gpt-tokenizer 2.0.0-beta.1 → 2.0.0-beta.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (63) hide show
  1. package/README.md +125 -43
  2. package/cjs/GptEncoding.d.ts +5 -0
  3. package/cjs/GptEncoding.js +6 -0
  4. package/cjs/GptEncoding.js.map +1 -1
  5. package/cjs/GptEncoding.test.js +38 -0
  6. package/cjs/GptEncoding.test.js.map +1 -1
  7. package/cjs/encoding/cl100k_base.d.ts +4 -0
  8. package/cjs/encoding/cl100k_base.js +17 -0
  9. package/cjs/encoding/cl100k_base.js.map +1 -1
  10. package/cjs/encoding/p50k_base.d.ts +4 -0
  11. package/cjs/encoding/p50k_base.js +17 -0
  12. package/cjs/encoding/p50k_base.js.map +1 -1
  13. package/cjs/encoding/p50k_edit.d.ts +4 -0
  14. package/cjs/encoding/p50k_edit.js +17 -0
  15. package/cjs/encoding/p50k_edit.js.map +1 -1
  16. package/cjs/encoding/r50k_base.d.ts +4 -0
  17. package/cjs/encoding/r50k_base.js +17 -0
  18. package/cjs/encoding/r50k_base.js.map +1 -1
  19. package/cjs/modelParams.js +12 -16
  20. package/cjs/modelParams.js.map +1 -1
  21. package/cjs/specialTokens.d.ts +5 -0
  22. package/cjs/specialTokens.js +9 -0
  23. package/cjs/specialTokens.js.map +1 -0
  24. package/data/TestPlans.txt +1024 -0
  25. package/dist/cl100k_base.js +1 -1
  26. package/dist/cl100k_base.js.map +1 -1
  27. package/dist/p50k_base.js +1 -1
  28. package/dist/p50k_base.js.map +1 -1
  29. package/dist/p50k_edit.js +1 -1
  30. package/dist/p50k_edit.js.map +1 -1
  31. package/dist/r50k_base.js +1 -1
  32. package/dist/r50k_base.js.map +1 -1
  33. package/esm/GptEncoding.d.ts +5 -0
  34. package/esm/GptEncoding.js +8 -1
  35. package/esm/GptEncoding.js.map +1 -1
  36. package/esm/GptEncoding.test.js +35 -0
  37. package/esm/GptEncoding.test.js.map +1 -1
  38. package/esm/encoding/cl100k_base.d.ts +4 -0
  39. package/esm/encoding/cl100k_base.js +3 -0
  40. package/esm/encoding/cl100k_base.js.map +1 -1
  41. package/esm/encoding/p50k_base.d.ts +4 -0
  42. package/esm/encoding/p50k_base.js +3 -0
  43. package/esm/encoding/p50k_base.js.map +1 -1
  44. package/esm/encoding/p50k_edit.d.ts +4 -0
  45. package/esm/encoding/p50k_edit.js +3 -0
  46. package/esm/encoding/p50k_edit.js.map +1 -1
  47. package/esm/encoding/r50k_base.d.ts +4 -0
  48. package/esm/encoding/r50k_base.js +3 -0
  49. package/esm/encoding/r50k_base.js.map +1 -1
  50. package/esm/modelParams.js +1 -5
  51. package/esm/modelParams.js.map +1 -1
  52. package/esm/specialTokens.d.ts +5 -0
  53. package/esm/specialTokens.js +6 -0
  54. package/esm/specialTokens.js.map +1 -0
  55. package/package.json +5 -5
  56. package/src/GptEncoding.test.ts +40 -0
  57. package/src/GptEncoding.ts +13 -0
  58. package/src/encoding/cl100k_base.ts +4 -0
  59. package/src/encoding/p50k_base.ts +4 -0
  60. package/src/encoding/p50k_edit.ts +4 -0
  61. package/src/encoding/r50k_base.ts +4 -0
  62. package/src/modelParams.ts +7 -6
  63. package/src/specialTokens.ts +5 -0
@@ -0,0 +1,1024 @@
1
+ EncodingName: r50k_base
2
+ Sample:
3
+ Encoded: []
4
+
5
+ EncodingName: r50k_base
6
+ Sample: a
7
+ Encoded: [64]
8
+
9
+ EncodingName: r50k_base
10
+ Sample: 1
11
+ Encoded: [16]
12
+
13
+ EncodingName: r50k_base
14
+ Sample: a a
15
+ Encoded: [64, 257]
16
+
17
+ EncodingName: r50k_base
18
+ Sample: hello
19
+ Encoded: [31373]
20
+
21
+ EncodingName: r50k_base
22
+ Sample: Hello, World! How are you today? 🌍
23
+ Encoded: [15496, 11, 2159, 0, 1374, 389, 345, 1909, 30, 12520, 234, 235]
24
+
25
+ EncodingName: r50k_base
26
+ Sample: こんにちは、世界!お元気ですか?
27
+ Encoded: [46036, 22174, 28618, 2515, 94, 31676, 23513, 10310, 244, 45911, 234, 171, 120, 223, 2515, 232, 17739, 225, 36365, 245, 30640, 33623, 27370, 171, 120, 253]
28
+
29
+ EncodingName: r50k_base
30
+ Sample: Hola, mundo! ¿Cómo estás hoy? 🇪🇸
31
+ Encoded: [39, 5708, 11, 27943, 78, 0, 1587, 123, 34, 10205, 5908, 1556, 40138, 289, 726, 30, 12520, 229, 103, 8582, 229, 116]
32
+
33
+ EncodingName: r50k_base
34
+ Sample: Привет, мир! Как дела?
35
+ Encoded: [140, 253, 21169, 18849, 38857, 16843, 20375, 11, 12466, 120, 18849, 21169, 0, 12466, 248, 16142, 31583, 12466, 112, 16843, 30143, 16142, 30]
36
+
37
+ EncodingName: r50k_base
38
+ Sample: 안녕하세요, 세상! 오늘 기분이 어때요? 🇰🇷
39
+ Encoded: [168, 243, 230, 167, 227, 243, 47991, 246, 168, 226, 116, 168, 248, 242, 11, 23821, 226, 116, 168, 225, 223, 0, 23821, 246, 97, 167, 232, 246, 220, 166, 116, 108, 167, 114, 226, 35975, 112, 23821, 244, 112, 167, 243, 234, 168, 248, 242, 30, 12520, 229, 108, 8582, 229, 115]
40
+
41
+ EncodingName: r50k_base
42
+ Sample: Bonjour, le monde ! Comment ça va aujourd'hui ? 🇫🇷
43
+ Encoded: [20682, 73, 454, 11, 443, 285, 14378, 5145, 18957, 6184, 100, 64, 46935, 257, 23577, 454, 67, 6, 71, 9019, 5633, 12520, 229, 104, 8582, 229, 115]
44
+
45
+ EncodingName: r50k_base
46
+ Sample: The quick brown fox jumps over 13 lazy dogs. 😺
47
+ Encoded: [464, 2068, 7586, 21831, 18045, 625, 1511, 16931, 6844, 13, 30325, 118]
48
+
49
+ EncodingName: r50k_base
50
+ Sample: 1234567890!@#$%^&*()-=_+[]{};:'",.<>?/|`~ 🎉
51
+ Encoded: [10163, 2231, 30924, 3829, 0, 31, 29953, 4, 61, 5, 9, 3419, 12, 28, 62, 10, 21737, 90, 19629, 32105, 1600, 29847, 29, 30, 14, 91, 63, 93, 12520, 236, 231]
52
+
53
+ EncodingName: r50k_base
54
+ Sample: C# is a great programming language for building apps.
55
+ Encoded: [34, 2, 318, 257, 1049, 8300, 3303, 329, 2615, 6725, 13]
56
+
57
+ EncodingName: r50k_base
58
+ Sample: El área de un triángulo es (base * altura) / 2.
59
+ Encoded: [9527, 6184, 94, 21468, 390, 555, 1333, 6557, 782, 43348, 1658, 357, 8692, 1635, 5988, 5330, 8, 1220, 362, 13]
60
+
61
+ EncodingName: r50k_base
62
+ Sample: Здравствуйте, это мой первый раз здесь. Что мне делать?
63
+ Encoded: [140, 245, 43666, 21169, 16142, 38857, 21727, 20375, 38857, 35072, 140, 117, 20375, 16843, 11, 220, 141, 235, 20375, 15166, 12466, 120, 25443, 117, 12466, 123, 16843, 21169, 38857, 45035, 140, 117, 220, 21169, 16142, 140, 115, 12466, 115, 43666, 16843, 21727, 45367, 13, 12466, 100, 20375, 15166, 12466, 120, 22177, 16843, 12466, 112, 16843, 30143, 16142, 20375, 45367, 30]
64
+
65
+ EncodingName: r50k_base
66
+ Sample: હેલો, વિશ્વ! તમે આજે કેમ છો? 🇮🇳
67
+ Encoded: [156, 103, 117, 156, 104, 229, 156, 103, 110, 156, 104, 233, 11, 220, 156, 103, 113, 156, 103, 123, 156, 103, 114, 156, 104, 235, 156, 103, 113, 0, 220, 156, 103, 97, 156, 103, 106, 156, 104, 229, 220, 156, 103, 228, 156, 103, 250, 156, 104, 229, 220, 156, 103, 243, 156, 104, 229, 156, 103, 106, 220, 156, 103, 249, 156, 104, 233, 30, 12520, 229, 106, 8582, 229, 111]
68
+
69
+ EncodingName: r50k_base
70
+ Sample: ความรักและการเป็นกันเองเป็นสิ่งสำคัญที่สุดในโลก 🇹🇭
71
+ Encoded: [19567, 226, 19567, 100, 19567, 110, 19567, 94, 19567, 96, 19567, 109, 19567, 223, 31479, 223, 19567, 98, 19567, 108, 19567, 223, 19567, 110, 19567, 96, 31479, 222, 19567, 249, 31479, 229, 19567, 247, 19567, 223, 19567, 109, 19567, 247, 31479, 222, 19567, 255, 19567, 229, 31479, 222, 19567, 249, 31479, 229, 19567, 247, 19567, 103, 19567, 112, 31479, 230, 19567, 229, 19567, 103, 19567, 111, 19567, 226, 19567, 109, 19567, 235, 19567, 245, 19567, 113, 31479, 230, 19567, 103, 19567, 116, 19567, 242, 31479, 225, 19567, 247, 31479, 224, 19567, 98, 19567, 223, 12520, 229, 117, 8582, 229, 255]
72
+
73
+ EncodingName: r50k_base
74
+ Sample: Python vs Java: Which programming language should you learn first?
75
+ Encoded: [37906, 3691, 7349, 25, 9022, 8300, 3303, 815, 345, 2193, 717, 30]
76
+
77
+ EncodingName: r50k_base
78
+ Sample: A journey of a thousand miles begins with a single step. - Lao Tzu
79
+ Encoded: [32, 7002, 286, 257, 7319, 4608, 6140, 351, 257, 2060, 2239, 13, 532, 4689, 78, 309, 27624]
80
+
81
+ EncodingName: r50k_base
82
+ Sample: Die Grenzen meiner Sprache bedeuten die Grenzen meiner Welt. 🇩🇪
83
+ Encoded: [32423, 19674, 4801, 502, 7274, 5522, 4891, 3996, 68, 7809, 4656, 19674, 4801, 502, 7274, 370, 2120, 13, 12520, 229, 102, 8582, 229, 103]
84
+
85
+ EncodingName: r50k_base
86
+ Sample: יש לי כמה שאלות בנוגע לפרויקט החדש שלך. 🇮🇱
87
+ Encoded: [33951, 102, 14360, 250, 25529, 14360, 249, 49168, 38269, 14360, 102, 42973, 40010, 27072, 42064, 14360, 239, 147, 254, 27072, 147, 240, 147, 95, 14360, 250, 147, 97, 37778, 27072, 33951, 100, 147, 246, 14360, 242, 147, 245, 147, 241, 50227, 14360, 102, 40010, 147, 248, 13, 12520, 229, 106, 8582, 229, 109]
88
+
89
+ EncodingName: r50k_base
90
+ Sample: Det är en vacker dag i Sverige. 🇸🇪
91
+ Encoded: [11242, 6184, 97, 81, 551, 410, 10735, 48924, 1312, 311, 332, 10045, 13, 12520, 229, 116, 8582, 229, 103]
92
+
93
+ EncodingName: r50k_base
94
+ Sample: A ∀ x (P(x) → Q(x)) ∧ (∃x P(x)) → ∃x Q(x)
95
+ Encoded: [32, 18872, 222, 2124, 357, 47, 7, 87, 8, 15168, 1195, 7, 87, 4008, 18872, 100, 357, 24861, 225, 87, 350, 7, 87, 4008, 15168, 18872, 225, 87, 1195, 7, 87, 8]
96
+
97
+ EncodingName: r50k_base
98
+ Sample: O Brasil é o maior país da América do Sul. 🇧🇷
99
+ Encoded: [46, 39452, 346, 38251, 267, 17266, 1504, 14187, 41200, 12379, 1703, 2634, 30997, 466, 29357, 13, 12520, 229, 100, 8582, 229, 115]
100
+
101
+ EncodingName: r50k_base
102
+ Sample: L'amore è una forza potente che unisce le persone. 🇮🇹
103
+ Encoded: [43, 6, 321, 382, 6184, 101, 555, 64, 329, 4496, 16739, 68, 1125, 555, 271, 344, 443, 2774, 505, 13, 12520, 229, 106, 8582, 229, 117]
104
+
105
+ EncodingName: r50k_base
106
+ Sample: Είναι μια ηλιόλουστη ημέρα στην Ελλάδα. 🇬🇷
107
+ Encoded: [138, 243, 138, 107, 26180, 17394, 29945, 18919, 29945, 17394, 7377, 115, 39377, 29945, 139, 234, 39377, 26517, 139, 227, 38392, 32830, 138, 115, 7377, 115, 34703, 138, 255, 33643, 17394, 18074, 225, 32830, 138, 115, 26180, 7377, 243, 39377, 39377, 138, 105, 138, 112, 17394, 13, 12520, 229, 105, 8582, 229, 115]
108
+
109
+ EncodingName: r50k_base
110
+ Sample: Teslim tarihi yaklaşıyor, projeyi zamanında bitirmemiz gerekiyor. 🇹🇷
111
+ Encoded: [36504, 2475, 256, 2743, 5303, 46251, 5031, 46481, 30102, 88, 273, 11, 386, 73, 2959, 72, 1976, 10546, 30102, 45658, 1643, 2533, 368, 528, 308, 567, 4106, 88, 273, 13, 12520, 229, 117, 8582, 229, 115]
112
+
113
+ EncodingName: r50k_base
114
+ Sample: Det finnes ingen bedre tid enn nå for å starte noe nytt. 🇳🇴
115
+ Encoded: [11242, 957, 2516, 27016, 3996, 260, 29770, 551, 77, 299, 29090, 329, 6184, 98, 923, 68, 645, 68, 299, 88, 926, 13, 12520, 229, 111, 8582, 229, 112]
116
+
117
+ EncodingName: r50k_base
118
+ Sample: Aanvaard de uitdagingen van het leven met moed en vastberadenheid. 🇳🇱
119
+ Encoded: [32, 272, 6862, 446, 390, 334, 270, 67, 3039, 268, 5719, 339, 83, 443, 574, 1138, 6941, 276, 551, 5909, 527, 40780, 28420, 13, 12520, 229, 111, 8582, 229, 109]
120
+
121
+ EncodingName: r50k_base
122
+ Sample: Chào mừng bạn đến với thế giới của lập trình. 🇻🇳
123
+ Encoded: [1925, 24247, 78, 285, 157, 119, 104, 782, 275, 157, 118, 94, 77, 34754, 239, 157, 118, 123, 77, 410, 157, 119, 249, 72, 294, 157, 118, 123, 308, 72, 157, 119, 249, 72, 269, 157, 119, 100, 64, 300, 157, 118, 255, 79, 491, 127, 105, 77, 71, 13, 12520, 229, 119, 8582, 229, 111]
124
+
125
+ EncodingName: r50k_base
126
+ Sample: Dlaczego warto uczyć się języków obcych? 🇵🇱
127
+ Encoded: [35, 75, 330, 89, 1533, 78, 32943, 78, 334, 66, 7357, 38325, 33721, 128, 247, 474, 128, 247, 46355, 10205, 86, 909, 948, 354, 30, 12520, 229, 113, 8582, 229, 109]
128
+
129
+ EncodingName: r50k_base
130
+ Sample: E = mc², uma equação famosa na física. 🇵🇹
131
+ Encoded: [36, 796, 36650, 31185, 11, 334, 2611, 1602, 64, 16175, 28749, 1145, 8546, 12385, 277, 41200, 3970, 13, 12520, 229, 113, 8582, 229, 117]
132
+
133
+ EncodingName: r50k_base
134
+ Sample: 你今天遇到什么有趣的事情了吗?🇨🇳
135
+ Encoded: [19526, 254, 20015, 232, 25465, 34402, 229, 26344, 108, 20015, 222, 20046, 230, 17312, 231, 164, 114, 96, 21410, 12859, 233, 46349, 227, 12859, 228, 28938, 245, 171, 120, 253, 8582, 229, 101, 8582, 229, 111]
136
+
137
+ EncodingName: r50k_base
138
+ Sample: Nå er det tid for å feire med familie og venner. 🇳🇴
139
+ Encoded: [45, 29090, 1931, 1062, 29770, 329, 6184, 98, 730, 557, 1117, 1145, 346, 494, 267, 70, 8710, 1008, 13, 12520, 229, 111, 8582, 229, 112]
140
+
141
+ EncodingName: r50k_base
142
+ Sample: Þetta er góður dagur til að læra eitthvað nýtt. 🇮🇸
143
+ Encoded: [127, 252, 15253, 1931, 308, 10205, 27214, 333, 48924, 333, 21502, 257, 27214, 300, 21241, 430, 304, 270, 400, 6862, 27214, 299, 127, 121, 926, 13, 12520, 229, 106, 8582, 229, 116]
144
+
145
+ EncodingName: r50k_base
146
+ Sample: გამარჯობა! როგორ ხართ დღეს? 🇬🇪
147
+ Encoded: [157, 225, 240, 157, 225, 238, 157, 225, 249, 157, 225, 238, 157, 225, 254, 157, 225, 107, 157, 225, 251, 157, 225, 239, 157, 225, 238, 0, 28053, 225, 254, 157, 225, 251, 157, 225, 240, 157, 225, 251, 157, 225, 254, 28053, 225, 106, 157, 225, 238, 157, 225, 254, 157, 225, 245, 28053, 225, 241, 157, 225, 99, 157, 225, 242, 157, 225, 94, 30, 12520, 229, 105, 8582, 229, 103]
148
+
149
+ EncodingName: r50k_base
150
+ Sample: Mā te whakawhiti kōrero e whai hua ai tātou. 🇳🇿
151
+ Encoded: [44, 10235, 573, 348, 461, 707, 71, 8846, 479, 13090, 34785, 304, 348, 1872, 289, 6413, 257, 72, 256, 10235, 83, 280, 13, 12520, 229, 111, 8582, 229, 123]
152
+
153
+ EncodingName: r50k_base
154
+ Sample: Это был незабываемый опыт, который я буду помнить всегда.
155
+ Encoded: [140, 255, 20375, 15166, 12466, 109, 45035, 30143, 12466, 121, 16843, 140, 115, 16142, 140, 109, 45035, 38857, 16142, 16843, 43108, 45035, 140, 117, 12466, 122, 140, 123, 45035, 20375, 11, 12466, 118, 15166, 20375, 15166, 21169, 45035, 140, 117, 220, 40623, 12466, 109, 35072, 43666, 35072, 12466, 123, 25443, 120, 22177, 18849, 20375, 45367, 12466, 110, 21727, 16843, 140, 111, 43666, 16142, 13]
156
+
157
+ EncodingName: r50k_base
158
+ Sample: Διαβάζοντας βιβλία, εμπλουτίζουμε τον εαυτό μας με γνώσεις.
159
+ Encoded: [138, 242, 29945, 17394, 26638, 138, 105, 138, 114, 26517, 26180, 32830, 17394, 35558, 27169, 29945, 26638, 39377, 138, 107, 17394, 11, 7377, 113, 34703, 46582, 39377, 26517, 139, 227, 32830, 138, 107, 138, 114, 26517, 139, 227, 34703, 30950, 46651, 26517, 26180, 7377, 113, 17394, 139, 227, 32830, 139, 234, 18919, 17394, 35558, 18919, 30950, 7377, 111, 26180, 139, 236, 38392, 30950, 29945, 35558, 13]
160
+
161
+ EncodingName: r50k_base
162
+ Sample: A számítástechnika világa tele van izgalmas lehetőségekkel. 🇭🇺
163
+ Encoded: [32, 264, 89, 6557, 76, 8836, 83, 6557, 4169, 1349, 9232, 39796, 6557, 4908, 5735, 5719, 220, 528, 13528, 5356, 443, 3202, 129, 239, 82, 2634, 469, 74, 7750, 13, 12520, 229, 255, 8582, 229, 118]
164
+
165
+ EncodingName: r50k_base
166
+ Sample: Vždy je dobré mít plán B, pokud něco nevyjde. 🇨🇿
167
+ Encoded: [53, 129, 122, 9892, 11223, 466, 1671, 2634, 285, 8836, 83, 458, 21162, 347, 11, 279, 482, 463, 299, 128, 249, 1073, 497, 7670, 73, 2934, 13, 12520, 229, 101, 8582, 229, 123]
168
+
169
+ EncodingName: r50k_base
170
+ Sample: Dragostea e un sentiment minunat care ne unește pe toți. 🇷🇴
171
+ Encoded: [46022, 455, 18213, 304, 555, 15598, 949, 403, 265, 1337, 497, 17809, 132, 247, 660, 613, 284, 132, 249, 72, 13, 12520, 229, 115, 8582, 229, 112]
172
+
173
+ EncodingName: r50k_base
174
+ Sample: دیکھو، آسمان میں کتنی تارے ہیں! 🇵🇰
175
+ Encoded: [38843, 151, 234, 150, 102, 150, 122, 30335, 148, 234, 17550, 95, 45692, 25405, 12919, 23338, 47048, 151, 234, 150, 118, 220, 150, 102, 41486, 23338, 151, 234, 17550, 103, 12919, 26897, 151, 240, 220, 151, 223, 151, 234, 150, 118, 0, 12520, 229, 113, 8582, 229, 108]
176
+
177
+ EncodingName: r50k_base
178
+ Sample: Nenda polepole na ujifunze kila siku. 🇹🇿
179
+ Encoded: [45, 7438, 16825, 36869, 12385, 334, 73, 361, 403, 2736, 8769, 64, 264, 28643, 13, 12520, 229, 117, 8582, 229, 123]
180
+
181
+ EncodingName: r50k_base
182
+ Sample: Каква е твоята любима храна? 🇧🇬
183
+ Encoded: [140, 248, 16142, 31583, 38857, 16142, 12466, 113, 220, 20375, 38857, 15166, 40623, 20375, 16142, 12466, 119, 141, 236, 140, 109, 18849, 43108, 16142, 220, 141, 227, 21169, 16142, 22177, 16142, 30, 12520, 229, 100, 8582, 229, 105]
184
+
185
+ EncodingName: r50k_base
186
+ Sample: Sträva alltid efter att bli en bättre version av dig själv.
187
+ Encoded: [13290, 11033, 6862, 477, 83, 312, 304, 637, 708, 698, 72, 551, 275, 11033, 926, 260, 2196, 1196, 3100, 264, 73, 11033, 6780, 13]
188
+
189
+ EncodingName: r50k_base
190
+ Sample: Філософія - це наука про знання. 🇺🇦
191
+ Encoded: [140, 97, 141, 244, 30143, 15166, 21727, 15166, 141, 226, 141, 244, 40623, 532, 220, 141, 228, 16843, 12466, 121, 16142, 35072, 31583, 16142, 12466, 123, 21169, 15166, 12466, 115, 22177, 16142, 22177, 22177, 40623, 13, 12520, 229, 118, 8582, 229, 99]
192
+
193
+ EncodingName: r50k_base
194
+ Sample: Το πρόγραμμα αυτό είναι πολύ ενδιαφέρον. 🇬🇷
195
+ Encoded: [138, 97, 26517, 18074, 222, 33643, 139, 234, 42063, 33643, 17394, 34703, 34703, 17394, 26367, 139, 227, 32830, 139, 234, 7377, 113, 138, 107, 26180, 17394, 29945, 18074, 222, 26517, 39377, 139, 235, 7377, 113, 26180, 138, 112, 29945, 17394, 139, 228, 138, 255, 33643, 26517, 26180, 13, 12520, 229, 105, 8582, 229, 115]
196
+
197
+ EncodingName: r50k_base
198
+ Sample: ^$%#*@!&)(_+=}{|:;"?><,~`'-./][
199
+ Encoded: [61, 3, 4, 2, 9, 31, 0, 5, 5769, 62, 47932, 18477, 91, 25, 26, 13984, 6927, 11, 93, 63, 29001, 19571, 7131]
200
+
201
+ EncodingName: r50k_base
202
+ Sample: 4gH@!0sT*#(9^%$[x{}j+|Yz6;Q]~8
203
+ Encoded: [19, 70, 39, 31, 0, 15, 82, 51, 9, 2, 7, 24, 61, 4, 3, 58, 87, 90, 92, 73, 10, 91, 56, 89, 21, 26, 48, 60, 93, 23]
204
+
205
+ EncodingName: r50k_base
206
+ Sample: wNb)I<>#:i^P]*cR8ytUx1Q`6O@z/
207
+ Encoded: [86, 45, 65, 8, 40, 27, 29, 2, 25, 72, 61, 47, 60, 9, 66, 49, 23, 20760, 52, 87, 16, 48, 63, 21, 46, 31, 89, 14]
208
+
209
+ EncodingName: r50k_base
210
+ Sample: ÄÜö¿¡¢£¤¥¦§¨©ª«¬®¯°±²³´µ¶·¸¹º»¼½¾¿
211
+ Encoded: [127, 226, 127, 250, 9101, 126, 123, 126, 94, 44359, 14988, 126, 97, 126, 98, 126, 99, 16273, 37102, 16224, 126, 103, 24328, 126, 105, 7461, 5196, 7200, 22519, 31185, 126, 111, 18265, 126, 113, 26604, 9129, 126, 116, 126, 117, 36165, 17730, 126, 120, 23141, 126, 122, 126, 123]
212
+
213
+ EncodingName: r50k_base
214
+ Sample: ƒšŠŒŽƒšŠŒŽƒšŠŒŽƒšŠŒŽƒšŠŒŽƒšŠŒŽ
215
+ Encoded: [130, 240, 32790, 129, 254, 129, 240, 129, 121, 130, 240, 32790, 129, 254, 129, 240, 129, 121, 130, 240, 32790, 129, 254, 129, 240, 129, 121, 130, 240, 32790, 129, 254, 129, 240, 129, 121, 130, 240, 32790, 129, 254, 129, 240, 129, 121, 130, 240, 32790, 129, 254, 129, 240, 129, 121]
216
+
217
+ EncodingName: r50k_base
218
+ Sample: 5ħÅŸēýïūē$%#^*()_+{[ö&!@#?>|,.<>
219
+ Encoded: [20, 128, 100, 127, 227, 129, 116, 27092, 127, 121, 26884, 20317, 27092, 3, 4, 2, 61, 9, 3419, 62, 10, 90, 58, 9101, 5, 0, 41573, 30, 29, 91, 11, 29847, 29]
220
+
221
+ EncodingName: r50k_base
222
+ Sample: 1B4t#%&*()_+dF5g^hJk7LmN0pQrS<>?
223
+ Encoded: [16, 33, 19, 83, 2, 4, 5, 9, 3419, 62, 10, 67, 37, 20, 70, 61, 71, 41, 74, 22, 43, 76, 45, 15, 79, 48, 81, 50, 27, 29, 30]
224
+
225
+ EncodingName: r50k_base
226
+ Sample: ¬§±²³µ¶·¹ºª«»¦©¯°±!@#$%^&*()_+
227
+ Encoded: [126, 105, 16273, 22519, 31185, 126, 111, 126, 113, 26604, 9129, 126, 117, 36165, 126, 103, 24328, 17730, 126, 99, 16224, 5196, 7200, 22519, 0, 31, 29953, 4, 61, 5, 9, 3419, 62, 10]
228
+
229
+ EncodingName: r50k_base
230
+ Sample: 8mR5*w7^a$!F(0%#J9@X6vZ1)nU3]_Y/
231
+ Encoded: [23, 76, 49, 20, 9, 86, 22, 61, 64, 3, 0, 37, 7, 15, 4, 2, 41, 24, 31, 55, 21, 85, 57, 16, 8, 77, 52, 18, 60, 62, 56, 14]
232
+
233
+ EncodingName: r50k_base
234
+ Sample: 😊😀😁😂🤣😃😄😅😆😉😊😋😎😍😘😗😙😚☺️🙂🤗🤔
235
+ Encoded: [47249, 232, 47249, 222, 47249, 223, 47249, 224, 8582, 97, 96, 47249, 225, 47249, 226, 8582, 11805, 47249, 228, 47249, 231, 47249, 232, 47249, 233, 47249, 236, 47249, 235, 47249, 246, 47249, 245, 47249, 247, 47249, 248, 24583, 118, 37929, 8582, 25081, 8582, 97, 245, 8582, 97, 242]
236
+
237
+ EncodingName: r50k_base
238
+ Sample: 🤨😐😑😶🙄😏😣😥😮🤐😯😪😫😴😌🤓😛😜😝🤤
239
+ Encoded: [8582, 97, 101, 47249, 238, 47249, 239, 47249, 114, 8582, 247, 226, 47249, 237, 47249, 96, 47249, 98, 47249, 106, 8582, 97, 238, 47249, 107, 47249, 103, 47249, 104, 47249, 112, 47249, 234, 8582, 97, 241, 47249, 249, 47249, 250, 47249, 251, 8582, 97, 97]
240
+
241
+ EncodingName: r50k_base
242
+ Sample: 😒😓😔😕🙃🤑😲😷🤒🤕🤢🤧😈👿👹👺💀☠️
243
+ Encoded: [47249, 240, 47249, 241, 47249, 242, 47249, 243, 8582, 247, 225, 8582, 97, 239, 47249, 110, 47249, 115, 8582, 97, 240, 8582, 97, 243, 8582, 97, 95, 8582, 97, 100, 47249, 230, 41840, 123, 41840, 117, 41840, 118, 8582, 240, 222, 24583, 254, 37929]
244
+
245
+ EncodingName: r50k_base
246
+ Sample: 😾😿🙀😽😼😻🙈🙉🙊👶👦👧👨👩👴👵👨‍⚕️👩‍⚕️
247
+ Encoded: [47249, 122, 47249, 123, 8582, 247, 222, 47249, 121, 47249, 120, 47249, 119, 8582, 247, 230, 8582, 247, 231, 8582, 247, 232, 41840, 114, 41840, 99, 41840, 100, 41840, 101, 41840, 102, 41840, 112, 41840, 113, 41840, 101, 447, 235, 158, 248, 243, 37929, 41840, 102, 447, 235, 158, 248, 243, 37929]
248
+
249
+ EncodingName: r50k_base
250
+ Sample: 🌞🌝🌚🌛🌜🌙⭐️🌟💫✨🔥💥☄️🌈☀️🌤️⛅️🌥️
251
+ Encoded: [8582, 234, 252, 8582, 234, 251, 8582, 234, 248, 8582, 234, 249, 8582, 234, 250, 8582, 234, 247, 158, 255, 238, 37929, 8582, 234, 253, 8582, 240, 104, 26486, 101, 8582, 242, 98, 8582, 240, 98, 24583, 226, 37929, 8582, 234, 230, 24583, 222, 37929, 8582, 234, 97, 37929, 158, 249, 227, 37929, 8582, 234, 98, 37929]
252
+
253
+ EncodingName: r50k_base
254
+ Sample: 🍏🍎🍐🍊🍋🍌🍉🍇🍓🍈🍒🍑
255
+ Encoded: [8582, 235, 237, 8582, 235, 236, 8582, 235, 238, 8582, 235, 232, 8582, 235, 233, 8582, 235, 234, 8582, 235, 231, 8582, 235, 229, 8582, 235, 241, 8582, 235, 230, 8582, 235, 240, 8582, 235, 239]
256
+
257
+ EncodingName: p50k_base
258
+ Sample:
259
+ Encoded: []
260
+
261
+ EncodingName: p50k_base
262
+ Sample: a
263
+ Encoded: [64]
264
+
265
+ EncodingName: p50k_base
266
+ Sample: 1
267
+ Encoded: [16]
268
+
269
+ EncodingName: p50k_base
270
+ Sample: a a
271
+ Encoded: [64, 257]
272
+
273
+ EncodingName: p50k_base
274
+ Sample: hello
275
+ Encoded: [31373]
276
+
277
+ EncodingName: p50k_base
278
+ Sample: Hello, World! How are you today? 🌍
279
+ Encoded: [15496, 11, 2159, 0, 1374, 389, 345, 1909, 30, 12520, 234, 235]
280
+
281
+ EncodingName: p50k_base
282
+ Sample: こんにちは、世界!お元気ですか?
283
+ Encoded: [46036, 22174, 28618, 2515, 94, 31676, 23513, 10310, 244, 45911, 234, 171, 120, 223, 2515, 232, 17739, 225, 36365, 245, 30640, 33623, 27370, 171, 120, 253]
284
+
285
+ EncodingName: p50k_base
286
+ Sample: Hola, mundo! ¿Cómo estás hoy? 🇪🇸
287
+ Encoded: [39, 5708, 11, 27943, 78, 0, 1587, 123, 34, 10205, 5908, 1556, 40138, 289, 726, 30, 12520, 229, 103, 8582, 229, 116]
288
+
289
+ EncodingName: p50k_base
290
+ Sample: Привет, мир! Как дела?
291
+ Encoded: [140, 253, 21169, 18849, 38857, 16843, 20375, 11, 12466, 120, 18849, 21169, 0, 12466, 248, 16142, 31583, 12466, 112, 16843, 30143, 16142, 30]
292
+
293
+ EncodingName: p50k_base
294
+ Sample: 안녕하세요, 세상! 오늘 기분이 어때요? 🇰🇷
295
+ Encoded: [168, 243, 230, 167, 227, 243, 47991, 246, 168, 226, 116, 168, 248, 242, 11, 23821, 226, 116, 168, 225, 223, 0, 23821, 246, 97, 167, 232, 246, 220, 166, 116, 108, 167, 114, 226, 35975, 112, 23821, 244, 112, 167, 243, 234, 168, 248, 242, 30, 12520, 229, 108, 8582, 229, 115]
296
+
297
+ EncodingName: p50k_base
298
+ Sample: Bonjour, le monde ! Comment ça va aujourd'hui ? 🇫🇷
299
+ Encoded: [20682, 73, 454, 11, 443, 285, 14378, 5145, 18957, 6184, 100, 64, 46935, 257, 23577, 454, 67, 6, 71, 9019, 5633, 12520, 229, 104, 8582, 229, 115]
300
+
301
+ EncodingName: p50k_base
302
+ Sample: The quick brown fox jumps over 13 lazy dogs. 😺
303
+ Encoded: [464, 2068, 7586, 21831, 18045, 625, 1511, 16931, 6844, 13, 30325, 118]
304
+
305
+ EncodingName: p50k_base
306
+ Sample: 1234567890!@#$%^&*()-=_+[]{};:'",.<>?/|`~ 🎉
307
+ Encoded: [10163, 2231, 30924, 3829, 0, 31, 29953, 4, 61, 5, 9, 3419, 12, 28, 62, 10, 21737, 90, 19629, 32105, 1600, 29847, 29, 30, 14, 91, 63, 93, 12520, 236, 231]
308
+
309
+ EncodingName: p50k_base
310
+ Sample: C# is a great programming language for building apps.
311
+ Encoded: [34, 2, 318, 257, 1049, 8300, 3303, 329, 2615, 6725, 13]
312
+
313
+ EncodingName: p50k_base
314
+ Sample: El área de un triángulo es (base * altura) / 2.
315
+ Encoded: [9527, 6184, 94, 21468, 390, 555, 1333, 6557, 782, 43348, 1658, 357, 8692, 1635, 5988, 5330, 8, 1220, 362, 13]
316
+
317
+ EncodingName: p50k_base
318
+ Sample: Здравствуйте, это мой первый раз здесь. Что мне делать?
319
+ Encoded: [140, 245, 43666, 21169, 16142, 38857, 21727, 20375, 38857, 35072, 140, 117, 20375, 16843, 11, 220, 141, 235, 20375, 15166, 12466, 120, 25443, 117, 12466, 123, 16843, 21169, 38857, 45035, 140, 117, 220, 21169, 16142, 140, 115, 12466, 115, 43666, 16843, 21727, 45367, 13, 12466, 100, 20375, 15166, 12466, 120, 22177, 16843, 12466, 112, 16843, 30143, 16142, 20375, 45367, 30]
320
+
321
+ EncodingName: p50k_base
322
+ Sample: હેલો, વિશ્વ! તમે આજે કેમ છો? 🇮🇳
323
+ Encoded: [156, 103, 117, 156, 104, 229, 156, 103, 110, 156, 104, 233, 11, 220, 156, 103, 113, 156, 103, 123, 156, 103, 114, 156, 104, 235, 156, 103, 113, 0, 220, 156, 103, 97, 156, 103, 106, 156, 104, 229, 220, 156, 103, 228, 156, 103, 250, 156, 104, 229, 220, 156, 103, 243, 156, 104, 229, 156, 103, 106, 220, 156, 103, 249, 156, 104, 233, 30, 12520, 229, 106, 8582, 229, 111]
324
+
325
+ EncodingName: p50k_base
326
+ Sample: ความรักและการเป็นกันเองเป็นสิ่งสำคัญที่สุดในโลก 🇹🇭
327
+ Encoded: [19567, 226, 19567, 100, 19567, 110, 19567, 94, 19567, 96, 19567, 109, 19567, 223, 31479, 223, 19567, 98, 19567, 108, 19567, 223, 19567, 110, 19567, 96, 31479, 222, 19567, 249, 31479, 229, 19567, 247, 19567, 223, 19567, 109, 19567, 247, 31479, 222, 19567, 255, 19567, 229, 31479, 222, 19567, 249, 31479, 229, 19567, 247, 19567, 103, 19567, 112, 31479, 230, 19567, 229, 19567, 103, 19567, 111, 19567, 226, 19567, 109, 19567, 235, 19567, 245, 19567, 113, 31479, 230, 19567, 103, 19567, 116, 19567, 242, 31479, 225, 19567, 247, 31479, 224, 19567, 98, 19567, 223, 12520, 229, 117, 8582, 229, 255]
328
+
329
+ EncodingName: p50k_base
330
+ Sample: Python vs Java: Which programming language should you learn first?
331
+ Encoded: [37906, 3691, 7349, 25, 9022, 8300, 3303, 815, 345, 2193, 717, 30]
332
+
333
+ EncodingName: p50k_base
334
+ Sample: A journey of a thousand miles begins with a single step. - Lao Tzu
335
+ Encoded: [32, 7002, 286, 257, 7319, 4608, 6140, 351, 257, 2060, 2239, 13, 532, 4689, 78, 309, 27624]
336
+
337
+ EncodingName: p50k_base
338
+ Sample: Die Grenzen meiner Sprache bedeuten die Grenzen meiner Welt. 🇩🇪
339
+ Encoded: [32423, 19674, 4801, 502, 7274, 5522, 4891, 3996, 68, 7809, 4656, 19674, 4801, 502, 7274, 370, 2120, 13, 12520, 229, 102, 8582, 229, 103]
340
+
341
+ EncodingName: p50k_base
342
+ Sample: יש לי כמה שאלות בנוגע לפרויקט החדש שלך. 🇮🇱
343
+ Encoded: [33951, 102, 14360, 250, 25529, 14360, 249, 49168, 38269, 14360, 102, 42973, 40010, 27072, 42064, 14360, 239, 147, 254, 27072, 147, 240, 147, 95, 14360, 250, 147, 97, 37778, 27072, 33951, 100, 147, 246, 14360, 242, 147, 245, 147, 241, 50227, 14360, 102, 40010, 147, 248, 13, 12520, 229, 106, 8582, 229, 109]
344
+
345
+ EncodingName: p50k_base
346
+ Sample: Det är en vacker dag i Sverige. 🇸🇪
347
+ Encoded: [11242, 6184, 97, 81, 551, 410, 10735, 48924, 1312, 311, 332, 10045, 13, 12520, 229, 116, 8582, 229, 103]
348
+
349
+ EncodingName: p50k_base
350
+ Sample: A ∀ x (P(x) → Q(x)) ∧ (∃x P(x)) → ∃x Q(x)
351
+ Encoded: [32, 18872, 222, 2124, 357, 47, 7, 87, 8, 15168, 1195, 7, 87, 4008, 18872, 100, 357, 24861, 225, 87, 350, 7, 87, 4008, 15168, 18872, 225, 87, 1195, 7, 87, 8]
352
+
353
+ EncodingName: p50k_base
354
+ Sample: O Brasil é o maior país da América do Sul. 🇧🇷
355
+ Encoded: [46, 39452, 346, 38251, 267, 17266, 1504, 14187, 41200, 12379, 1703, 2634, 30997, 466, 29357, 13, 12520, 229, 100, 8582, 229, 115]
356
+
357
+ EncodingName: p50k_base
358
+ Sample: L'amore è una forza potente che unisce le persone. 🇮🇹
359
+ Encoded: [43, 6, 321, 382, 6184, 101, 555, 64, 329, 4496, 16739, 68, 1125, 555, 271, 344, 443, 2774, 505, 13, 12520, 229, 106, 8582, 229, 117]
360
+
361
+ EncodingName: p50k_base
362
+ Sample: Είναι μια ηλιόλουστη ημέρα στην Ελλάδα. 🇬🇷
363
+ Encoded: [138, 243, 138, 107, 26180, 17394, 29945, 18919, 29945, 17394, 7377, 115, 39377, 29945, 139, 234, 39377, 26517, 139, 227, 38392, 32830, 138, 115, 7377, 115, 34703, 138, 255, 33643, 17394, 18074, 225, 32830, 138, 115, 26180, 7377, 243, 39377, 39377, 138, 105, 138, 112, 17394, 13, 12520, 229, 105, 8582, 229, 115]
364
+
365
+ EncodingName: p50k_base
366
+ Sample: Teslim tarihi yaklaşıyor, projeyi zamanında bitirmemiz gerekiyor. 🇹🇷
367
+ Encoded: [36504, 2475, 256, 2743, 5303, 46251, 5031, 46481, 30102, 88, 273, 11, 386, 73, 2959, 72, 1976, 10546, 30102, 45658, 1643, 2533, 368, 528, 308, 567, 4106, 88, 273, 13, 12520, 229, 117, 8582, 229, 115]
368
+
369
+ EncodingName: p50k_base
370
+ Sample: Det finnes ingen bedre tid enn nå for å starte noe nytt. 🇳🇴
371
+ Encoded: [11242, 957, 2516, 27016, 3996, 260, 29770, 551, 77, 299, 29090, 329, 6184, 98, 923, 68, 645, 68, 299, 88, 926, 13, 12520, 229, 111, 8582, 229, 112]
372
+
373
+ EncodingName: p50k_base
374
+ Sample: Aanvaard de uitdagingen van het leven met moed en vastberadenheid. 🇳🇱
375
+ Encoded: [32, 272, 6862, 446, 390, 334, 270, 67, 3039, 268, 5719, 339, 83, 443, 574, 1138, 6941, 276, 551, 5909, 527, 40780, 28420, 13, 12520, 229, 111, 8582, 229, 109]
376
+
377
+ EncodingName: p50k_base
378
+ Sample: Chào mừng bạn đến với thế giới của lập trình. 🇻🇳
379
+ Encoded: [1925, 24247, 78, 285, 157, 119, 104, 782, 275, 157, 118, 94, 77, 34754, 239, 157, 118, 123, 77, 410, 157, 119, 249, 72, 294, 157, 118, 123, 308, 72, 157, 119, 249, 72, 269, 157, 119, 100, 64, 300, 157, 118, 255, 79, 491, 127, 105, 77, 71, 13, 12520, 229, 119, 8582, 229, 111]
380
+
381
+ EncodingName: p50k_base
382
+ Sample: Dlaczego warto uczyć się języków obcych? 🇵🇱
383
+ Encoded: [35, 75, 330, 89, 1533, 78, 32943, 78, 334, 66, 7357, 38325, 33721, 128, 247, 474, 128, 247, 46355, 10205, 86, 909, 948, 354, 30, 12520, 229, 113, 8582, 229, 109]
384
+
385
+ EncodingName: p50k_base
386
+ Sample: E = mc², uma equação famosa na física. 🇵🇹
387
+ Encoded: [36, 796, 36650, 31185, 11, 334, 2611, 1602, 64, 16175, 28749, 1145, 8546, 12385, 277, 41200, 3970, 13, 12520, 229, 113, 8582, 229, 117]
388
+
389
+ EncodingName: p50k_base
390
+ Sample: 你今天遇到什么有趣的事情了吗?🇨🇳
391
+ Encoded: [19526, 254, 20015, 232, 25465, 34402, 229, 26344, 108, 20015, 222, 20046, 230, 17312, 231, 164, 114, 96, 21410, 12859, 233, 46349, 227, 12859, 228, 28938, 245, 171, 120, 253, 8582, 229, 101, 8582, 229, 111]
392
+
393
+ EncodingName: p50k_base
394
+ Sample: Nå er det tid for å feire med familie og venner. 🇳🇴
395
+ Encoded: [45, 29090, 1931, 1062, 29770, 329, 6184, 98, 730, 557, 1117, 1145, 346, 494, 267, 70, 8710, 1008, 13, 12520, 229, 111, 8582, 229, 112]
396
+
397
+ EncodingName: p50k_base
398
+ Sample: Þetta er góður dagur til að læra eitthvað nýtt. 🇮🇸
399
+ Encoded: [127, 252, 15253, 1931, 308, 10205, 27214, 333, 48924, 333, 21502, 257, 27214, 300, 21241, 430, 304, 270, 400, 6862, 27214, 299, 127, 121, 926, 13, 12520, 229, 106, 8582, 229, 116]
400
+
401
+ EncodingName: p50k_base
402
+ Sample: გამარჯობა! როგორ ხართ დღეს? 🇬🇪
403
+ Encoded: [157, 225, 240, 157, 225, 238, 157, 225, 249, 157, 225, 238, 157, 225, 254, 157, 225, 107, 157, 225, 251, 157, 225, 239, 157, 225, 238, 0, 28053, 225, 254, 157, 225, 251, 157, 225, 240, 157, 225, 251, 157, 225, 254, 28053, 225, 106, 157, 225, 238, 157, 225, 254, 157, 225, 245, 28053, 225, 241, 157, 225, 99, 157, 225, 242, 157, 225, 94, 30, 12520, 229, 105, 8582, 229, 103]
404
+
405
+ EncodingName: p50k_base
406
+ Sample: Mā te whakawhiti kōrero e whai hua ai tātou. 🇳🇿
407
+ Encoded: [44, 10235, 573, 348, 461, 707, 71, 8846, 479, 13090, 34785, 304, 348, 1872, 289, 6413, 257, 72, 256, 10235, 83, 280, 13, 12520, 229, 111, 8582, 229, 123]
408
+
409
+ EncodingName: p50k_base
410
+ Sample: Это был незабываемый опыт, который я буду помнить всегда.
411
+ Encoded: [140, 255, 20375, 15166, 12466, 109, 45035, 30143, 12466, 121, 16843, 140, 115, 16142, 140, 109, 45035, 38857, 16142, 16843, 43108, 45035, 140, 117, 12466, 122, 140, 123, 45035, 20375, 11, 12466, 118, 15166, 20375, 15166, 21169, 45035, 140, 117, 220, 40623, 12466, 109, 35072, 43666, 35072, 12466, 123, 25443, 120, 22177, 18849, 20375, 45367, 12466, 110, 21727, 16843, 140, 111, 43666, 16142, 13]
412
+
413
+ EncodingName: p50k_base
414
+ Sample: Διαβάζοντας βιβλία, εμπλουτίζουμε τον εαυτό μας με γνώσεις.
415
+ Encoded: [138, 242, 29945, 17394, 26638, 138, 105, 138, 114, 26517, 26180, 32830, 17394, 35558, 27169, 29945, 26638, 39377, 138, 107, 17394, 11, 7377, 113, 34703, 46582, 39377, 26517, 139, 227, 32830, 138, 107, 138, 114, 26517, 139, 227, 34703, 30950, 46651, 26517, 26180, 7377, 113, 17394, 139, 227, 32830, 139, 234, 18919, 17394, 35558, 18919, 30950, 7377, 111, 26180, 139, 236, 38392, 30950, 29945, 35558, 13]
416
+
417
+ EncodingName: p50k_base
418
+ Sample: A számítástechnika világa tele van izgalmas lehetőségekkel. 🇭🇺
419
+ Encoded: [32, 264, 89, 6557, 76, 8836, 83, 6557, 4169, 1349, 9232, 39796, 6557, 4908, 5735, 5719, 220, 528, 13528, 5356, 443, 3202, 129, 239, 82, 2634, 469, 74, 7750, 13, 12520, 229, 255, 8582, 229, 118]
420
+
421
+ EncodingName: p50k_base
422
+ Sample: Vždy je dobré mít plán B, pokud něco nevyjde. 🇨🇿
423
+ Encoded: [53, 129, 122, 9892, 11223, 466, 1671, 2634, 285, 8836, 83, 458, 21162, 347, 11, 279, 482, 463, 299, 128, 249, 1073, 497, 7670, 73, 2934, 13, 12520, 229, 101, 8582, 229, 123]
424
+
425
+ EncodingName: p50k_base
426
+ Sample: Dragostea e un sentiment minunat care ne unește pe toți. 🇷🇴
427
+ Encoded: [46022, 455, 18213, 304, 555, 15598, 949, 403, 265, 1337, 497, 17809, 132, 247, 660, 613, 284, 132, 249, 72, 13, 12520, 229, 115, 8582, 229, 112]
428
+
429
+ EncodingName: p50k_base
430
+ Sample: دیکھو، آسمان میں کتنی تارے ہیں! 🇵🇰
431
+ Encoded: [38843, 151, 234, 150, 102, 150, 122, 30335, 148, 234, 17550, 95, 45692, 25405, 12919, 23338, 47048, 151, 234, 150, 118, 220, 150, 102, 41486, 23338, 151, 234, 17550, 103, 12919, 26897, 151, 240, 220, 151, 223, 151, 234, 150, 118, 0, 12520, 229, 113, 8582, 229, 108]
432
+
433
+ EncodingName: p50k_base
434
+ Sample: Nenda polepole na ujifunze kila siku. 🇹🇿
435
+ Encoded: [45, 7438, 16825, 36869, 12385, 334, 73, 361, 403, 2736, 8769, 64, 264, 28643, 13, 12520, 229, 117, 8582, 229, 123]
436
+
437
+ EncodingName: p50k_base
438
+ Sample: Каква е твоята любима храна? 🇧🇬
439
+ Encoded: [140, 248, 16142, 31583, 38857, 16142, 12466, 113, 220, 20375, 38857, 15166, 40623, 20375, 16142, 12466, 119, 141, 236, 140, 109, 18849, 43108, 16142, 220, 141, 227, 21169, 16142, 22177, 16142, 30, 12520, 229, 100, 8582, 229, 105]
440
+
441
+ EncodingName: p50k_base
442
+ Sample: Sträva alltid efter att bli en bättre version av dig själv.
443
+ Encoded: [13290, 11033, 6862, 477, 83, 312, 304, 637, 708, 698, 72, 551, 275, 11033, 926, 260, 2196, 1196, 3100, 264, 73, 11033, 6780, 13]
444
+
445
+ EncodingName: p50k_base
446
+ Sample: Філософія - це наука про знання. 🇺🇦
447
+ Encoded: [140, 97, 141, 244, 30143, 15166, 21727, 15166, 141, 226, 141, 244, 40623, 532, 220, 141, 228, 16843, 12466, 121, 16142, 35072, 31583, 16142, 12466, 123, 21169, 15166, 12466, 115, 22177, 16142, 22177, 22177, 40623, 13, 12520, 229, 118, 8582, 229, 99]
448
+
449
+ EncodingName: p50k_base
450
+ Sample: Το πρόγραμμα αυτό είναι πολύ ενδιαφέρον. 🇬🇷
451
+ Encoded: [138, 97, 26517, 18074, 222, 33643, 139, 234, 42063, 33643, 17394, 34703, 34703, 17394, 26367, 139, 227, 32830, 139, 234, 7377, 113, 138, 107, 26180, 17394, 29945, 18074, 222, 26517, 39377, 139, 235, 7377, 113, 26180, 138, 112, 29945, 17394, 139, 228, 138, 255, 33643, 26517, 26180, 13, 12520, 229, 105, 8582, 229, 115]
452
+
453
+ EncodingName: p50k_base
454
+ Sample: ^$%#*@!&)(_+=}{|:;"?><,~`'-./][
455
+ Encoded: [61, 3, 4, 2, 9, 31, 0, 5, 5769, 62, 47932, 18477, 91, 25, 26, 13984, 6927, 11, 93, 63, 29001, 19571, 7131]
456
+
457
+ EncodingName: p50k_base
458
+ Sample: 4gH@!0sT*#(9^%$[x{}j+|Yz6;Q]~8
459
+ Encoded: [19, 70, 39, 31, 0, 15, 82, 51, 9, 2, 7, 24, 61, 4, 3, 58, 87, 90, 92, 73, 10, 91, 56, 89, 21, 26, 48, 60, 93, 23]
460
+
461
+ EncodingName: p50k_base
462
+ Sample: wNb)I<>#:i^P]*cR8ytUx1Q`6O@z/
463
+ Encoded: [86, 45, 65, 8, 40, 27, 29, 2, 25, 72, 61, 47, 60, 9, 66, 49, 23, 20760, 52, 87, 16, 48, 63, 21, 46, 31, 89, 14]
464
+
465
+ EncodingName: p50k_base
466
+ Sample: ÄÜö¿¡¢£¤¥¦§¨©ª«¬®¯°±²³´µ¶·¸¹º»¼½¾¿
467
+ Encoded: [127, 226, 127, 250, 9101, 126, 123, 126, 94, 44359, 14988, 126, 97, 126, 98, 126, 99, 16273, 37102, 16224, 126, 103, 24328, 126, 105, 7461, 5196, 7200, 22519, 31185, 126, 111, 18265, 126, 113, 26604, 9129, 126, 116, 126, 117, 36165, 17730, 126, 120, 23141, 126, 122, 126, 123]
468
+
469
+ EncodingName: p50k_base
470
+ Sample: ƒšŠŒŽƒšŠŒŽƒšŠŒŽƒšŠŒŽƒšŠŒŽƒšŠŒŽ
471
+ Encoded: [130, 240, 32790, 129, 254, 129, 240, 129, 121, 130, 240, 32790, 129, 254, 129, 240, 129, 121, 130, 240, 32790, 129, 254, 129, 240, 129, 121, 130, 240, 32790, 129, 254, 129, 240, 129, 121, 130, 240, 32790, 129, 254, 129, 240, 129, 121, 130, 240, 32790, 129, 254, 129, 240, 129, 121]
472
+
473
+ EncodingName: p50k_base
474
+ Sample: 5ħÅŸēýïūē$%#^*()_+{[ö&!@#?>|,.<>
475
+ Encoded: [20, 128, 100, 127, 227, 129, 116, 27092, 127, 121, 26884, 20317, 27092, 3, 4, 2, 61, 9, 3419, 62, 10, 90, 58, 9101, 5, 0, 41573, 30, 29, 91, 11, 29847, 29]
476
+
477
+ EncodingName: p50k_base
478
+ Sample: 1B4t#%&*()_+dF5g^hJk7LmN0pQrS<>?
479
+ Encoded: [16, 33, 19, 83, 2, 4, 5, 9, 3419, 62, 10, 67, 37, 20, 70, 61, 71, 41, 74, 22, 43, 76, 45, 15, 79, 48, 81, 50, 27, 29, 30]
480
+
481
+ EncodingName: p50k_base
482
+ Sample: ¬§±²³µ¶·¹ºª«»¦©¯°±!@#$%^&*()_+
483
+ Encoded: [126, 105, 16273, 22519, 31185, 126, 111, 126, 113, 26604, 9129, 126, 117, 36165, 126, 103, 24328, 17730, 126, 99, 16224, 5196, 7200, 22519, 0, 31, 29953, 4, 61, 5, 9, 3419, 62, 10]
484
+
485
+ EncodingName: p50k_base
486
+ Sample: 8mR5*w7^a$!F(0%#J9@X6vZ1)nU3]_Y/
487
+ Encoded: [23, 76, 49, 20, 9, 86, 22, 61, 64, 3, 0, 37, 7, 15, 4, 2, 41, 24, 31, 55, 21, 85, 57, 16, 8, 77, 52, 18, 60, 62, 56, 14]
488
+
489
+ EncodingName: p50k_base
490
+ Sample: 😊😀😁😂🤣😃😄😅😆😉😊😋😎😍😘😗😙😚☺️🙂🤗🤔
491
+ Encoded: [47249, 232, 47249, 222, 47249, 223, 47249, 224, 8582, 97, 96, 47249, 225, 47249, 226, 8582, 11805, 47249, 228, 47249, 231, 47249, 232, 47249, 233, 47249, 236, 47249, 235, 47249, 246, 47249, 245, 47249, 247, 47249, 248, 24583, 118, 37929, 8582, 25081, 8582, 97, 245, 8582, 97, 242]
492
+
493
+ EncodingName: p50k_base
494
+ Sample: 🤨😐😑😶🙄😏😣😥😮🤐😯😪😫😴😌🤓😛😜😝🤤
495
+ Encoded: [8582, 97, 101, 47249, 238, 47249, 239, 47249, 114, 8582, 247, 226, 47249, 237, 47249, 96, 47249, 98, 47249, 106, 8582, 97, 238, 47249, 107, 47249, 103, 47249, 104, 47249, 112, 47249, 234, 8582, 97, 241, 47249, 249, 47249, 250, 47249, 251, 8582, 97, 97]
496
+
497
+ EncodingName: p50k_base
498
+ Sample: 😒😓😔😕🙃🤑😲😷🤒🤕🤢🤧😈👿👹👺💀☠️
499
+ Encoded: [47249, 240, 47249, 241, 47249, 242, 47249, 243, 8582, 247, 225, 8582, 97, 239, 47249, 110, 47249, 115, 8582, 97, 240, 8582, 97, 243, 8582, 97, 95, 8582, 97, 100, 47249, 230, 41840, 123, 41840, 117, 41840, 118, 8582, 240, 222, 24583, 254, 37929]
500
+
501
+ EncodingName: p50k_base
502
+ Sample: 😾😿🙀😽😼😻🙈🙉🙊👶👦👧👨👩👴👵👨‍⚕️👩‍⚕️
503
+ Encoded: [47249, 122, 47249, 123, 8582, 247, 222, 47249, 121, 47249, 120, 47249, 119, 8582, 247, 230, 8582, 247, 231, 8582, 247, 232, 41840, 114, 41840, 99, 41840, 100, 41840, 101, 41840, 102, 41840, 112, 41840, 113, 41840, 101, 447, 235, 158, 248, 243, 37929, 41840, 102, 447, 235, 158, 248, 243, 37929]
504
+
505
+ EncodingName: p50k_base
506
+ Sample: 🌞🌝🌚🌛🌜🌙⭐️🌟💫✨🔥💥☄️🌈☀️🌤️⛅️🌥️
507
+ Encoded: [8582, 234, 252, 8582, 234, 251, 8582, 234, 248, 8582, 234, 249, 8582, 234, 250, 8582, 234, 247, 158, 255, 238, 37929, 8582, 234, 253, 8582, 240, 104, 26486, 101, 8582, 242, 98, 8582, 240, 98, 24583, 226, 37929, 8582, 234, 230, 24583, 222, 37929, 8582, 234, 97, 37929, 158, 249, 227, 37929, 8582, 234, 98, 37929]
508
+
509
+ EncodingName: p50k_base
510
+ Sample: 🍏🍎🍐🍊🍋🍌🍉🍇🍓🍈🍒🍑
511
+ Encoded: [8582, 235, 237, 8582, 235, 236, 8582, 235, 238, 8582, 235, 232, 8582, 235, 233, 8582, 235, 234, 8582, 235, 231, 8582, 235, 229, 8582, 235, 241, 8582, 235, 230, 8582, 235, 240, 8582, 235, 239]
512
+
513
+ EncodingName: p50k_edit
514
+ Sample:
515
+ Encoded: []
516
+
517
+ EncodingName: p50k_edit
518
+ Sample: a
519
+ Encoded: [64]
520
+
521
+ EncodingName: p50k_edit
522
+ Sample: 1
523
+ Encoded: [16]
524
+
525
+ EncodingName: p50k_edit
526
+ Sample: a a
527
+ Encoded: [64, 257]
528
+
529
+ EncodingName: p50k_edit
530
+ Sample: hello
531
+ Encoded: [31373]
532
+
533
+ EncodingName: p50k_edit
534
+ Sample: Hello, World! How are you today? 🌍
535
+ Encoded: [15496, 11, 2159, 0, 1374, 389, 345, 1909, 30, 12520, 234, 235]
536
+
537
+ EncodingName: p50k_edit
538
+ Sample: こんにちは、世界!お元気ですか?
539
+ Encoded: [46036, 22174, 28618, 2515, 94, 31676, 23513, 10310, 244, 45911, 234, 171, 120, 223, 2515, 232, 17739, 225, 36365, 245, 30640, 33623, 27370, 171, 120, 253]
540
+
541
+ EncodingName: p50k_edit
542
+ Sample: Hola, mundo! ¿Cómo estás hoy? 🇪🇸
543
+ Encoded: [39, 5708, 11, 27943, 78, 0, 1587, 123, 34, 10205, 5908, 1556, 40138, 289, 726, 30, 12520, 229, 103, 8582, 229, 116]
544
+
545
+ EncodingName: p50k_edit
546
+ Sample: Привет, мир! Как дела?
547
+ Encoded: [140, 253, 21169, 18849, 38857, 16843, 20375, 11, 12466, 120, 18849, 21169, 0, 12466, 248, 16142, 31583, 12466, 112, 16843, 30143, 16142, 30]
548
+
549
+ EncodingName: p50k_edit
550
+ Sample: 안녕하세요, 세상! 오늘 기분이 어때요? 🇰🇷
551
+ Encoded: [168, 243, 230, 167, 227, 243, 47991, 246, 168, 226, 116, 168, 248, 242, 11, 23821, 226, 116, 168, 225, 223, 0, 23821, 246, 97, 167, 232, 246, 220, 166, 116, 108, 167, 114, 226, 35975, 112, 23821, 244, 112, 167, 243, 234, 168, 248, 242, 30, 12520, 229, 108, 8582, 229, 115]
552
+
553
+ EncodingName: p50k_edit
554
+ Sample: Bonjour, le monde ! Comment ça va aujourd'hui ? 🇫🇷
555
+ Encoded: [20682, 73, 454, 11, 443, 285, 14378, 5145, 18957, 6184, 100, 64, 46935, 257, 23577, 454, 67, 6, 71, 9019, 5633, 12520, 229, 104, 8582, 229, 115]
556
+
557
+ EncodingName: p50k_edit
558
+ Sample: The quick brown fox jumps over 13 lazy dogs. 😺
559
+ Encoded: [464, 2068, 7586, 21831, 18045, 625, 1511, 16931, 6844, 13, 30325, 118]
560
+
561
+ EncodingName: p50k_edit
562
+ Sample: 1234567890!@#$%^&*()-=_+[]{};:'",.<>?/|`~ 🎉
563
+ Encoded: [10163, 2231, 30924, 3829, 0, 31, 29953, 4, 61, 5, 9, 3419, 12, 28, 62, 10, 21737, 90, 19629, 32105, 1600, 29847, 29, 30, 14, 91, 63, 93, 12520, 236, 231]
564
+
565
+ EncodingName: p50k_edit
566
+ Sample: C# is a great programming language for building apps.
567
+ Encoded: [34, 2, 318, 257, 1049, 8300, 3303, 329, 2615, 6725, 13]
568
+
569
+ EncodingName: p50k_edit
570
+ Sample: El área de un triángulo es (base * altura) / 2.
571
+ Encoded: [9527, 6184, 94, 21468, 390, 555, 1333, 6557, 782, 43348, 1658, 357, 8692, 1635, 5988, 5330, 8, 1220, 362, 13]
572
+
573
+ EncodingName: p50k_edit
574
+ Sample: Здравствуйте, это мой первый раз здесь. Что мне делать?
575
+ Encoded: [140, 245, 43666, 21169, 16142, 38857, 21727, 20375, 38857, 35072, 140, 117, 20375, 16843, 11, 220, 141, 235, 20375, 15166, 12466, 120, 25443, 117, 12466, 123, 16843, 21169, 38857, 45035, 140, 117, 220, 21169, 16142, 140, 115, 12466, 115, 43666, 16843, 21727, 45367, 13, 12466, 100, 20375, 15166, 12466, 120, 22177, 16843, 12466, 112, 16843, 30143, 16142, 20375, 45367, 30]
576
+
577
+ EncodingName: p50k_edit
578
+ Sample: હેલો, વિશ્વ! તમે આજે કેમ છો? 🇮🇳
579
+ Encoded: [156, 103, 117, 156, 104, 229, 156, 103, 110, 156, 104, 233, 11, 220, 156, 103, 113, 156, 103, 123, 156, 103, 114, 156, 104, 235, 156, 103, 113, 0, 220, 156, 103, 97, 156, 103, 106, 156, 104, 229, 220, 156, 103, 228, 156, 103, 250, 156, 104, 229, 220, 156, 103, 243, 156, 104, 229, 156, 103, 106, 220, 156, 103, 249, 156, 104, 233, 30, 12520, 229, 106, 8582, 229, 111]
580
+
581
+ EncodingName: p50k_edit
582
+ Sample: ความรักและการเป็นกันเองเป็นสิ่งสำคัญที่สุดในโลก 🇹🇭
583
+ Encoded: [19567, 226, 19567, 100, 19567, 110, 19567, 94, 19567, 96, 19567, 109, 19567, 223, 31479, 223, 19567, 98, 19567, 108, 19567, 223, 19567, 110, 19567, 96, 31479, 222, 19567, 249, 31479, 229, 19567, 247, 19567, 223, 19567, 109, 19567, 247, 31479, 222, 19567, 255, 19567, 229, 31479, 222, 19567, 249, 31479, 229, 19567, 247, 19567, 103, 19567, 112, 31479, 230, 19567, 229, 19567, 103, 19567, 111, 19567, 226, 19567, 109, 19567, 235, 19567, 245, 19567, 113, 31479, 230, 19567, 103, 19567, 116, 19567, 242, 31479, 225, 19567, 247, 31479, 224, 19567, 98, 19567, 223, 12520, 229, 117, 8582, 229, 255]
584
+
585
+ EncodingName: p50k_edit
586
+ Sample: Python vs Java: Which programming language should you learn first?
587
+ Encoded: [37906, 3691, 7349, 25, 9022, 8300, 3303, 815, 345, 2193, 717, 30]
588
+
589
+ EncodingName: p50k_edit
590
+ Sample: A journey of a thousand miles begins with a single step. - Lao Tzu
591
+ Encoded: [32, 7002, 286, 257, 7319, 4608, 6140, 351, 257, 2060, 2239, 13, 532, 4689, 78, 309, 27624]
592
+
593
+ EncodingName: p50k_edit
594
+ Sample: Die Grenzen meiner Sprache bedeuten die Grenzen meiner Welt. 🇩🇪
595
+ Encoded: [32423, 19674, 4801, 502, 7274, 5522, 4891, 3996, 68, 7809, 4656, 19674, 4801, 502, 7274, 370, 2120, 13, 12520, 229, 102, 8582, 229, 103]
596
+
597
+ EncodingName: p50k_edit
598
+ Sample: יש לי כמה שאלות בנוגע לפרויקט החדש שלך. 🇮🇱
599
+ Encoded: [33951, 102, 14360, 250, 25529, 14360, 249, 49168, 38269, 14360, 102, 42973, 40010, 27072, 42064, 14360, 239, 147, 254, 27072, 147, 240, 147, 95, 14360, 250, 147, 97, 37778, 27072, 33951, 100, 147, 246, 14360, 242, 147, 245, 147, 241, 50227, 14360, 102, 40010, 147, 248, 13, 12520, 229, 106, 8582, 229, 109]
600
+
601
+ EncodingName: p50k_edit
602
+ Sample: Det är en vacker dag i Sverige. 🇸🇪
603
+ Encoded: [11242, 6184, 97, 81, 551, 410, 10735, 48924, 1312, 311, 332, 10045, 13, 12520, 229, 116, 8582, 229, 103]
604
+
605
+ EncodingName: p50k_edit
606
+ Sample: A ∀ x (P(x) → Q(x)) ∧ (∃x P(x)) → ∃x Q(x)
607
+ Encoded: [32, 18872, 222, 2124, 357, 47, 7, 87, 8, 15168, 1195, 7, 87, 4008, 18872, 100, 357, 24861, 225, 87, 350, 7, 87, 4008, 15168, 18872, 225, 87, 1195, 7, 87, 8]
608
+
609
+ EncodingName: p50k_edit
610
+ Sample: O Brasil é o maior país da América do Sul. 🇧🇷
611
+ Encoded: [46, 39452, 346, 38251, 267, 17266, 1504, 14187, 41200, 12379, 1703, 2634, 30997, 466, 29357, 13, 12520, 229, 100, 8582, 229, 115]
612
+
613
+ EncodingName: p50k_edit
614
+ Sample: L'amore è una forza potente che unisce le persone. 🇮🇹
615
+ Encoded: [43, 6, 321, 382, 6184, 101, 555, 64, 329, 4496, 16739, 68, 1125, 555, 271, 344, 443, 2774, 505, 13, 12520, 229, 106, 8582, 229, 117]
616
+
617
+ EncodingName: p50k_edit
618
+ Sample: Είναι μια ηλιόλουστη ημέρα στην Ελλάδα. 🇬🇷
619
+ Encoded: [138, 243, 138, 107, 26180, 17394, 29945, 18919, 29945, 17394, 7377, 115, 39377, 29945, 139, 234, 39377, 26517, 139, 227, 38392, 32830, 138, 115, 7377, 115, 34703, 138, 255, 33643, 17394, 18074, 225, 32830, 138, 115, 26180, 7377, 243, 39377, 39377, 138, 105, 138, 112, 17394, 13, 12520, 229, 105, 8582, 229, 115]
620
+
621
+ EncodingName: p50k_edit
622
+ Sample: Teslim tarihi yaklaşıyor, projeyi zamanında bitirmemiz gerekiyor. 🇹🇷
623
+ Encoded: [36504, 2475, 256, 2743, 5303, 46251, 5031, 46481, 30102, 88, 273, 11, 386, 73, 2959, 72, 1976, 10546, 30102, 45658, 1643, 2533, 368, 528, 308, 567, 4106, 88, 273, 13, 12520, 229, 117, 8582, 229, 115]
624
+
625
+ EncodingName: p50k_edit
626
+ Sample: Det finnes ingen bedre tid enn nå for å starte noe nytt. 🇳🇴
627
+ Encoded: [11242, 957, 2516, 27016, 3996, 260, 29770, 551, 77, 299, 29090, 329, 6184, 98, 923, 68, 645, 68, 299, 88, 926, 13, 12520, 229, 111, 8582, 229, 112]
628
+
629
+ EncodingName: p50k_edit
630
+ Sample: Aanvaard de uitdagingen van het leven met moed en vastberadenheid. 🇳🇱
631
+ Encoded: [32, 272, 6862, 446, 390, 334, 270, 67, 3039, 268, 5719, 339, 83, 443, 574, 1138, 6941, 276, 551, 5909, 527, 40780, 28420, 13, 12520, 229, 111, 8582, 229, 109]
632
+
633
+ EncodingName: p50k_edit
634
+ Sample: Chào mừng bạn đến với thế giới của lập trình. 🇻🇳
635
+ Encoded: [1925, 24247, 78, 285, 157, 119, 104, 782, 275, 157, 118, 94, 77, 34754, 239, 157, 118, 123, 77, 410, 157, 119, 249, 72, 294, 157, 118, 123, 308, 72, 157, 119, 249, 72, 269, 157, 119, 100, 64, 300, 157, 118, 255, 79, 491, 127, 105, 77, 71, 13, 12520, 229, 119, 8582, 229, 111]
636
+
637
+ EncodingName: p50k_edit
638
+ Sample: Dlaczego warto uczyć się języków obcych? 🇵🇱
639
+ Encoded: [35, 75, 330, 89, 1533, 78, 32943, 78, 334, 66, 7357, 38325, 33721, 128, 247, 474, 128, 247, 46355, 10205, 86, 909, 948, 354, 30, 12520, 229, 113, 8582, 229, 109]
640
+
641
+ EncodingName: p50k_edit
642
+ Sample: E = mc², uma equação famosa na física. 🇵🇹
643
+ Encoded: [36, 796, 36650, 31185, 11, 334, 2611, 1602, 64, 16175, 28749, 1145, 8546, 12385, 277, 41200, 3970, 13, 12520, 229, 113, 8582, 229, 117]
644
+
645
+ EncodingName: p50k_edit
646
+ Sample: 你今天遇到什么有趣的事情了吗?🇨🇳
647
+ Encoded: [19526, 254, 20015, 232, 25465, 34402, 229, 26344, 108, 20015, 222, 20046, 230, 17312, 231, 164, 114, 96, 21410, 12859, 233, 46349, 227, 12859, 228, 28938, 245, 171, 120, 253, 8582, 229, 101, 8582, 229, 111]
648
+
649
+ EncodingName: p50k_edit
650
+ Sample: Nå er det tid for å feire med familie og venner. 🇳🇴
651
+ Encoded: [45, 29090, 1931, 1062, 29770, 329, 6184, 98, 730, 557, 1117, 1145, 346, 494, 267, 70, 8710, 1008, 13, 12520, 229, 111, 8582, 229, 112]
652
+
653
+ EncodingName: p50k_edit
654
+ Sample: Þetta er góður dagur til að læra eitthvað nýtt. 🇮🇸
655
+ Encoded: [127, 252, 15253, 1931, 308, 10205, 27214, 333, 48924, 333, 21502, 257, 27214, 300, 21241, 430, 304, 270, 400, 6862, 27214, 299, 127, 121, 926, 13, 12520, 229, 106, 8582, 229, 116]
656
+
657
+ EncodingName: p50k_edit
658
+ Sample: გამარჯობა! როგორ ხართ დღეს? 🇬🇪
659
+ Encoded: [157, 225, 240, 157, 225, 238, 157, 225, 249, 157, 225, 238, 157, 225, 254, 157, 225, 107, 157, 225, 251, 157, 225, 239, 157, 225, 238, 0, 28053, 225, 254, 157, 225, 251, 157, 225, 240, 157, 225, 251, 157, 225, 254, 28053, 225, 106, 157, 225, 238, 157, 225, 254, 157, 225, 245, 28053, 225, 241, 157, 225, 99, 157, 225, 242, 157, 225, 94, 30, 12520, 229, 105, 8582, 229, 103]
660
+
661
+ EncodingName: p50k_edit
662
+ Sample: Mā te whakawhiti kōrero e whai hua ai tātou. 🇳🇿
663
+ Encoded: [44, 10235, 573, 348, 461, 707, 71, 8846, 479, 13090, 34785, 304, 348, 1872, 289, 6413, 257, 72, 256, 10235, 83, 280, 13, 12520, 229, 111, 8582, 229, 123]
664
+
665
+ EncodingName: p50k_edit
666
+ Sample: Это был незабываемый опыт, который я буду помнить всегда.
667
+ Encoded: [140, 255, 20375, 15166, 12466, 109, 45035, 30143, 12466, 121, 16843, 140, 115, 16142, 140, 109, 45035, 38857, 16142, 16843, 43108, 45035, 140, 117, 12466, 122, 140, 123, 45035, 20375, 11, 12466, 118, 15166, 20375, 15166, 21169, 45035, 140, 117, 220, 40623, 12466, 109, 35072, 43666, 35072, 12466, 123, 25443, 120, 22177, 18849, 20375, 45367, 12466, 110, 21727, 16843, 140, 111, 43666, 16142, 13]
668
+
669
+ EncodingName: p50k_edit
670
+ Sample: Διαβάζοντας βιβλία, εμπλουτίζουμε τον εαυτό μας με γνώσεις.
671
+ Encoded: [138, 242, 29945, 17394, 26638, 138, 105, 138, 114, 26517, 26180, 32830, 17394, 35558, 27169, 29945, 26638, 39377, 138, 107, 17394, 11, 7377, 113, 34703, 46582, 39377, 26517, 139, 227, 32830, 138, 107, 138, 114, 26517, 139, 227, 34703, 30950, 46651, 26517, 26180, 7377, 113, 17394, 139, 227, 32830, 139, 234, 18919, 17394, 35558, 18919, 30950, 7377, 111, 26180, 139, 236, 38392, 30950, 29945, 35558, 13]
672
+
673
+ EncodingName: p50k_edit
674
+ Sample: A számítástechnika világa tele van izgalmas lehetőségekkel. 🇭🇺
675
+ Encoded: [32, 264, 89, 6557, 76, 8836, 83, 6557, 4169, 1349, 9232, 39796, 6557, 4908, 5735, 5719, 220, 528, 13528, 5356, 443, 3202, 129, 239, 82, 2634, 469, 74, 7750, 13, 12520, 229, 255, 8582, 229, 118]
676
+
677
+ EncodingName: p50k_edit
678
+ Sample: Vždy je dobré mít plán B, pokud něco nevyjde. 🇨🇿
679
+ Encoded: [53, 129, 122, 9892, 11223, 466, 1671, 2634, 285, 8836, 83, 458, 21162, 347, 11, 279, 482, 463, 299, 128, 249, 1073, 497, 7670, 73, 2934, 13, 12520, 229, 101, 8582, 229, 123]
680
+
681
+ EncodingName: p50k_edit
682
+ Sample: Dragostea e un sentiment minunat care ne unește pe toți. 🇷🇴
683
+ Encoded: [46022, 455, 18213, 304, 555, 15598, 949, 403, 265, 1337, 497, 17809, 132, 247, 660, 613, 284, 132, 249, 72, 13, 12520, 229, 115, 8582, 229, 112]
684
+
685
+ EncodingName: p50k_edit
686
+ Sample: دیکھو، آسمان میں کتنی تارے ہیں! 🇵🇰
687
+ Encoded: [38843, 151, 234, 150, 102, 150, 122, 30335, 148, 234, 17550, 95, 45692, 25405, 12919, 23338, 47048, 151, 234, 150, 118, 220, 150, 102, 41486, 23338, 151, 234, 17550, 103, 12919, 26897, 151, 240, 220, 151, 223, 151, 234, 150, 118, 0, 12520, 229, 113, 8582, 229, 108]
688
+
689
+ EncodingName: p50k_edit
690
+ Sample: Nenda polepole na ujifunze kila siku. 🇹🇿
691
+ Encoded: [45, 7438, 16825, 36869, 12385, 334, 73, 361, 403, 2736, 8769, 64, 264, 28643, 13, 12520, 229, 117, 8582, 229, 123]
692
+
693
+ EncodingName: p50k_edit
694
+ Sample: Каква е твоята любима храна? 🇧🇬
695
+ Encoded: [140, 248, 16142, 31583, 38857, 16142, 12466, 113, 220, 20375, 38857, 15166, 40623, 20375, 16142, 12466, 119, 141, 236, 140, 109, 18849, 43108, 16142, 220, 141, 227, 21169, 16142, 22177, 16142, 30, 12520, 229, 100, 8582, 229, 105]
696
+
697
+ EncodingName: p50k_edit
698
+ Sample: Sträva alltid efter att bli en bättre version av dig själv.
699
+ Encoded: [13290, 11033, 6862, 477, 83, 312, 304, 637, 708, 698, 72, 551, 275, 11033, 926, 260, 2196, 1196, 3100, 264, 73, 11033, 6780, 13]
700
+
701
+ EncodingName: p50k_edit
702
+ Sample: Філософія - це наука про знання. 🇺🇦
703
+ Encoded: [140, 97, 141, 244, 30143, 15166, 21727, 15166, 141, 226, 141, 244, 40623, 532, 220, 141, 228, 16843, 12466, 121, 16142, 35072, 31583, 16142, 12466, 123, 21169, 15166, 12466, 115, 22177, 16142, 22177, 22177, 40623, 13, 12520, 229, 118, 8582, 229, 99]
704
+
705
+ EncodingName: p50k_edit
706
+ Sample: Το πρόγραμμα αυτό είναι πολύ ενδιαφέρον. 🇬🇷
707
+ Encoded: [138, 97, 26517, 18074, 222, 33643, 139, 234, 42063, 33643, 17394, 34703, 34703, 17394, 26367, 139, 227, 32830, 139, 234, 7377, 113, 138, 107, 26180, 17394, 29945, 18074, 222, 26517, 39377, 139, 235, 7377, 113, 26180, 138, 112, 29945, 17394, 139, 228, 138, 255, 33643, 26517, 26180, 13, 12520, 229, 105, 8582, 229, 115]
708
+
709
+ EncodingName: p50k_edit
710
+ Sample: ^$%#*@!&)(_+=}{|:;"?><,~`'-./][
711
+ Encoded: [61, 3, 4, 2, 9, 31, 0, 5, 5769, 62, 47932, 18477, 91, 25, 26, 13984, 6927, 11, 93, 63, 29001, 19571, 7131]
712
+
713
+ EncodingName: p50k_edit
714
+ Sample: 4gH@!0sT*#(9^%$[x{}j+|Yz6;Q]~8
715
+ Encoded: [19, 70, 39, 31, 0, 15, 82, 51, 9, 2, 7, 24, 61, 4, 3, 58, 87, 90, 92, 73, 10, 91, 56, 89, 21, 26, 48, 60, 93, 23]
716
+
717
+ EncodingName: p50k_edit
718
+ Sample: wNb)I<>#:i^P]*cR8ytUx1Q`6O@z/
719
+ Encoded: [86, 45, 65, 8, 40, 27, 29, 2, 25, 72, 61, 47, 60, 9, 66, 49, 23, 20760, 52, 87, 16, 48, 63, 21, 46, 31, 89, 14]
720
+
721
+ EncodingName: p50k_edit
722
+ Sample: ÄÜö¿¡¢£¤¥¦§¨©ª«¬®¯°±²³´µ¶·¸¹º»¼½¾¿
723
+ Encoded: [127, 226, 127, 250, 9101, 126, 123, 126, 94, 44359, 14988, 126, 97, 126, 98, 126, 99, 16273, 37102, 16224, 126, 103, 24328, 126, 105, 7461, 5196, 7200, 22519, 31185, 126, 111, 18265, 126, 113, 26604, 9129, 126, 116, 126, 117, 36165, 17730, 126, 120, 23141, 126, 122, 126, 123]
724
+
725
+ EncodingName: p50k_edit
726
+ Sample: ƒšŠŒŽƒšŠŒŽƒšŠŒŽƒšŠŒŽƒšŠŒŽƒšŠŒŽ
727
+ Encoded: [130, 240, 32790, 129, 254, 129, 240, 129, 121, 130, 240, 32790, 129, 254, 129, 240, 129, 121, 130, 240, 32790, 129, 254, 129, 240, 129, 121, 130, 240, 32790, 129, 254, 129, 240, 129, 121, 130, 240, 32790, 129, 254, 129, 240, 129, 121, 130, 240, 32790, 129, 254, 129, 240, 129, 121]
728
+
729
+ EncodingName: p50k_edit
730
+ Sample: 5ħÅŸēýïūē$%#^*()_+{[ö&!@#?>|,.<>
731
+ Encoded: [20, 128, 100, 127, 227, 129, 116, 27092, 127, 121, 26884, 20317, 27092, 3, 4, 2, 61, 9, 3419, 62, 10, 90, 58, 9101, 5, 0, 41573, 30, 29, 91, 11, 29847, 29]
732
+
733
+ EncodingName: p50k_edit
734
+ Sample: 1B4t#%&*()_+dF5g^hJk7LmN0pQrS<>?
735
+ Encoded: [16, 33, 19, 83, 2, 4, 5, 9, 3419, 62, 10, 67, 37, 20, 70, 61, 71, 41, 74, 22, 43, 76, 45, 15, 79, 48, 81, 50, 27, 29, 30]
736
+
737
+ EncodingName: p50k_edit
738
+ Sample: ¬§±²³µ¶·¹ºª«»¦©¯°±!@#$%^&*()_+
739
+ Encoded: [126, 105, 16273, 22519, 31185, 126, 111, 126, 113, 26604, 9129, 126, 117, 36165, 126, 103, 24328, 17730, 126, 99, 16224, 5196, 7200, 22519, 0, 31, 29953, 4, 61, 5, 9, 3419, 62, 10]
740
+
741
+ EncodingName: p50k_edit
742
+ Sample: 8mR5*w7^a$!F(0%#J9@X6vZ1)nU3]_Y/
743
+ Encoded: [23, 76, 49, 20, 9, 86, 22, 61, 64, 3, 0, 37, 7, 15, 4, 2, 41, 24, 31, 55, 21, 85, 57, 16, 8, 77, 52, 18, 60, 62, 56, 14]
744
+
745
+ EncodingName: p50k_edit
746
+ Sample: 😊😀😁😂🤣😃😄😅😆😉😊😋😎😍😘😗😙😚☺️🙂🤗🤔
747
+ Encoded: [47249, 232, 47249, 222, 47249, 223, 47249, 224, 8582, 97, 96, 47249, 225, 47249, 226, 8582, 11805, 47249, 228, 47249, 231, 47249, 232, 47249, 233, 47249, 236, 47249, 235, 47249, 246, 47249, 245, 47249, 247, 47249, 248, 24583, 118, 37929, 8582, 25081, 8582, 97, 245, 8582, 97, 242]
748
+
749
+ EncodingName: p50k_edit
750
+ Sample: 🤨😐😑😶🙄😏😣😥😮🤐😯😪😫😴😌🤓😛😜😝🤤
751
+ Encoded: [8582, 97, 101, 47249, 238, 47249, 239, 47249, 114, 8582, 247, 226, 47249, 237, 47249, 96, 47249, 98, 47249, 106, 8582, 97, 238, 47249, 107, 47249, 103, 47249, 104, 47249, 112, 47249, 234, 8582, 97, 241, 47249, 249, 47249, 250, 47249, 251, 8582, 97, 97]
752
+
753
+ EncodingName: p50k_edit
754
+ Sample: 😒😓😔😕🙃🤑😲😷🤒🤕🤢🤧😈👿👹👺💀☠️
755
+ Encoded: [47249, 240, 47249, 241, 47249, 242, 47249, 243, 8582, 247, 225, 8582, 97, 239, 47249, 110, 47249, 115, 8582, 97, 240, 8582, 97, 243, 8582, 97, 95, 8582, 97, 100, 47249, 230, 41840, 123, 41840, 117, 41840, 118, 8582, 240, 222, 24583, 254, 37929]
756
+
757
+ EncodingName: p50k_edit
758
+ Sample: 😾😿🙀😽😼😻🙈🙉🙊👶👦👧👨👩👴👵👨‍⚕️👩‍⚕️
759
+ Encoded: [47249, 122, 47249, 123, 8582, 247, 222, 47249, 121, 47249, 120, 47249, 119, 8582, 247, 230, 8582, 247, 231, 8582, 247, 232, 41840, 114, 41840, 99, 41840, 100, 41840, 101, 41840, 102, 41840, 112, 41840, 113, 41840, 101, 447, 235, 158, 248, 243, 37929, 41840, 102, 447, 235, 158, 248, 243, 37929]
760
+
761
+ EncodingName: p50k_edit
762
+ Sample: 🌞🌝🌚🌛🌜🌙⭐️🌟💫✨🔥💥☄️🌈☀️🌤️⛅️🌥️
763
+ Encoded: [8582, 234, 252, 8582, 234, 251, 8582, 234, 248, 8582, 234, 249, 8582, 234, 250, 8582, 234, 247, 158, 255, 238, 37929, 8582, 234, 253, 8582, 240, 104, 26486, 101, 8582, 242, 98, 8582, 240, 98, 24583, 226, 37929, 8582, 234, 230, 24583, 222, 37929, 8582, 234, 97, 37929, 158, 249, 227, 37929, 8582, 234, 98, 37929]
764
+
765
+ EncodingName: p50k_edit
766
+ Sample: 🍏🍎🍐🍊🍋🍌🍉🍇🍓🍈🍒🍑
767
+ Encoded: [8582, 235, 237, 8582, 235, 236, 8582, 235, 238, 8582, 235, 232, 8582, 235, 233, 8582, 235, 234, 8582, 235, 231, 8582, 235, 229, 8582, 235, 241, 8582, 235, 230, 8582, 235, 240, 8582, 235, 239]
768
+
769
+ EncodingName: cl100k_base
770
+ Sample:
771
+ Encoded: []
772
+
773
+ EncodingName: cl100k_base
774
+ Sample: a
775
+ Encoded: [64]
776
+
777
+ EncodingName: cl100k_base
778
+ Sample: 1
779
+ Encoded: [16]
780
+
781
+ EncodingName: cl100k_base
782
+ Sample: a a
783
+ Encoded: [64, 264]
784
+
785
+ EncodingName: cl100k_base
786
+ Sample: hello
787
+ Encoded: [15339]
788
+
789
+ EncodingName: cl100k_base
790
+ Sample: Hello, World! How are you today? 🌍
791
+ Encoded: [9906, 11, 4435, 0, 2650, 527, 499, 3432, 30, 11410, 234, 235]
792
+
793
+ EncodingName: cl100k_base
794
+ Sample: こんにちは、世界!お元気ですか?
795
+ Encoded: [90115, 5486, 3574, 244, 98220, 6447, 33334, 24186, 95221, 38641, 32149, 11571]
796
+
797
+ EncodingName: cl100k_base
798
+ Sample: Hola, mundo! ¿Cómo estás hoy? 🇪🇸
799
+ Encoded: [69112, 11, 29452, 0, 29386, 96997, 1826, 7206, 49841, 30, 11410, 229, 103, 9468, 229, 116]
800
+
801
+ EncodingName: cl100k_base
802
+ Sample: Привет, мир! Как дела?
803
+ Encoded: [54745, 28089, 8341, 11, 11562, 78746, 0, 36479, 16248, 95369, 1506, 30]
804
+
805
+ EncodingName: cl100k_base
806
+ Sample: 안녕하세요, 세상! 오늘 기분이 어때요? 🇰🇷
807
+ Encoded: [31495, 230, 75265, 243, 92245, 11, 28867, 116, 57002, 0, 74177, 15478, 246, 55216, 80816, 13094, 80402, 112, 167, 48478, 36811, 30, 11410, 229, 108, 9468, 229, 115]
808
+
809
+ EncodingName: cl100k_base
810
+ Sample: Bonjour, le monde ! Comment ça va aujourd'hui ? 🇫🇷
811
+ Encoded: [82681, 11, 514, 38900, 758, 12535, 39043, 11412, 75804, 88253, 949, 11410, 229, 104, 9468, 229, 115]
812
+
813
+ EncodingName: cl100k_base
814
+ Sample: The quick brown fox jumps over 13 lazy dogs. 😺
815
+ Encoded: [791, 4062, 14198, 39935, 35308, 927, 220, 1032, 16053, 12875, 13, 27623, 118]
816
+
817
+ EncodingName: cl100k_base
818
+ Sample: 1234567890!@#$%^&*()-=_+[]{};:'",.<>?/|`~ 🎉
819
+ Encoded: [4513, 10961, 16474, 15, 0, 31, 49177, 46999, 5, 9, 16069, 21574, 10, 1318, 6390, 26, 4989, 498, 16134, 48685, 14, 91, 63, 93, 11410, 236, 231]
820
+
821
+ EncodingName: cl100k_base
822
+ Sample: C# is a great programming language for building apps.
823
+ Encoded: [34, 2, 374, 264, 2294, 15840, 4221, 369, 4857, 10721, 13]
824
+
825
+ EncodingName: cl100k_base
826
+ Sample: El área de un triángulo es (base * altura) / 2.
827
+ Encoded: [6719, 55271, 409, 653, 2463, 1995, 983, 8938, 1560, 320, 3231, 353, 60352, 8, 611, 220, 17, 13]
828
+
829
+ EncodingName: cl100k_base
830
+ Sample: Здравствуйте, это мой первый раз здесь. Что мне делать?
831
+ Encoded: [36551, 7094, 28086, 20812, 83680, 51627, 11, 68979, 11562, 16742, 77901, 35723, 39479, 11122, 7094, 92691, 13, 1301, 100, 25657, 11562, 79862, 95369, 18482, 30]
832
+
833
+ EncodingName: cl100k_base
834
+ Sample: હેલો, વિશ્વ! તમે આજે કેમ છો? 🇮🇳
835
+ Encoded: [41814, 117, 73319, 229, 41814, 110, 73319, 233, 11, 95591, 113, 41814, 123, 41814, 114, 73319, 235, 41814, 113, 0, 95591, 97, 41814, 106, 73319, 229, 95591, 228, 41814, 250, 73319, 229, 95591, 243, 73319, 229, 41814, 106, 95591, 249, 73319, 233, 30, 11410, 229, 106, 9468, 229, 111]
836
+
837
+ EncodingName: cl100k_base
838
+ Sample: ความรักและการเป็นกันเองเป็นสิ่งสำคัญที่สุดในโลก 🇹🇭
839
+ Encoded: [41427, 38313, 21437, 27379, 23084, 24152, 26265, 72409, 32882, 73367, 94974, 28991, 55784, 84382, 20795, 26265, 67356, 28991, 23780, 31534, 28991, 55784, 84382, 20795, 36748, 31885, 19138, 31534, 36748, 76169, 41427, 24152, 3098, 235, 36984, 48271, 36748, 48742, 38133, 70967, 20795, 8321, 224, 32882, 26265, 11410, 229, 117, 9468, 229, 255]
840
+
841
+ EncodingName: cl100k_base
842
+ Sample: Python vs Java: Which programming language should you learn first?
843
+ Encoded: [31380, 6296, 8102, 25, 16299, 15840, 4221, 1288, 499, 4048, 1176, 30]
844
+
845
+ EncodingName: cl100k_base
846
+ Sample: A journey of a thousand miles begins with a single step. - Lao Tzu
847
+ Encoded: [32, 11879, 315, 264, 16579, 8931, 12302, 449, 264, 3254, 3094, 13, 482, 445, 3524, 350, 26738]
848
+
849
+ EncodingName: cl100k_base
850
+ Sample: Die Grenzen meiner Sprache bedeuten die Grenzen meiner Welt. 🇩🇪
851
+ Encoded: [18674, 39224, 5797, 72226, 15883, 1815, 4950, 68, 13462, 2815, 39224, 5797, 72226, 46066, 13, 11410, 229, 102, 9468, 229, 103]
852
+
853
+ EncodingName: cl100k_base
854
+ Sample: יש לי כמה שאלות בנוגע לפרויקט החדש שלך. 🇮🇱
855
+ Encoded: [43336, 102, 78062, 33545, 17732, 249, 68406, 47071, 88898, 59610, 50391, 37769, 103, 89631, 95526, 37769, 240, 87171, 78062, 147, 97, 51326, 32793, 43336, 100, 147, 246, 70446, 90993, 86884, 59511, 88898, 50391, 147, 248, 13, 11410, 229, 106, 9468, 229, 109]
856
+
857
+ EncodingName: cl100k_base
858
+ Sample: Det är en vacker dag i Sverige. 🇸🇪
859
+ Encoded: [17513, 19106, 665, 348, 9881, 29169, 602, 328, 75295, 13, 11410, 229, 116, 9468, 229, 103]
860
+
861
+ EncodingName: cl100k_base
862
+ Sample: A ∀ x (P(x) → Q(x)) ∧ (∃x P(x)) → ∃x Q(x)
863
+ Encoded: [32, 55800, 865, 320, 47, 2120, 8, 11651, 1229, 2120, 595, 75078, 95925, 225, 87, 393, 2120, 595, 11651, 12264, 225, 87, 1229, 2120, 8]
864
+
865
+ EncodingName: cl100k_base
866
+ Sample: O Brasil é o maior país da América do Sul. 🇧🇷
867
+ Encoded: [46, 43025, 4046, 297, 46591, 42765, 3067, 98192, 656, 46962, 13, 11410, 229, 100, 9468, 229, 115]
868
+
869
+ EncodingName: cl100k_base
870
+ Sample: L'amore è una forza potente che unisce le persone. 🇮🇹
871
+ Encoded: [43, 58591, 461, 11676, 5203, 369, 4458, 3419, 6960, 3091, 653, 90368, 514, 61788, 13, 11410, 229, 106, 9468, 229, 117]
872
+
873
+ EncodingName: cl100k_base
874
+ Sample: Είναι μια ηλιόλουστη ημέρα στην Ελλάδα. 🇬🇷
875
+ Encoded: [138, 243, 55241, 34369, 90002, 33983, 30862, 19481, 8008, 115, 34586, 30862, 76295, 34586, 73986, 45028, 36924, 42524, 8008, 115, 44223, 80531, 39179, 19481, 48823, 36924, 42524, 34369, 8008, 243, 34586, 34586, 75234, 86486, 19481, 13, 11410, 229, 105, 9468, 229, 115]
876
+
877
+ EncodingName: cl100k_base
878
+ Sample: Teslim tarihi yaklaşıyor, projeyi zamanında bitirmemiz gerekiyor. 🇹🇷
879
+ Encoded: [75048, 4763, 259, 2850, 6151, 74778, 4355, 78413, 48320, 11, 22040, 1216, 72, 84240, 39797, 2766, 2923, 336, 450, 67387, 6780, 48320, 13, 11410, 229, 117, 9468, 229, 115]
880
+
881
+ EncodingName: cl100k_base
882
+ Sample: Det finnes ingen bedre tid enn nå for å starte noe nytt. 🇳🇴
883
+ Encoded: [17513, 1913, 4978, 46492, 4950, 265, 13413, 61624, 43235, 369, 13376, 1212, 68, 67539, 19541, 5683, 13, 11410, 229, 111, 9468, 229, 112]
884
+
885
+ EncodingName: cl100k_base
886
+ Sample: Aanvaard de uitdagingen van het leven met moed en vastberadenheid. 🇳🇱
887
+ Encoded: [32, 276, 6723, 569, 409, 25290, 67, 4210, 268, 5355, 9194, 93303, 2322, 4647, 291, 665, 13057, 655, 21825, 45897, 13, 11410, 229, 111, 9468, 229, 109]
888
+
889
+ EncodingName: cl100k_base
890
+ Sample: Chào mừng bạn đến với thế giới của lập trình. 🇻🇳
891
+ Encoded: [1163, 6496, 78, 296, 5080, 104, 983, 90537, 15199, 71348, 348, 53047, 270, 27160, 13845, 53047, 60835, 326, 37845, 490, 59606, 13, 11410, 229, 119, 9468, 229, 111]
892
+
893
+ EncodingName: cl100k_base
894
+ Sample: Dlaczego warto uczyć się języków obcych? 🇵🇱
895
+ Encoded: [35, 75, 42930, 13546, 79934, 26805, 70700, 12951, 503, 5267, 4341, 94557, 1536, 74146, 30, 11410, 229, 113, 9468, 229, 109]
896
+
897
+ EncodingName: cl100k_base
898
+ Sample: E = mc², uma equação famosa na física. 🇵🇹
899
+ Encoded: [36, 284, 19777, 30556, 11, 10832, 3312, 13264, 2138, 12252, 4415, 65946, 3074, 13, 11410, 229, 113, 9468, 229, 117]
900
+
901
+ EncodingName: cl100k_base
902
+ Sample: 你今天遇到什么有趣的事情了吗?🇨🇳
903
+ Encoded: [57668, 37271, 36827, 30250, 229, 28037, 6271, 222, 82696, 19361, 50266, 96, 9554, 30926, 40474, 35287, 7305, 245, 11571, 9468, 229, 101, 9468, 229, 111]
904
+
905
+ EncodingName: cl100k_base
906
+ Sample: Nå er det tid for å feire med familie og venner. 🇳🇴
907
+ Encoded: [45, 3870, 2781, 3474, 13413, 369, 13376, 1172, 556, 1812, 44526, 648, 7500, 11457, 1215, 13, 11410, 229, 111, 9468, 229, 112]
908
+
909
+ EncodingName: cl100k_base
910
+ Sample: Þetta er góður dagur til að læra eitthvað nýtt. 🇮🇸
911
+ Encoded: [127, 252, 27625, 2781, 342, 1832, 68800, 324, 29169, 324, 10478, 264, 68800, 78314, 969, 384, 275, 339, 6723, 68800, 308, 20195, 5683, 13, 11410, 229, 106, 9468, 229, 116]
912
+
913
+ EncodingName: cl100k_base
914
+ Sample: გამარჯობა! როგორ ხართ დღეს? 🇬🇪
915
+ Encoded: [36393, 240, 36393, 238, 36393, 249, 36393, 238, 36393, 254, 36393, 107, 157, 30489, 36393, 239, 36393, 238, 0, 220, 36393, 254, 157, 30489, 36393, 240, 157, 30489, 36393, 254, 220, 36393, 106, 36393, 238, 36393, 254, 36393, 245, 220, 36393, 241, 36393, 99, 36393, 242, 36393, 94, 30, 11410, 229, 105, 9468, 229, 103]
916
+
917
+ EncodingName: cl100k_base
918
+ Sample: Mā te whakawhiti kōrero e whai hua ai tātou. 🇳🇿
919
+ Encoded: [44, 31757, 1028, 421, 587, 675, 71, 12583, 597, 56761, 81, 2382, 384, 421, 2192, 305, 4381, 16796, 259, 31757, 83, 283, 13, 11410, 229, 111, 9468, 229, 123]
920
+
921
+ EncodingName: cl100k_base
922
+ Sample: Это был незабываемый опыт, который я буду помнить всегда.
923
+ Encoded: [93311, 25657, 38760, 3114, 6850, 32985, 38722, 90705, 35723, 46339, 4655, 1830, 11, 98851, 46410, 51570, 3865, 76401, 2156, 18264, 35714, 25698, 40590, 13]
924
+
925
+ EncodingName: cl100k_base
926
+ Sample: Διαβάζοντας βιβλία, εμπλουτίζουμε τον εαυτό μας με γνώσεις.
927
+ Encoded: [138, 242, 30862, 19481, 52355, 75234, 138, 114, 28654, 34369, 36924, 19481, 46742, 34318, 30862, 52355, 34586, 55241, 19481, 11, 60247, 44223, 49345, 34586, 73986, 36924, 55241, 138, 114, 73986, 44223, 31243, 39570, 28654, 34369, 60247, 19481, 54556, 36924, 76295, 33983, 19481, 46742, 33983, 31243, 63127, 34369, 139, 236, 45028, 31243, 30862, 46742, 13]
928
+
929
+ EncodingName: cl100k_base
930
+ Sample: A számítástechnika világa tele van izgalmas lehetőségekkel. 🇭🇺
931
+ Encoded: [32, 10244, 36334, 16485, 1995, 5455, 2174, 11755, 26886, 1995, 6885, 8122, 5355, 22924, 16876, 7044, 77232, 96097, 978, 713, 74, 18126, 13, 11410, 229, 255, 9468, 229, 118]
932
+
933
+ EncodingName: cl100k_base
934
+ Sample: Vždy je dobré mít plán B, pokud něco nevyjde. 🇨🇿
935
+ Encoded: [53, 12453, 10470, 4864, 97668, 978, 296, 16485, 628, 11644, 426, 11, 45295, 664, 308, 22161, 1030, 841, 14029, 73, 451, 13, 11410, 229, 101, 9468, 229, 123]
936
+
937
+ EncodingName: cl100k_base
938
+ Sample: Dragostea e un sentiment minunat care ne unește pe toți. 🇷🇴
939
+ Encoded: [18389, 537, 12791, 384, 653, 27065, 1332, 359, 266, 2512, 841, 6316, 20674, 668, 1069, 311, 45755, 13, 11410, 229, 115, 9468, 229, 112]
940
+
941
+ EncodingName: cl100k_base
942
+ Sample: دیکھو، آسمان میں کتنی تارے ہیں! 🇵🇰
943
+ Encoded: [13628, 14728, 33411, 150, 122, 12942, 69885, 8979, 95, 20665, 10386, 40523, 24252, 14728, 150, 118, 46693, 14628, 12061, 14728, 40534, 36138, 151, 240, 220, 151, 223, 14728, 150, 118, 0, 11410, 229, 113, 9468, 229, 108]
944
+
945
+ EncodingName: cl100k_base
946
+ Sample: Nenda polepole na ujifunze kila siku. 🇹🇿
947
+ Encoded: [45, 9895, 26078, 69172, 4415, 577, 73, 333, 359, 3059, 597, 10746, 274, 39342, 13, 11410, 229, 117, 9468, 229, 123]
948
+
949
+ EncodingName: cl100k_base
950
+ Sample: Каква е твоята любима храна? 🇧🇬
951
+ Encoded: [27435, 16248, 94538, 22918, 11047, 5591, 61390, 44613, 94136, 10124, 16494, 1506, 45658, 35682, 1506, 30, 11410, 229, 100, 9468, 229, 105]
952
+
953
+ EncodingName: cl100k_base
954
+ Sample: Sträva alltid efter att bli en bättre version av dig själv.
955
+ Encoded: [2645, 2357, 6723, 682, 25453, 47580, 1651, 60389, 665, 293, 50291, 265, 2373, 1860, 4170, 38536, 2357, 22580, 13]
956
+
957
+ EncodingName: cl100k_base
958
+ Sample: Філософія - це наука про знання. 🇺🇦
959
+ Encoded: [55258, 27385, 3114, 23630, 1482, 19916, 27385, 4329, 482, 39233, 1532, 13373, 3865, 13433, 41291, 11122, 2156, 7486, 40251, 13, 11410, 229, 118, 9468, 229, 99]
960
+
961
+ EncodingName: cl100k_base
962
+ Sample: Το πρόγραμμα αυτό είναι πολύ ενδιαφέρον. 🇬🇷
963
+ Encoded: [138, 97, 28654, 52845, 39179, 76295, 60474, 39179, 19481, 44223, 44223, 19481, 19581, 54556, 36924, 76295, 60247, 55241, 34369, 90002, 52845, 28654, 34586, 139, 235, 60247, 34369, 86486, 30862, 19481, 86134, 80531, 39179, 28654, 34369, 13, 11410, 229, 105, 9468, 229, 115]
964
+
965
+ EncodingName: cl100k_base
966
+ Sample: ^$%#*@!&)(_+=}{|:;"?><,~`'-./][
967
+ Encoded: [61, 3, 4, 2, 85406, 0, 5, 73885, 8664, 15523, 91, 64073, 56417, 11, 93, 63, 25279, 1761, 1483]
968
+
969
+ EncodingName: cl100k_base
970
+ Sample: 4gH@!0sT*#(9^%$[x{}j+|Yz6;Q]~8
971
+ Encoded: [19, 70, 39, 31, 0, 15, 82, 51, 9, 2, 7, 24, 61, 4, 3, 58, 87, 6390, 73, 10, 91, 56, 89, 21, 26, 48, 60, 93, 23]
972
+
973
+ EncodingName: cl100k_base
974
+ Sample: wNb)I<>#:i^P]*cR8ytUx1Q`6O@z/
975
+ Encoded: [86, 86107, 8, 40, 21806, 49182, 72, 61, 47, 8632, 66, 49, 23, 16820, 52, 87, 16, 48, 63, 21, 46, 31, 89, 14]
976
+
977
+ EncodingName: cl100k_base
978
+ Sample: ÄÜö¿¡¢£¤¥¦§¨©ª«¬®¯°±²³´µ¶·¸¹º»¼½¾¿
979
+ Encoded: [88075, 53591, 3029, 31282, 40932, 57494, 22386, 82638, 82193, 65721, 18332, 76105, 20644, 65005, 24633, 83193, 12175, 35085, 11877, 38121, 30556, 44301, 29211, 74148, 55609, 14260, 126, 116, 60597, 29300, 13289, 42973, 27154, 68496, 31282]
980
+
981
+ EncodingName: cl100k_base
982
+ Sample: ƒšŠŒŽƒšŠŒŽƒšŠŒŽƒšŠŒŽƒšŠŒŽƒšŠŒŽ
983
+ Encoded: [130, 240, 11906, 129, 254, 129, 240, 129, 121, 130, 240, 11906, 129, 254, 129, 240, 129, 121, 130, 240, 11906, 129, 254, 129, 240, 129, 121, 130, 240, 11906, 129, 254, 129, 240, 129, 121, 130, 240, 11906, 129, 254, 129, 240, 129, 121, 130, 240, 11906, 129, 254, 129, 240, 129, 121]
984
+
985
+ EncodingName: cl100k_base
986
+ Sample: 5ħÅŸēýïūē$%#^*()_+{[ö&!@#?>|,.<>
987
+ Encoded: [20, 128, 100, 127, 227, 129, 116, 79083, 20195, 38672, 54056, 79083, 3, 4, 2, 61, 9, 368, 62, 10, 90, 58, 3029, 5, 0, 31, 2, 4887, 91, 11, 16134, 29]
988
+
989
+ EncodingName: cl100k_base
990
+ Sample: 1B4t#%&*()_+dF5g^hJk7LmN0pQrS<>?
991
+ Encoded: [16, 33, 19, 83, 2, 4, 5, 9, 368, 62, 10, 67, 37, 20, 70, 61, 71, 41, 74, 22, 43, 76, 45, 15, 79, 48, 81, 50, 21806, 30]
992
+
993
+ EncodingName: cl100k_base
994
+ Sample: ¬§±²³µ¶·¹ºª«»¦©¯°±!@#$%^&*()_+
995
+ Encoded: [83193, 18332, 38121, 30556, 44301, 74148, 55609, 14260, 60597, 29300, 65005, 24633, 13289, 65721, 20644, 35085, 11877, 38121, 0, 31, 49177, 46999, 5, 9, 368, 62, 10]
996
+
997
+ EncodingName: cl100k_base
998
+ Sample: 8mR5*w7^a$!F(0%#J9@X6vZ1)nU3]_Y/
999
+ Encoded: [23, 76, 49, 20, 60476, 22, 61, 64, 3, 0, 37, 7, 15, 4, 2, 41, 24, 31, 55, 21, 85, 57, 16, 80198, 52, 18, 60, 62, 56, 14]
1000
+
1001
+ EncodingName: cl100k_base
1002
+ Sample: 😊😀😁😂🤣😃😄😅😆😉😊😋😎😍😘😗😙😚☺️🙂🤗🤔
1003
+ Encoded: [76460, 232, 76460, 222, 76460, 223, 76460, 224, 9468, 97, 96, 76460, 225, 76460, 226, 76460, 227, 76460, 228, 76460, 231, 76460, 232, 76460, 233, 76460, 236, 76460, 235, 76460, 246, 76460, 245, 76460, 247, 76460, 248, 18107, 118, 31643, 9468, 19044, 9468, 97, 245, 9468, 97, 242]
1004
+
1005
+ EncodingName: cl100k_base
1006
+ Sample: 🤨😐😑😶🙄😏😣😥😮🤐😯😪😫😴😌🤓😛😜😝🤤
1007
+ Encoded: [9468, 97, 101, 76460, 238, 76460, 239, 76460, 114, 9468, 247, 226, 76460, 237, 76460, 96, 76460, 98, 76460, 106, 9468, 97, 238, 76460, 107, 76460, 103, 76460, 104, 76460, 112, 76460, 234, 9468, 97, 241, 76460, 249, 76460, 250, 76460, 251, 9468, 97, 97]
1008
+
1009
+ EncodingName: cl100k_base
1010
+ Sample: 😒😓😔😕🙃🤑😲😷🤒🤕🤢🤧😈👿👹👺💀☠️
1011
+ Encoded: [76460, 240, 76460, 241, 76460, 242, 76460, 243, 9468, 247, 225, 9468, 97, 239, 76460, 110, 76460, 115, 9468, 97, 240, 9468, 97, 243, 9468, 97, 95, 9468, 97, 100, 76460, 230, 9468, 239, 123, 9468, 239, 117, 9468, 239, 118, 93273, 222, 18107, 254, 31643]
1012
+
1013
+ EncodingName: cl100k_base
1014
+ Sample: 😾😿🙀😽😼😻🙈🙉🙊👶👦👧👨👩👴👵👨‍⚕️👩‍⚕️
1015
+ Encoded: [76460, 122, 76460, 123, 9468, 247, 222, 76460, 121, 76460, 120, 76460, 119, 9468, 247, 230, 9468, 247, 231, 9468, 247, 232, 9468, 239, 114, 9468, 239, 99, 9468, 239, 100, 9468, 239, 101, 9468, 239, 102, 9468, 239, 112, 9468, 239, 113, 9468, 239, 101, 378, 235, 158, 248, 243, 31643, 9468, 239, 102, 378, 235, 158, 248, 243, 31643]
1016
+
1017
+ EncodingName: cl100k_base
1018
+ Sample: 🌞🌝🌚🌛🌜🌙⭐️🌟💫✨🔥💥☄️🌈☀️🌤️⛅️🌥️
1019
+ Encoded: [9468, 234, 252, 9468, 234, 251, 9468, 234, 248, 9468, 234, 249, 9468, 234, 250, 9468, 234, 247, 158, 99834, 31643, 9468, 234, 253, 93273, 104, 38798, 101, 9468, 242, 98, 93273, 98, 18107, 226, 31643, 9468, 234, 230, 18107, 222, 31643, 9468, 234, 97, 31643, 158, 249, 227, 31643, 9468, 234, 98, 31643]
1020
+
1021
+ EncodingName: cl100k_base
1022
+ Sample: 🍏🍎🍐🍊🍋🍌🍉🍇🍓🍈🍒🍑
1023
+ Encoded: [9468, 235, 237, 9468, 235, 236, 9468, 235, 238, 9468, 235, 232, 9468, 235, 233, 9468, 235, 234, 9468, 235, 231, 9468, 235, 229, 9468, 235, 241, 9468, 235, 230, 9468, 235, 240, 9468, 235, 239]
1024
+