poem-bpe-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": "[SEP]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "[SOS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "[EOS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 4,
      "content": "[UNK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "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,
      "[SEP]": 1,
      "[SOS]": 2,
      "[EOS]": 3,
      "[UNK]": 4,
      "!": 5,
      ":": 6,
      "«": 7,
      "»": 8,
      "،": 9,
      "؟": 10,
      "آ": 11,
      "أ": 12,
      "ؤ": 13,
      "ئ": 14,
      "ا": 15,
      "ب": 16,
      "ت": 17,
      "ث": 18,
      "ج": 19,
      "ح": 20,
      "خ": 21,
      "د": 22,
      "ذ": 23,
      "ر": 24,
      "ز": 25,
      "س": 26,
      "ش": 27,
      "ص": 28,
      "ض": 29,
      "ط": 30,
      "ظ": 31,
      "ع": 32,
      "غ": 33,
      "ـ": 34,
      "ف": 35,
      "ق": 36,
      "ل": 37,
      "م": 38,
      "ن": 39,
      "ه": 40,
      "و": 41,
      "َ": 42,
      "ُ": 43,
      "ِ": 44,
      "ّ": 45,
      "ْ": 46,
      "ٔ": 47,
      "پ": 48,
      "چ": 49,
      "ژ": 50,
      "ک": 51,
      "گ": 52,
      "ی": 53,
      "‌": 54
    },
    "merges": []
  }
}