Upload tokenizer.json with huggingface_hub
Browse files- tokenizer.json +118 -0
tokenizer.json
ADDED
|
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 60,
|
| 8 |
+
"content": "<unk>",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
}
|
| 15 |
+
],
|
| 16 |
+
"normalizer": {
|
| 17 |
+
"type": "Sequence",
|
| 18 |
+
"normalizers": [
|
| 19 |
+
{
|
| 20 |
+
"type": "Lowercase"
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"type": "Replace",
|
| 24 |
+
"pattern": {
|
| 25 |
+
"Regex": "[^|\u0abe\u0ac7\u0aa4\u0aa8\u0ab0\u0acd\u0aae\u0ac0\u0a95\u0a82\u0acb\u0aaa\u0ab5\u0ac1\u0ab8\u0aaf\u0ab9\u0a9c\u0aa5\u0abf\u0ab6\u0aa3\u0a9b\u0ab2\u0aa6\u0a86\u0a93\u0a85\u0a8f\u0a88\u0aac\u0a97\u0a96\u0aa7\u0aad\u0a9f\u0ab3\u0ac2\u0a9a\u0aa1\u0ab7\u0a89\u0aab\u0a98\u0aa0\u0ac3'\u0a8a\u0a87\u0a9e\u0a9d\u0aa2\u0ac8\u0a83\u0acc\\-\u0a8b\u0a90 ]"
|
| 26 |
+
},
|
| 27 |
+
"content": ""
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"type": "Strip",
|
| 31 |
+
"strip_left": true,
|
| 32 |
+
"strip_right": true
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"type": "Replace",
|
| 36 |
+
"pattern": {
|
| 37 |
+
"Regex": "(?=.)|(?<!^)$"
|
| 38 |
+
},
|
| 39 |
+
"content": "|"
|
| 40 |
+
}
|
| 41 |
+
]
|
| 42 |
+
},
|
| 43 |
+
"pre_tokenizer": {
|
| 44 |
+
"type": "Split",
|
| 45 |
+
"pattern": {
|
| 46 |
+
"Regex": ""
|
| 47 |
+
},
|
| 48 |
+
"behavior": "Isolated",
|
| 49 |
+
"invert": false
|
| 50 |
+
},
|
| 51 |
+
"post_processor": null,
|
| 52 |
+
"decoder": null,
|
| 53 |
+
"model": {
|
| 54 |
+
"vocab": {
|
| 55 |
+
"|": 0,
|
| 56 |
+
"\u0abe": 1,
|
| 57 |
+
"\u0ac7": 2,
|
| 58 |
+
"\u0aa4": 3,
|
| 59 |
+
"\u0aa8": 4,
|
| 60 |
+
"\u0ab0": 5,
|
| 61 |
+
"\u0acd": 6,
|
| 62 |
+
"\u0aae": 7,
|
| 63 |
+
"\u0ac0": 8,
|
| 64 |
+
"\u0a95": 9,
|
| 65 |
+
"\u0a82": 10,
|
| 66 |
+
"\u0acb": 11,
|
| 67 |
+
"\u0aaa": 12,
|
| 68 |
+
"\u0ab5": 13,
|
| 69 |
+
"\u0ac1": 14,
|
| 70 |
+
"\u0ab8": 15,
|
| 71 |
+
"\u0aaf": 16,
|
| 72 |
+
"\u0ab9": 17,
|
| 73 |
+
"\u0a9c": 18,
|
| 74 |
+
"\u0aa5": 19,
|
| 75 |
+
"\u0abf": 20,
|
| 76 |
+
"\u0ab6": 21,
|
| 77 |
+
"\u0aa3": 22,
|
| 78 |
+
"\u0a9b": 23,
|
| 79 |
+
"\u0ab2": 24,
|
| 80 |
+
"\u0aa6": 25,
|
| 81 |
+
"\u0a86": 26,
|
| 82 |
+
"\u0a93": 27,
|
| 83 |
+
"\u0a85": 28,
|
| 84 |
+
"\u0a8f": 29,
|
| 85 |
+
"\u0a88": 30,
|
| 86 |
+
"\u0aac": 31,
|
| 87 |
+
"\u0a97": 32,
|
| 88 |
+
"\u0a96": 33,
|
| 89 |
+
"\u0aa7": 34,
|
| 90 |
+
"\u0aad": 35,
|
| 91 |
+
"\u0a9f": 36,
|
| 92 |
+
"\u0ab3": 37,
|
| 93 |
+
"\u0ac2": 38,
|
| 94 |
+
"\u0a9a": 39,
|
| 95 |
+
"\u0aa1": 40,
|
| 96 |
+
"\u0ab7": 41,
|
| 97 |
+
"\u0a89": 42,
|
| 98 |
+
"\u0aab": 43,
|
| 99 |
+
"\u0a98": 44,
|
| 100 |
+
"\u0aa0": 45,
|
| 101 |
+
"\u0ac3": 46,
|
| 102 |
+
"'": 47,
|
| 103 |
+
"\u0a8a": 48,
|
| 104 |
+
"\u0a87": 49,
|
| 105 |
+
"\u0a9e": 50,
|
| 106 |
+
"\u0a9d": 51,
|
| 107 |
+
"\u0aa2": 52,
|
| 108 |
+
"\u0ac8": 53,
|
| 109 |
+
"\u0a83": 54,
|
| 110 |
+
"\u0acc": 55,
|
| 111 |
+
"-": 56,
|
| 112 |
+
"\u0a8b": 57,
|
| 113 |
+
"\u0a90": 58,
|
| 114 |
+
" ": 59,
|
| 115 |
+
"<unk>": 60
|
| 116 |
+
}
|
| 117 |
+
}
|
| 118 |
+
}
|