@lenml/tokenizer-gemini
Version:
gemini tokenizer for NodeJS/Browser
2,352 lines (2,351 loc) • 17.5 MB
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": false
},
{
"id": 5,
"content": "<2mass>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 6,
"content": "[@BOS@]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 7,
"content": "<unused0>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 8,
"content": "<unused1>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 9,
"content": "<unused2>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 10,
"content": "<unused3>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 11,
"content": "<unused4>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 12,
"content": "<unused5>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 13,
"content": "<unused6>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 14,
"content": "<unused7>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 15,
"content": "<unused8>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 16,
"content": "<unused9>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 17,
"content": "<unused10>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 18,
"content": "<unused11>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 19,
"content": "<unused12>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 20,
"content": "<unused13>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 21,
"content": "<unused14>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 22,
"content": "<unused15>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 23,
"content": "<unused16>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 24,
"content": "<unused17>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 25,
"content": "<unused18>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 26,
"content": "<unused19>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 27,
"content": "<unused20>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 28,
"content": "<unused21>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 29,
"content": "<unused22>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 30,
"content": "<unused23>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 31,
"content": "<unused24>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 32,
"content": "<unused25>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 33,
"content": "<unused26>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 34,
"content": "<unused27>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 35,
"content": "<unused28>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 36,
"content": "<unused29>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 37,
"content": "<unused30>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 38,
"content": "<unused31>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 39,
"content": "<unused32>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 40,
"content": "<unused33>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 41,
"content": "<unused34>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 42,
"content": "<unused35>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 43,
"content": "<unused36>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 44,
"content": "<unused37>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 45,
"content": "<unused38>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 46,
"content": "<unused39>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 47,
"content": "<unused40>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 48,
"content": "<unused41>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 49,
"content": "<unused42>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 50,
"content": "<unused43>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 51,
"content": "<unused44>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 52,
"content": "<unused45>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 53,
"content": "<unused46>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 54,
"content": "<unused47>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 55,
"content": "<unused48>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 56,
"content": "<unused49>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 57,
"content": "<unused50>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 58,
"content": "<unused51>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 59,
"content": "<unused52>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 60,
"content": "<unused53>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 61,
"content": "<unused54>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 62,
"content": "<unused55>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 63,
"content": "<unused56>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 64,
"content": "<unused57>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 65,
"content": "<unused58>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 66,
"content": "<unused59>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 67,
"content": "<unused60>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 68,
"content": "<unused61>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 69,
"content": "<unused62>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 70,
"content": "<unused63>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 71,
"content": "<unused64>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 72,
"content": "<unused65>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 73,
"content": "<unused66>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 74,
"content": "<unused67>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 75,
"content": "<unused68>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 76,
"content": "<unused69>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 77,
"content": "<unused70>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 78,
"content": "<unused71>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 79,
"content": "<unused72>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 80,
"content": "<unused73>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 81,
"content": "<unused74>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 82,
"content": "<unused75>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 83,
"content": "<unused76>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 84,
"content": "<unused77>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 85,
"content": "<unused78>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 86,
"content": "<unused79>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 87,
"content": "<unused80>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 88,
"content": "<unused81>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 89,
"content": "<unused82>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 90,
"content": "<unused83>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 91,
"content": "<unused84>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 92,
"content": "<unused85>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 93,
"content": "<unused86>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 94,
"content": "<unused87>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 95,
"content": "<unused88>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 96,
"content": "<unused89>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 97,
"content": "<unused90>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 98,
"content": "<unused91>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 99,
"content": "<unused92>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 100,
"content": "<unused93>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 101,
"content": "<unused94>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 102,
"content": "<unused95>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 103,
"content": "<unused96>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 104,
"content": "<unused97>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 105,
"content": "<unused98>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 106,
"content": "<start_of_turn>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 107,
"content": "<end_of_turn>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 108,
"content": "\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 109,
"content": "\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 110,
"content": "\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 111,
"content": "\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 112,
"content": "\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 113,
"content": "\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 114,
"content": "\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 115,
"content": "\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 116,
"content": "\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 117,
"content": "\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 118,
"content": "\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 119,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 120,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 121,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 122,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 123,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 124,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 125,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 126,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 127,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 128,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 129,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 130,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 131,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 132,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 133,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 134,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 135,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 136,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 137,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 138,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 139,
"content": "▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 140,
"content": "▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 141,
"content": "▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 142,
"content": "▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 143,
"content": "▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 144,
"content": "▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 145,
"content": "▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 146,
"content": "▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 147,
"content": "▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 148,
"content": "▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 149,
"content": "▁▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 150,
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 151,
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 152,
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 153,
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 154,
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 155,
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 156,
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 157,
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 158,
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 159,
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 160,
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 161,
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 162,
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 163,
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 164,
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 165,
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 166,
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 167,
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 168,
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 169,
"content": "<table>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 170,
"content": "<caption>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 171,
"content": "<thead>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 172,
"content": "<tbody>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 173,
"content": "<tfoot>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 174,
"content": "<tr>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 175,
"content": "<th>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 176,
"content": "<td>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 177,
"content": "</table>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 178,
"content": "</caption>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 179,
"content": "</thead>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 180,
"content": "</tbody>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 181,
"content": "</tfoot>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 182,
"content": "</tr>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 183,
"content": "</th>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 184,
"content": "</td>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 185,
"content": "<h1>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 186,
"content": "<h2>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 187,
"content": "<h3>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 188,
"content": "<h4>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 189,
"content": "<h5>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 190,
"content": "<h6>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 191,
"content": "<blockquote>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 192,
"content": "</h1>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 193,
"content": "</h2>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 194,
"content": "</h3>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 195,
"content": "</h4>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 196,
"content": "</h5>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 197,
"content": "</h6>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 198,
"content": "</blockquote>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 199,
"content": "<strong>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 200,
"content": "<em>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 201,
"content": "<b>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 202,
"content": "<i>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 203,
"content": "<u>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 204,
"content": "<s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 205,
"content": "<sub>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 206,
"content": "<sup>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 207,
"content": "<code>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 208,
"content": "</strong>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 209,
"content": "</em>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 210,
"content": "</b>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 211,
"content": "</i>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 212,
"content": "</u>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 213,
"content": "</s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 214,
"content": "</sub>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 215,
"content": "</sup>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
{
"id": 216,
"content": "</code>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
}
],
"normalizer": {
"type": "Replace",
"pattern": {
"String": " "
},
"content": "▁"
},
"pre_tokenizer": null,
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": "<bos>",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
}
],
"pair": [
{
"SpecialToken": {
"id": "<bos>",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "<bos>",
"type_id": 1
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {
"<bos>": {
"id": "<bos>",
"ids": [
2
],
"tokens": [
"<bos>"
]
}
}
},
"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,
"<2mass>": 5,
"[@BOS@]": 6,
"<unused0>": 7,
"<unused1>": 8,
"<unused2>": 9,
"<unused3>": 10,
"<unused4>": 11,
"<unused5>": 12,
"<unused6>": 13,
"<unused7>": 14,
"<unused8>": 15,
"<unused9>": 16,
"<unused10>": 17,
"<unused11>": 18,
"<unused12>": 19,
"<unused13>": 20,
"<unused14>": 21,
"<unused15>": 22,
"<unused16>": 23,
"<unused17>": 24,
"<unused18>": 25,
"<unused19>": 26,
"<unused20>": 27,
"<unused21>": 28,
"<unused22>": 29,
"<unused23>": 30,
"<unused24>": 31,
"<unused25>": 32,
"<unused26>": 33,
"<unused27>": 34,
"<unused28>": 35,
"<unused29>": 36,
"<unused30>": 37,
"<unused31>": 38,
"<unused32>": 39,
"<unused33>": 40,
"<unused34>": 41,
"<unused35>": 42,
"<unused36>": 43,
"<unused37>": 44,
"<unused38>": 45,
"<unused39>": 46,
"<unused40>": 47,
"<unused41>": 48,
"<unused42>": 49,
"<unused43>": 50,
"<unused44>": 51,
"<unused45>": 52,
"<unused46>": 53,
"<unused47>": 54,
"<unused48>": 55,
"<unused49>": 56,
"<unused50>": 57,
"<unused51>": 58,
"<unused52>": 59,
"<unused53>": 60,
"<unused54>": 61,
"<unused55>": 62,
"<unused56>": 63,
"<unused57>": 64,
"<unused58>": 65,
"<unused59>": 66,
"<unused60>": 67,
"<unused61>": 68,
"<unused62>": 69,
"<unused63>": 70,
"<unused64>": 71,
"<unused65>": 72,
"<unused66>": 73,
"<unused67>": 74,
"<unused68>": 75,
"<unused69>": 76,
"<unused70>": 77,
"<unused71>": 78,
"<unused72>": 79,
"<unused73>": 80,
"<unused74>": 81,
"<unused75>": 82,
"<unused76>": 83,
"<unused77>": 84,
"<unused78>": 85,
"<unused79>": 86,
"<unused80>": 87,
"<unused81>": 88,
"<unused82>": 89,
"<unused83>": 90,
"<unused84>": 91,
"<unused85>": 92,
"<unused86>": 93,
"<unused87>": 94,
"<unused88>": 95,
"<unused89>": 96,
"<unused90>": 97,
"<unused91>": 98,
"<unused92>": 99,
"<unused93>": 100,
"<unused94>": 101,
"<unused95>": 102,
"<unused96>": 103,
"<unused97>": 104,
"<unused98>": 105,
"<start_of_turn>": 106,
"<end_of_turn>": 107,
"\n": 108,
"\n\n": 109,
"\n\n\n": 110,
"\n\n\n\n": 111,
"\n\n\n\n\n": 112,
"\n\n\n\n\n\n": 113,
"\n\n\n\n\n\n\n": 114,
"\n\n\n\n\n\n\n\n": 115,
"\n\n\n\n\n\n\n\n\n": 116,
"\n\n\n\n\n\n\n\n\n\n": 117,
"\n\n\n\n\n\n\n\n\n\n\n": 118,
"\n\n\n\n\n\n\n\n\n\n\n\n": 119,
"\n\n\n\n\n\n\n\n\n\n\n\n\n": 120,
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n": 121,
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n": 122,
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n": 123,
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n": 124,
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n": 125,
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n": 126,
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n": 127,
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n": 128,
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n": 129,
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n": 130,
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n": 131,
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n": 132,
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n": 133,
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n": 134,
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n": 135,
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n": 136,
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n": 137,
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n": 138,
"▁▁": 139,
"▁▁▁": 140,
"▁▁▁▁": 141,
"▁▁▁▁▁": 142,
"▁▁▁▁▁▁": 143,
"▁▁▁▁▁▁▁": 144,
"▁▁▁▁▁▁▁▁": 145,
"▁▁▁▁▁▁▁▁▁": 146,
"▁▁▁▁▁▁▁▁▁▁": 147,
"▁▁▁▁▁▁▁▁▁▁▁": 148,
"▁▁▁▁▁▁▁▁▁▁▁▁": 149,
"▁▁▁▁▁▁▁▁▁▁▁▁▁": 150,
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 151,
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 152,
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 153,
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 154,
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 155,
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 156,
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 157,
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 158,
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 159,
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 160,
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 161,
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 162,
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 163,
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 164,
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 165,
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 166,
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 167,
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁": 168,
"<table>": 169,
"<caption>": 170,
"<thead>": 171,
"<tbody>": 172,
"<tfoot>": 173,
"<tr>": 174,
"<th>": 175,
"<td>": 176,
"</table>": 177,
"</caption>": 178,
"</thead>": 179,
"</tbody>": 180,
"</tfoot>": 181,
"</tr>": 182,
"</th>": 183,
"</td>": 184,
"<h1>": 185,
"<h2>": 186,
"<h3>": 187,
"<h4>": 188,
"<h5>": 189,
"<h6>": 190,
"<blockquote>": 191,
"</h1>": 192,
"</h2>": 193,
"</h3>": 194,
"</h4>": 195,
"</h5>": 196,
"</h6>": 197,
"</blockquote>": 198,
"<strong>": 199,
"<em>": 200,
"<b>": 201,
"<i>": 202,
"<u>": 203,
"<s>": 204,
"<sub>": 205,
"<sup>": 206,
"<code>": 207,
"</strong>": 208,
"</em>": 209,
"</b>": 210,
"</i>": 211,
"</u>": 212,
"</s>": 213,
"</sub>": 214,
"</sup>": 215,
"</code>": 216,
"<0x00>": 217,
"<0x01>": 218,
"<0x02>": 219,
"<0x03>": 220,
"<0x04>": 221,
"<0x05>": 222,
"<0x06>": 223,
"<0x07>": 224,
"<0x08>": 225,
"\t": 226,
"<0x0A>": 227,
"<0x0B>": 228,
"<0x0C>": 229,
"<0x0D>": 230,
"<0x0E>": 231,
"<0x0F>": 232,
"<0x10>": 233,
"<0x11>": 234,
"<0x12>": 235,
"<0x13>": 236,
"<0x14>": 237,
"<0x15>": 238,
"<0x16>": 239,
"<0x17>": 240,
"<0x18>": 241,
"<0x19>": 242,
"<0x1A>": 243,
"<0x1B>": 244,
"<0x1C>": 245,
"<0x1D>": 246,
"<0x1E>": 247,
"<0x1F>": 248,
"<0x20>": 249,
"<0x21>": 250,
"<0x22>": 251,
"<0x23>": 252,
"<0x24>": 253,
"<0x25>": 254,
"<0x26>": 255,
"<0x27>": 256,
"<0x28>": 257,
"<0x29>": 258,
"<0x2A>": 259,
"<0x2B>": 260,
"<0x2C>": 261,
"<0x2D>": 262,
"<0x2E>": 263,
"<0x2F>": 264,
"<0x30>": 265,
"<0x31>": 266,
"<0x32>": 267,
"<0x33>": 268,
"<0x34>": 269,
"<0x35>": 270,
"<0x36>": 271,
"<0x37>": 272,
"<0x38>": 273,
"<0x39>": 274,
"<0x3A>": 275,
"<0x3B>": 276,
"<0x3C>": 277,
"<0x3D>": 278,
"<0x3E>": 279,
"<0x3F>": 280,
"<0x40>": 281,
"<0x41>": 282,
"<0x42>": 283,
"<0x43>": 284,
"<0x44>": 285,
"<0x45>": 286,
"<0x46>": 287,
"<0x47>": 288,
"<0x48>": 289,
"<0x49>": 290,
"<0x4A>": 291,
"<0x4B>": 292,
"<0x4C>": 293,
"<0x4D>": 294,
"<0x4E>": 295,
"<0x4F>": 296,
"<0x50>": 297,
"<0x51>": 298,
"<0x52>": 299,
"<0x53>": 300,
"<0x54>": 301,