poem-char-tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": {
    "strategy": "BatchLongest",
    "direction": "Right",
    "pad_to_multiple_of": null,
    "pad_id": 0,
    "pad_type_id": 0,
    "pad_token": "[PAD]"
  },
  "added_tokens": [
    {
      "id": 0,
      "content": "[PAD]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "[SOS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "[EOS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": null,
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": null,
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "vocab": {
      "[PAD]": 0,
      "[SOS]": 1,
      "[EOS]": 2,
      " ": 3,
      "!": 4,
      ":": 5,
      "«": 6,
      "»": 7,
      "،": 8,
      "؟": 9,
      "آ": 10,
      "أ": 11,
      "ؤ": 12,
      "ئ": 13,
      "ا": 14,
      "ب": 15,
      "ت": 16,
      "ث": 17,
      "ج": 18,
      "ح": 19,
      "خ": 20,
      "د": 21,
      "ذ": 22,
      "ر": 23,
      "ز": 24,
      "س": 25,
      "ش": 26,
      "ص": 27,
      "ض": 28,
      "ط": 29,
      "ظ": 30,
      "ع": 31,
      "غ": 32,
      "ـ": 33,
      "ف": 34,
      "ق": 35,
      "ل": 36,
      "م": 37,
      "ن": 38,
      "ه": 39,
      "و": 40,
      "َ": 41,
      "ُ": 42,
      "ِ": 43,
      "ّ": 44,
      "ٔ": 45,
      "پ": 46,
      "چ": 47,
      "ژ": 48,
      "ک": 49,
      "گ": 50,
      "ی": 51,
      "‌": 52
    },
    "merges": []
  }
}