Upload tokenizer.json with huggingface_hub (#2)
Browse files- Upload tokenizer.json with huggingface_hub (f5e39bcd916b66d7be27c2c790067d52106e1922)
Co-authored-by: Joshua <Xenova@users.noreply.huggingface.co>
- tokenizer.json +131 -0
tokenizer.json
ADDED
@@ -0,0 +1,131 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
5 |
+
"added_tokens": [
|
6 |
+
{
|
7 |
+
"id": 73,
|
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": "[^\u0919\u0939\u0906\u092c\u0922\u09162\u0902\u0924\u091f_\u0938\u090a1\u0915\u0914\u0933\u091a\u0913\\-\u0908\u0936\u091c\u0943\u0917\u091d\u0288\u0910\u0926 \u0921\u090f\u0948\u094c97\u0920\u0931\u0935\u094b\u090b04\u092f6\u0903\u0932\u0927\u092a\u091e\u092b\u0909\u0928\u0937\u092e\u091b\u0947\u093f\u0923'\u0905\u0907\u093e\u0941\u0942\u0287\u0934\u0918\u094d\u0930\u092d\u0940\u0925]"
|
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": "\u0919"
|
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 |
+
"\u0919": 0,
|
56 |
+
"\u0939": 1,
|
57 |
+
"\u0906": 2,
|
58 |
+
"\u092c": 3,
|
59 |
+
"\u0922": 4,
|
60 |
+
"\u0916": 5,
|
61 |
+
"2": 6,
|
62 |
+
"\u0902": 7,
|
63 |
+
"\u0924": 8,
|
64 |
+
"\u091f": 9,
|
65 |
+
"_": 10,
|
66 |
+
"\u0938": 11,
|
67 |
+
"\u090a": 12,
|
68 |
+
"1": 13,
|
69 |
+
"\u0915": 14,
|
70 |
+
"\u0914": 15,
|
71 |
+
"\u0933": 16,
|
72 |
+
"\u091a": 17,
|
73 |
+
"\u0913": 18,
|
74 |
+
"-": 19,
|
75 |
+
"\u0908": 20,
|
76 |
+
"\u0936": 21,
|
77 |
+
"\u091c": 22,
|
78 |
+
"\u0943": 23,
|
79 |
+
"\u0917": 24,
|
80 |
+
"\u091d": 25,
|
81 |
+
"\u0288": 26,
|
82 |
+
"\u0910": 27,
|
83 |
+
"\u0926": 28,
|
84 |
+
" ": 29,
|
85 |
+
"\u0921": 30,
|
86 |
+
"\u090f": 31,
|
87 |
+
"\u0948": 32,
|
88 |
+
"\u094c": 33,
|
89 |
+
"9": 34,
|
90 |
+
"7": 35,
|
91 |
+
"\u0920": 36,
|
92 |
+
"\u0931": 37,
|
93 |
+
"\u0935": 38,
|
94 |
+
"\u094b": 39,
|
95 |
+
"\u090b": 40,
|
96 |
+
"0": 41,
|
97 |
+
"4": 42,
|
98 |
+
"\u092f": 43,
|
99 |
+
"6": 44,
|
100 |
+
"\u0903": 45,
|
101 |
+
"\u0932": 46,
|
102 |
+
"\u0927": 47,
|
103 |
+
"\u092a": 48,
|
104 |
+
"\u091e": 49,
|
105 |
+
"\u092b": 50,
|
106 |
+
"\u0909": 51,
|
107 |
+
"\u0928": 52,
|
108 |
+
"\u0937": 53,
|
109 |
+
"\u092e": 54,
|
110 |
+
"\u091b": 55,
|
111 |
+
"\u0947": 56,
|
112 |
+
"\u093f": 57,
|
113 |
+
"\u0923": 58,
|
114 |
+
"'": 59,
|
115 |
+
"\u0905": 60,
|
116 |
+
"\u0907": 61,
|
117 |
+
"\u093e": 62,
|
118 |
+
"\u0941": 63,
|
119 |
+
"\u0942": 64,
|
120 |
+
"\u0287": 65,
|
121 |
+
"\u0934": 66,
|
122 |
+
"\u0918": 67,
|
123 |
+
"\u094d": 68,
|
124 |
+
"\u0930": 69,
|
125 |
+
"\u092d": 70,
|
126 |
+
"\u0940": 71,
|
127 |
+
"\u0925": 72,
|
128 |
+
"<unk>": 73
|
129 |
+
}
|
130 |
+
}
|
131 |
+
}
|