Upload tokenizer.json with huggingface_hub (#2)
Browse files- Upload tokenizer.json with huggingface_hub (a5f8b3e4962b7ee43afbca28697aec17fd0ead88)
Co-authored-by: Joshua <[email protected]>
- tokenizer.json +116 -0
tokenizer.json
ADDED
|
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 58,
|
| 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": "[^3\u0b85\u0b88\u0b89_\u0ba8\u0b95 \u0bc7\u0bbe\u0bc6\u0b8a\u0bc0'7a\u0b8f\u0bb5\u0bcd\u0bb9\u0bc2\u0bb2\u0b9f2\u0bb4\u0bb0\u0bae\u0b92\u0bb1\u0b9e\u0b9a9\u0bbf\u0bb8\u0bc8\u0ba96\u0b8e\u0b87\u0baf\u0bcc\u0ba4\u0bcb\u0bb31\u0b86\u0baa0\u0ba3\u0b93\u0b99\u0bc1\u0b90\u0b9c4\u0bb7\u0bca5]"
|
| 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": "3"
|
| 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 |
+
"3": 0,
|
| 56 |
+
"\u0b85": 1,
|
| 57 |
+
"\u0b88": 2,
|
| 58 |
+
"\u0b89": 3,
|
| 59 |
+
"_": 4,
|
| 60 |
+
"\u0ba8": 5,
|
| 61 |
+
"\u0b95": 6,
|
| 62 |
+
" ": 7,
|
| 63 |
+
"\u0bc7": 8,
|
| 64 |
+
"\u0bbe": 9,
|
| 65 |
+
"\u0bc6": 10,
|
| 66 |
+
"\u0b8a": 11,
|
| 67 |
+
"\u0bc0": 12,
|
| 68 |
+
"'": 13,
|
| 69 |
+
"7": 14,
|
| 70 |
+
"a": 15,
|
| 71 |
+
"\u0b8f": 16,
|
| 72 |
+
"\u0bb5": 17,
|
| 73 |
+
"\u0bcd": 18,
|
| 74 |
+
"\u0bb9": 19,
|
| 75 |
+
"\u0bc2": 20,
|
| 76 |
+
"\u0bb2": 21,
|
| 77 |
+
"\u0b9f": 22,
|
| 78 |
+
"2": 23,
|
| 79 |
+
"\u0bb4": 24,
|
| 80 |
+
"\u0bb0": 25,
|
| 81 |
+
"\u0bae": 26,
|
| 82 |
+
"\u0b92": 27,
|
| 83 |
+
"\u0bb1": 28,
|
| 84 |
+
"\u0b9e": 29,
|
| 85 |
+
"\u0b9a": 30,
|
| 86 |
+
"9": 31,
|
| 87 |
+
"\u0bbf": 32,
|
| 88 |
+
"\u0bb8": 33,
|
| 89 |
+
"\u0bc8": 34,
|
| 90 |
+
"\u0ba9": 35,
|
| 91 |
+
"6": 36,
|
| 92 |
+
"\u0b8e": 37,
|
| 93 |
+
"\u0b87": 38,
|
| 94 |
+
"\u0baf": 39,
|
| 95 |
+
"\u0bcc": 40,
|
| 96 |
+
"\u0ba4": 41,
|
| 97 |
+
"\u0bcb": 42,
|
| 98 |
+
"\u0bb3": 43,
|
| 99 |
+
"1": 44,
|
| 100 |
+
"\u0b86": 45,
|
| 101 |
+
"\u0baa": 46,
|
| 102 |
+
"0": 47,
|
| 103 |
+
"\u0ba3": 48,
|
| 104 |
+
"\u0b93": 49,
|
| 105 |
+
"\u0b99": 50,
|
| 106 |
+
"\u0bc1": 51,
|
| 107 |
+
"\u0b90": 52,
|
| 108 |
+
"\u0b9c": 53,
|
| 109 |
+
"4": 54,
|
| 110 |
+
"\u0bb7": 55,
|
| 111 |
+
"\u0bca": 56,
|
| 112 |
+
"5": 57,
|
| 113 |
+
"<unk>": 58
|
| 114 |
+
}
|
| 115 |
+
}
|
| 116 |
+
}
|