      },
      {
        "type": "Replace",
        "pattern": {
          "String": " "
        },
        "content": "▁"
      }
    ]
  },
  "pre_tokenizer": null,
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "<s>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "SpecialToken": {
          "id": "<s>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "<s>",
          "type_id": 1
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "<s>": {
        "id": "<s>",
        "ids": [
          1
        ],
        "tokens": [
          "<s>"
        ]
      }
    }
  },
  "decoder": {
    "type": "Sequence",
    "decoders": [
      {
        "type": "Replace",
        "pattern": {
          "String": "▁"
        },
        "content": " "
      },
      {
        "type": "ByteFallback"
      },
      {
        "type": "Fuse"
      },
      {
        "type": "Strip",
        "content": " ",
        "start": 1,
        "stop": 0
      }
    ]
  },
  "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": {
      "<unk>": 0,
      "<s>": 1,
      "</s>": 2,
      "<pad>": 3,
      "te": 4,
      "en": 5,
      "ar": 6,
      "▁=": 7,
      "▁[": 8,
      "▁": 9,
      "e": 10,
      "a": 11,
      "t": 12,
      "i": 13,
      "r": 14,
      "s": 15,
      "n": 16,
      "|": 17,
      "o": 18,
      ".": 19,
      "l": 20,
      "1": 21,
      "0": 22,
      "m": 23,
      "[": 24,
      "]": 25,
      "=": 26,
      "c": 27,
      "p": 28,
      "d": 29,
      "u": 30,
      "2": 31,
      "%": 32,
      "-": 33,
      "'": 34,
      "/": 35,
      "3": 36,
      "8": 37,
      "h": 38,
      "g": 39,
      "9": 40,
      "w": 41,
      ":": 42,
      "D": 43,
      "<": 44,
      ">": 45,
      "_": 46,
      "{": 47,
      "}": 48,
      "6": 49,
      "4": 50,
      "B": 51,
      "k": 52,
      "5": 53,
      ",": 54,
      "b": 55,
      "7": 56,
      "(": 57,
      ")": 58,
      "z": 59,
      "f": 60,
      "y": 61,
      "x": 62,
      "v": 63,
      "*": 64,
      "I": 65,
      "F": 66,
      "E": 67,
      "X": 68,
      "S": 69,
      "A": 70,
      "C": 71,
      "T": 72,
      "#": 73,
      "N": 74,
      "P": 75,
      "q": 76,
      "M": 77,
      "Z": 78,
      "H": 79,
      "Q": 80,
      "W": 81,
      "j": 82,
      "G": 83,
      "\"": 84,
      ";": 85,
      "L": 86,
      "U": 87,
      "R": 88,
      "K": 89,
      "J": 90,
      "V": 91,
      "?": 92,
      "O": 93,
      "&": 94,
      "+": 95
    },
    "merges": [
      [
        "t",
        "e"
      ],
      [
        "e",
        "n"
      ],
      [
        "a",
        "r"
      ],
      [
        "▁",
        "="
      ],
      [
        "▁",
        "["
      ]
    ]
  }
}