Upload tokenizer.json
Browse files- tokenizer.json +102 -0
tokenizer.json
ADDED
|
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 44,
|
| 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": "[^\u0447 \u0434\u044c\u044f\u0439\u0441\u0443\u0430\u043e20\u044a\u044b\u043d\u043b\u0436\u0445\u0448\u0437c_\u043fm\u044e\u044d\u04404\u0449o\u2013\u0444q\u0438\u0446\u043a1\u0435\u0431\\-\u0442\u0432\u0433\u043c]"
|
| 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": "\u0447"
|
| 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 |
+
"\u0447": 0,
|
| 56 |
+
" ": 1,
|
| 57 |
+
"\u0434": 2,
|
| 58 |
+
"\u044c": 3,
|
| 59 |
+
"\u044f": 4,
|
| 60 |
+
"\u0439": 5,
|
| 61 |
+
"\u0441": 6,
|
| 62 |
+
"\u0443": 7,
|
| 63 |
+
"\u0430": 8,
|
| 64 |
+
"\u043e": 9,
|
| 65 |
+
"2": 10,
|
| 66 |
+
"0": 11,
|
| 67 |
+
"\u044a": 12,
|
| 68 |
+
"\u044b": 13,
|
| 69 |
+
"\u043d": 14,
|
| 70 |
+
"\u043b": 15,
|
| 71 |
+
"\u0436": 16,
|
| 72 |
+
"\u0445": 17,
|
| 73 |
+
"\u0448": 18,
|
| 74 |
+
"\u0437": 19,
|
| 75 |
+
"c": 20,
|
| 76 |
+
"_": 21,
|
| 77 |
+
"\u043f": 22,
|
| 78 |
+
"m": 23,
|
| 79 |
+
"\u044e": 24,
|
| 80 |
+
"\u044d": 25,
|
| 81 |
+
"\u0440": 26,
|
| 82 |
+
"4": 27,
|
| 83 |
+
"\u0449": 28,
|
| 84 |
+
"o": 29,
|
| 85 |
+
"\u2013": 30,
|
| 86 |
+
"\u0444": 31,
|
| 87 |
+
"q": 32,
|
| 88 |
+
"\u0438": 33,
|
| 89 |
+
"\u0446": 34,
|
| 90 |
+
"\u043a": 35,
|
| 91 |
+
"1": 36,
|
| 92 |
+
"\u0435": 37,
|
| 93 |
+
"\u0431": 38,
|
| 94 |
+
"-": 39,
|
| 95 |
+
"\u0442": 40,
|
| 96 |
+
"\u0432": 41,
|
| 97 |
+
"\u0433": 42,
|
| 98 |
+
"\u043c": 43,
|
| 99 |
+
"<unk>": 44
|
| 100 |
+
}
|
| 101 |
+
}
|
| 102 |
+
}
|