AbstractPhil commited on
Commit
91cd1c5
·
verified ·
1 Parent(s): 8521e58

bytelex v1: 12 normalized token->bytes vocabulary tables (fleet-extracted, round-trip spot-checked)

Browse files
.gitattributes CHANGED
@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ vocab_cl100k_base.jsonl filter=lfs diff=lfs merge=lfs -text
37
+ vocab_deepseek-v3.jsonl filter=lfs diff=lfs merge=lfs -text
38
+ vocab_llama3.jsonl filter=lfs diff=lfs merge=lfs -text
39
+ vocab_o200k_base.jsonl filter=lfs diff=lfs merge=lfs -text
40
+ vocab_qwen3-newest.jsonl filter=lfs diff=lfs merge=lfs -text
41
+ vocab_xlmr.jsonl filter=lfs diff=lfs merge=lfs -text
vocab_bert-wordpiece.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
vocab_byt5-control.jsonl ADDED
@@ -0,0 +1,384 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"id": 0, "hex": "3c7061643e", "text": "<pad>", "n_bytes": 5, "is_special": true, "continuation": false}
2
+ {"id": 1, "hex": "3c2f733e", "text": "</s>", "n_bytes": 4, "is_special": true, "continuation": false}
3
+ {"id": 2, "hex": "3c756e6b3e", "text": "<unk>", "n_bytes": 5, "is_special": true, "continuation": false}
4
+ {"id": 3, "hex": "00", "text": "\u0000", "n_bytes": 1, "is_special": false, "continuation": false}
5
+ {"id": 4, "hex": "01", "text": "\u0001", "n_bytes": 1, "is_special": false, "continuation": false}
6
+ {"id": 5, "hex": "02", "text": "\u0002", "n_bytes": 1, "is_special": false, "continuation": false}
7
+ {"id": 6, "hex": "03", "text": "\u0003", "n_bytes": 1, "is_special": false, "continuation": false}
8
+ {"id": 7, "hex": "04", "text": "\u0004", "n_bytes": 1, "is_special": false, "continuation": false}
9
+ {"id": 8, "hex": "05", "text": "\u0005", "n_bytes": 1, "is_special": false, "continuation": false}
10
+ {"id": 9, "hex": "06", "text": "\u0006", "n_bytes": 1, "is_special": false, "continuation": false}
11
+ {"id": 10, "hex": "07", "text": "\u0007", "n_bytes": 1, "is_special": false, "continuation": false}
12
+ {"id": 11, "hex": "08", "text": "\b", "n_bytes": 1, "is_special": false, "continuation": false}
13
+ {"id": 12, "hex": "09", "text": "\t", "n_bytes": 1, "is_special": false, "continuation": false}
14
+ {"id": 13, "hex": "0a", "text": "\n", "n_bytes": 1, "is_special": false, "continuation": false}
15
+ {"id": 14, "hex": "0b", "text": "\u000b", "n_bytes": 1, "is_special": false, "continuation": false}
16
+ {"id": 15, "hex": "0c", "text": "\f", "n_bytes": 1, "is_special": false, "continuation": false}
17
+ {"id": 16, "hex": "0d", "text": "\r", "n_bytes": 1, "is_special": false, "continuation": false}
18
+ {"id": 17, "hex": "0e", "text": "\u000e", "n_bytes": 1, "is_special": false, "continuation": false}
19
+ {"id": 18, "hex": "0f", "text": "\u000f", "n_bytes": 1, "is_special": false, "continuation": false}
20
+ {"id": 19, "hex": "10", "text": "\u0010", "n_bytes": 1, "is_special": false, "continuation": false}
21
+ {"id": 20, "hex": "11", "text": "\u0011", "n_bytes": 1, "is_special": false, "continuation": false}
22
+ {"id": 21, "hex": "12", "text": "\u0012", "n_bytes": 1, "is_special": false, "continuation": false}
23
+ {"id": 22, "hex": "13", "text": "\u0013", "n_bytes": 1, "is_special": false, "continuation": false}
24
+ {"id": 23, "hex": "14", "text": "\u0014", "n_bytes": 1, "is_special": false, "continuation": false}
25
+ {"id": 24, "hex": "15", "text": "\u0015", "n_bytes": 1, "is_special": false, "continuation": false}
26
+ {"id": 25, "hex": "16", "text": "\u0016", "n_bytes": 1, "is_special": false, "continuation": false}
27
+ {"id": 26, "hex": "17", "text": "\u0017", "n_bytes": 1, "is_special": false, "continuation": false}
28
+ {"id": 27, "hex": "18", "text": "\u0018", "n_bytes": 1, "is_special": false, "continuation": false}
29
+ {"id": 28, "hex": "19", "text": "\u0019", "n_bytes": 1, "is_special": false, "continuation": false}
30
+ {"id": 29, "hex": "1a", "text": "\u001a", "n_bytes": 1, "is_special": false, "continuation": false}
31
+ {"id": 30, "hex": "1b", "text": "\u001b", "n_bytes": 1, "is_special": false, "continuation": false}
32
+ {"id": 31, "hex": "1c", "text": "\u001c", "n_bytes": 1, "is_special": false, "continuation": false}
33
+ {"id": 32, "hex": "1d", "text": "\u001d", "n_bytes": 1, "is_special": false, "continuation": false}
34
+ {"id": 33, "hex": "1e", "text": "\u001e", "n_bytes": 1, "is_special": false, "continuation": false}
35
+ {"id": 34, "hex": "1f", "text": "\u001f", "n_bytes": 1, "is_special": false, "continuation": false}
36
+ {"id": 35, "hex": "20", "text": " ", "n_bytes": 1, "is_special": false, "continuation": false}
37
+ {"id": 36, "hex": "21", "text": "!", "n_bytes": 1, "is_special": false, "continuation": false}
38
+ {"id": 37, "hex": "22", "text": "\"", "n_bytes": 1, "is_special": false, "continuation": false}
39
+ {"id": 38, "hex": "23", "text": "#", "n_bytes": 1, "is_special": false, "continuation": false}
40
+ {"id": 39, "hex": "24", "text": "$", "n_bytes": 1, "is_special": false, "continuation": false}
41
+ {"id": 40, "hex": "25", "text": "%", "n_bytes": 1, "is_special": false, "continuation": false}
42
+ {"id": 41, "hex": "26", "text": "&", "n_bytes": 1, "is_special": false, "continuation": false}
43
+ {"id": 42, "hex": "27", "text": "'", "n_bytes": 1, "is_special": false, "continuation": false}
44
+ {"id": 43, "hex": "28", "text": "(", "n_bytes": 1, "is_special": false, "continuation": false}
45
+ {"id": 44, "hex": "29", "text": ")", "n_bytes": 1, "is_special": false, "continuation": false}
46
+ {"id": 45, "hex": "2a", "text": "*", "n_bytes": 1, "is_special": false, "continuation": false}
47
+ {"id": 46, "hex": "2b", "text": "+", "n_bytes": 1, "is_special": false, "continuation": false}
48
+ {"id": 47, "hex": "2c", "text": ",", "n_bytes": 1, "is_special": false, "continuation": false}
49
+ {"id": 48, "hex": "2d", "text": "-", "n_bytes": 1, "is_special": false, "continuation": false}
50
+ {"id": 49, "hex": "2e", "text": ".", "n_bytes": 1, "is_special": false, "continuation": false}
51
+ {"id": 50, "hex": "2f", "text": "/", "n_bytes": 1, "is_special": false, "continuation": false}
52
+ {"id": 51, "hex": "30", "text": "0", "n_bytes": 1, "is_special": false, "continuation": false}
53
+ {"id": 52, "hex": "31", "text": "1", "n_bytes": 1, "is_special": false, "continuation": false}
54
+ {"id": 53, "hex": "32", "text": "2", "n_bytes": 1, "is_special": false, "continuation": false}
55
+ {"id": 54, "hex": "33", "text": "3", "n_bytes": 1, "is_special": false, "continuation": false}
56
+ {"id": 55, "hex": "34", "text": "4", "n_bytes": 1, "is_special": false, "continuation": false}
57
+ {"id": 56, "hex": "35", "text": "5", "n_bytes": 1, "is_special": false, "continuation": false}
58
+ {"id": 57, "hex": "36", "text": "6", "n_bytes": 1, "is_special": false, "continuation": false}
59
+ {"id": 58, "hex": "37", "text": "7", "n_bytes": 1, "is_special": false, "continuation": false}
60
+ {"id": 59, "hex": "38", "text": "8", "n_bytes": 1, "is_special": false, "continuation": false}
61
+ {"id": 60, "hex": "39", "text": "9", "n_bytes": 1, "is_special": false, "continuation": false}
62
+ {"id": 61, "hex": "3a", "text": ":", "n_bytes": 1, "is_special": false, "continuation": false}
63
+ {"id": 62, "hex": "3b", "text": ";", "n_bytes": 1, "is_special": false, "continuation": false}
64
+ {"id": 63, "hex": "3c", "text": "<", "n_bytes": 1, "is_special": false, "continuation": false}
65
+ {"id": 64, "hex": "3d", "text": "=", "n_bytes": 1, "is_special": false, "continuation": false}
66
+ {"id": 65, "hex": "3e", "text": ">", "n_bytes": 1, "is_special": false, "continuation": false}
67
+ {"id": 66, "hex": "3f", "text": "?", "n_bytes": 1, "is_special": false, "continuation": false}
68
+ {"id": 67, "hex": "40", "text": "@", "n_bytes": 1, "is_special": false, "continuation": false}
69
+ {"id": 68, "hex": "41", "text": "A", "n_bytes": 1, "is_special": false, "continuation": false}
70
+ {"id": 69, "hex": "42", "text": "B", "n_bytes": 1, "is_special": false, "continuation": false}
71
+ {"id": 70, "hex": "43", "text": "C", "n_bytes": 1, "is_special": false, "continuation": false}
72
+ {"id": 71, "hex": "44", "text": "D", "n_bytes": 1, "is_special": false, "continuation": false}
73
+ {"id": 72, "hex": "45", "text": "E", "n_bytes": 1, "is_special": false, "continuation": false}
74
+ {"id": 73, "hex": "46", "text": "F", "n_bytes": 1, "is_special": false, "continuation": false}
75
+ {"id": 74, "hex": "47", "text": "G", "n_bytes": 1, "is_special": false, "continuation": false}
76
+ {"id": 75, "hex": "48", "text": "H", "n_bytes": 1, "is_special": false, "continuation": false}
77
+ {"id": 76, "hex": "49", "text": "I", "n_bytes": 1, "is_special": false, "continuation": false}
78
+ {"id": 77, "hex": "4a", "text": "J", "n_bytes": 1, "is_special": false, "continuation": false}
79
+ {"id": 78, "hex": "4b", "text": "K", "n_bytes": 1, "is_special": false, "continuation": false}
80
+ {"id": 79, "hex": "4c", "text": "L", "n_bytes": 1, "is_special": false, "continuation": false}
81
+ {"id": 80, "hex": "4d", "text": "M", "n_bytes": 1, "is_special": false, "continuation": false}
82
+ {"id": 81, "hex": "4e", "text": "N", "n_bytes": 1, "is_special": false, "continuation": false}
83
+ {"id": 82, "hex": "4f", "text": "O", "n_bytes": 1, "is_special": false, "continuation": false}
84
+ {"id": 83, "hex": "50", "text": "P", "n_bytes": 1, "is_special": false, "continuation": false}
85
+ {"id": 84, "hex": "51", "text": "Q", "n_bytes": 1, "is_special": false, "continuation": false}
86
+ {"id": 85, "hex": "52", "text": "R", "n_bytes": 1, "is_special": false, "continuation": false}
87
+ {"id": 86, "hex": "53", "text": "S", "n_bytes": 1, "is_special": false, "continuation": false}
88
+ {"id": 87, "hex": "54", "text": "T", "n_bytes": 1, "is_special": false, "continuation": false}
89
+ {"id": 88, "hex": "55", "text": "U", "n_bytes": 1, "is_special": false, "continuation": false}
90
+ {"id": 89, "hex": "56", "text": "V", "n_bytes": 1, "is_special": false, "continuation": false}
91
+ {"id": 90, "hex": "57", "text": "W", "n_bytes": 1, "is_special": false, "continuation": false}
92
+ {"id": 91, "hex": "58", "text": "X", "n_bytes": 1, "is_special": false, "continuation": false}
93
+ {"id": 92, "hex": "59", "text": "Y", "n_bytes": 1, "is_special": false, "continuation": false}
94
+ {"id": 93, "hex": "5a", "text": "Z", "n_bytes": 1, "is_special": false, "continuation": false}
95
+ {"id": 94, "hex": "5b", "text": "[", "n_bytes": 1, "is_special": false, "continuation": false}
96
+ {"id": 95, "hex": "5c", "text": "\\", "n_bytes": 1, "is_special": false, "continuation": false}
97
+ {"id": 96, "hex": "5d", "text": "]", "n_bytes": 1, "is_special": false, "continuation": false}
98
+ {"id": 97, "hex": "5e", "text": "^", "n_bytes": 1, "is_special": false, "continuation": false}
99
+ {"id": 98, "hex": "5f", "text": "_", "n_bytes": 1, "is_special": false, "continuation": false}
100
+ {"id": 99, "hex": "60", "text": "`", "n_bytes": 1, "is_special": false, "continuation": false}
101
+ {"id": 100, "hex": "61", "text": "a", "n_bytes": 1, "is_special": false, "continuation": false}
102
+ {"id": 101, "hex": "62", "text": "b", "n_bytes": 1, "is_special": false, "continuation": false}
103
+ {"id": 102, "hex": "63", "text": "c", "n_bytes": 1, "is_special": false, "continuation": false}
104
+ {"id": 103, "hex": "64", "text": "d", "n_bytes": 1, "is_special": false, "continuation": false}
105
+ {"id": 104, "hex": "65", "text": "e", "n_bytes": 1, "is_special": false, "continuation": false}
106
+ {"id": 105, "hex": "66", "text": "f", "n_bytes": 1, "is_special": false, "continuation": false}
107
+ {"id": 106, "hex": "67", "text": "g", "n_bytes": 1, "is_special": false, "continuation": false}
108
+ {"id": 107, "hex": "68", "text": "h", "n_bytes": 1, "is_special": false, "continuation": false}
109
+ {"id": 108, "hex": "69", "text": "i", "n_bytes": 1, "is_special": false, "continuation": false}
110
+ {"id": 109, "hex": "6a", "text": "j", "n_bytes": 1, "is_special": false, "continuation": false}
111
+ {"id": 110, "hex": "6b", "text": "k", "n_bytes": 1, "is_special": false, "continuation": false}
112
+ {"id": 111, "hex": "6c", "text": "l", "n_bytes": 1, "is_special": false, "continuation": false}
113
+ {"id": 112, "hex": "6d", "text": "m", "n_bytes": 1, "is_special": false, "continuation": false}
114
+ {"id": 113, "hex": "6e", "text": "n", "n_bytes": 1, "is_special": false, "continuation": false}
115
+ {"id": 114, "hex": "6f", "text": "o", "n_bytes": 1, "is_special": false, "continuation": false}
116
+ {"id": 115, "hex": "70", "text": "p", "n_bytes": 1, "is_special": false, "continuation": false}
117
+ {"id": 116, "hex": "71", "text": "q", "n_bytes": 1, "is_special": false, "continuation": false}
118
+ {"id": 117, "hex": "72", "text": "r", "n_bytes": 1, "is_special": false, "continuation": false}
119
+ {"id": 118, "hex": "73", "text": "s", "n_bytes": 1, "is_special": false, "continuation": false}
120
+ {"id": 119, "hex": "74", "text": "t", "n_bytes": 1, "is_special": false, "continuation": false}
121
+ {"id": 120, "hex": "75", "text": "u", "n_bytes": 1, "is_special": false, "continuation": false}
122
+ {"id": 121, "hex": "76", "text": "v", "n_bytes": 1, "is_special": false, "continuation": false}
123
+ {"id": 122, "hex": "77", "text": "w", "n_bytes": 1, "is_special": false, "continuation": false}
124
+ {"id": 123, "hex": "78", "text": "x", "n_bytes": 1, "is_special": false, "continuation": false}
125
+ {"id": 124, "hex": "79", "text": "y", "n_bytes": 1, "is_special": false, "continuation": false}
126
+ {"id": 125, "hex": "7a", "text": "z", "n_bytes": 1, "is_special": false, "continuation": false}
127
+ {"id": 126, "hex": "7b", "text": "{", "n_bytes": 1, "is_special": false, "continuation": false}
128
+ {"id": 127, "hex": "7c", "text": "|", "n_bytes": 1, "is_special": false, "continuation": false}
129
+ {"id": 128, "hex": "7d", "text": "}", "n_bytes": 1, "is_special": false, "continuation": false}
130
+ {"id": 129, "hex": "7e", "text": "~", "n_bytes": 1, "is_special": false, "continuation": false}
131
+ {"id": 130, "hex": "7f", "text": "", "n_bytes": 1, "is_special": false, "continuation": false}
132
+ {"id": 131, "hex": "80", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
133
+ {"id": 132, "hex": "81", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
134
+ {"id": 133, "hex": "82", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
135
+ {"id": 134, "hex": "83", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
136
+ {"id": 135, "hex": "84", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
137
+ {"id": 136, "hex": "85", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
138
+ {"id": 137, "hex": "86", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
139
+ {"id": 138, "hex": "87", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
140
+ {"id": 139, "hex": "88", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
141
+ {"id": 140, "hex": "89", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
142
+ {"id": 141, "hex": "8a", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
143
+ {"id": 142, "hex": "8b", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
144
+ {"id": 143, "hex": "8c", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
145
+ {"id": 144, "hex": "8d", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
146
+ {"id": 145, "hex": "8e", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
147
+ {"id": 146, "hex": "8f", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
148
+ {"id": 147, "hex": "90", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
149
+ {"id": 148, "hex": "91", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
150
+ {"id": 149, "hex": "92", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
151
+ {"id": 150, "hex": "93", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
152
+ {"id": 151, "hex": "94", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
153
+ {"id": 152, "hex": "95", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
154
+ {"id": 153, "hex": "96", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
155
+ {"id": 154, "hex": "97", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
156
+ {"id": 155, "hex": "98", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
157
+ {"id": 156, "hex": "99", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
158
+ {"id": 157, "hex": "9a", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
159
+ {"id": 158, "hex": "9b", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
160
+ {"id": 159, "hex": "9c", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
161
+ {"id": 160, "hex": "9d", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
162
+ {"id": 161, "hex": "9e", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
163
+ {"id": 162, "hex": "9f", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
164
+ {"id": 163, "hex": "a0", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
165
+ {"id": 164, "hex": "a1", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
166
+ {"id": 165, "hex": "a2", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
167
+ {"id": 166, "hex": "a3", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
168
+ {"id": 167, "hex": "a4", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
169
+ {"id": 168, "hex": "a5", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
170
+ {"id": 169, "hex": "a6", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
171
+ {"id": 170, "hex": "a7", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
172
+ {"id": 171, "hex": "a8", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
173
+ {"id": 172, "hex": "a9", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
174
+ {"id": 173, "hex": "aa", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
175
+ {"id": 174, "hex": "ab", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
176
+ {"id": 175, "hex": "ac", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
177
+ {"id": 176, "hex": "ad", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
178
+ {"id": 177, "hex": "ae", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
179
+ {"id": 178, "hex": "af", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
180
+ {"id": 179, "hex": "b0", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
181
+ {"id": 180, "hex": "b1", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
182
+ {"id": 181, "hex": "b2", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
183
+ {"id": 182, "hex": "b3", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
184
+ {"id": 183, "hex": "b4", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
185
+ {"id": 184, "hex": "b5", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
186
+ {"id": 185, "hex": "b6", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
187
+ {"id": 186, "hex": "b7", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
188
+ {"id": 187, "hex": "b8", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
189
+ {"id": 188, "hex": "b9", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
190
+ {"id": 189, "hex": "ba", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
191
+ {"id": 190, "hex": "bb", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
192
+ {"id": 191, "hex": "bc", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
193
+ {"id": 192, "hex": "bd", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
194
+ {"id": 193, "hex": "be", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
195
+ {"id": 194, "hex": "bf", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
196
+ {"id": 195, "hex": "c0", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
197
+ {"id": 196, "hex": "c1", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
198
+ {"id": 197, "hex": "c2", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
199
+ {"id": 198, "hex": "c3", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
200
+ {"id": 199, "hex": "c4", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
201
+ {"id": 200, "hex": "c5", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
202
+ {"id": 201, "hex": "c6", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
203
+ {"id": 202, "hex": "c7", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
204
+ {"id": 203, "hex": "c8", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
205
+ {"id": 204, "hex": "c9", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
206
+ {"id": 205, "hex": "ca", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
207
+ {"id": 206, "hex": "cb", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
208
+ {"id": 207, "hex": "cc", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
209
+ {"id": 208, "hex": "cd", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
210
+ {"id": 209, "hex": "ce", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
211
+ {"id": 210, "hex": "cf", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
212
+ {"id": 211, "hex": "d0", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
213
+ {"id": 212, "hex": "d1", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
214
+ {"id": 213, "hex": "d2", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
215
+ {"id": 214, "hex": "d3", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
216
+ {"id": 215, "hex": "d4", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
217
+ {"id": 216, "hex": "d5", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
218
+ {"id": 217, "hex": "d6", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
219
+ {"id": 218, "hex": "d7", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
220
+ {"id": 219, "hex": "d8", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
221
+ {"id": 220, "hex": "d9", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
222
+ {"id": 221, "hex": "da", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
223
+ {"id": 222, "hex": "db", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
224
+ {"id": 223, "hex": "dc", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
225
+ {"id": 224, "hex": "dd", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
226
+ {"id": 225, "hex": "de", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
227
+ {"id": 226, "hex": "df", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
228
+ {"id": 227, "hex": "e0", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
229
+ {"id": 228, "hex": "e1", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
230
+ {"id": 229, "hex": "e2", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
231
+ {"id": 230, "hex": "e3", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
232
+ {"id": 231, "hex": "e4", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
233
+ {"id": 232, "hex": "e5", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
234
+ {"id": 233, "hex": "e6", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
235
+ {"id": 234, "hex": "e7", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
236
+ {"id": 235, "hex": "e8", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
237
+ {"id": 236, "hex": "e9", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
238
+ {"id": 237, "hex": "ea", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
239
+ {"id": 238, "hex": "eb", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
240
+ {"id": 239, "hex": "ec", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
241
+ {"id": 240, "hex": "ed", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
242
+ {"id": 241, "hex": "ee", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
243
+ {"id": 242, "hex": "ef", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
244
+ {"id": 243, "hex": "f0", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
245
+ {"id": 244, "hex": "f1", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
246
+ {"id": 245, "hex": "f2", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
247
+ {"id": 246, "hex": "f3", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
248
+ {"id": 247, "hex": "f4", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
249
+ {"id": 248, "hex": "f5", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
250
+ {"id": 249, "hex": "f6", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
251
+ {"id": 250, "hex": "f7", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
252
+ {"id": 251, "hex": "f8", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
253
+ {"id": 252, "hex": "f9", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
254
+ {"id": 253, "hex": "fa", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
255
+ {"id": 254, "hex": "fb", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
256
+ {"id": 255, "hex": "fc", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
257
+ {"id": 256, "hex": "fd", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
258
+ {"id": 257, "hex": "fe", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
259
+ {"id": 258, "hex": "ff", "text": null, "n_bytes": 1, "is_special": false, "continuation": false}
260
+ {"id": 259, "hex": "3c65787472615f69645f303e", "text": "<extra_id_0>", "n_bytes": 12, "is_special": true, "continuation": false}
261
+ {"id": 260, "hex": "3c65787472615f69645f313e", "text": "<extra_id_1>", "n_bytes": 12, "is_special": true, "continuation": false}
262
+ {"id": 261, "hex": "3c65787472615f69645f323e", "text": "<extra_id_2>", "n_bytes": 12, "is_special": true, "continuation": false}
263
+ {"id": 262, "hex": "3c65787472615f69645f333e", "text": "<extra_id_3>", "n_bytes": 12, "is_special": true, "continuation": false}
264
+ {"id": 263, "hex": "3c65787472615f69645f343e", "text": "<extra_id_4>", "n_bytes": 12, "is_special": true, "continuation": false}
265
+ {"id": 264, "hex": "3c65787472615f69645f353e", "text": "<extra_id_5>", "n_bytes": 12, "is_special": true, "continuation": false}
266
+ {"id": 265, "hex": "3c65787472615f69645f363e", "text": "<extra_id_6>", "n_bytes": 12, "is_special": true, "continuation": false}
267
+ {"id": 266, "hex": "3c65787472615f69645f373e", "text": "<extra_id_7>", "n_bytes": 12, "is_special": true, "continuation": false}
268
+ {"id": 267, "hex": "3c65787472615f69645f383e", "text": "<extra_id_8>", "n_bytes": 12, "is_special": true, "continuation": false}
269
+ {"id": 268, "hex": "3c65787472615f69645f393e", "text": "<extra_id_9>", "n_bytes": 12, "is_special": true, "continuation": false}
270
+ {"id": 269, "hex": "3c65787472615f69645f31303e", "text": "<extra_id_10>", "n_bytes": 13, "is_special": true, "continuation": false}
271
+ {"id": 270, "hex": "3c65787472615f69645f31313e", "text": "<extra_id_11>", "n_bytes": 13, "is_special": true, "continuation": false}
272
+ {"id": 271, "hex": "3c65787472615f69645f31323e", "text": "<extra_id_12>", "n_bytes": 13, "is_special": true, "continuation": false}
273
+ {"id": 272, "hex": "3c65787472615f69645f31333e", "text": "<extra_id_13>", "n_bytes": 13, "is_special": true, "continuation": false}
274
+ {"id": 273, "hex": "3c65787472615f69645f31343e", "text": "<extra_id_14>", "n_bytes": 13, "is_special": true, "continuation": false}
275
+ {"id": 274, "hex": "3c65787472615f69645f31353e", "text": "<extra_id_15>", "n_bytes": 13, "is_special": true, "continuation": false}
276
+ {"id": 275, "hex": "3c65787472615f69645f31363e", "text": "<extra_id_16>", "n_bytes": 13, "is_special": true, "continuation": false}
277
+ {"id": 276, "hex": "3c65787472615f69645f31373e", "text": "<extra_id_17>", "n_bytes": 13, "is_special": true, "continuation": false}
278
+ {"id": 277, "hex": "3c65787472615f69645f31383e", "text": "<extra_id_18>", "n_bytes": 13, "is_special": true, "continuation": false}
279
+ {"id": 278, "hex": "3c65787472615f69645f31393e", "text": "<extra_id_19>", "n_bytes": 13, "is_special": true, "continuation": false}
280
+ {"id": 279, "hex": "3c65787472615f69645f32303e", "text": "<extra_id_20>", "n_bytes": 13, "is_special": true, "continuation": false}
281
+ {"id": 280, "hex": "3c65787472615f69645f32313e", "text": "<extra_id_21>", "n_bytes": 13, "is_special": true, "continuation": false}
282
+ {"id": 281, "hex": "3c65787472615f69645f32323e", "text": "<extra_id_22>", "n_bytes": 13, "is_special": true, "continuation": false}
283
+ {"id": 282, "hex": "3c65787472615f69645f32333e", "text": "<extra_id_23>", "n_bytes": 13, "is_special": true, "continuation": false}
284
+ {"id": 283, "hex": "3c65787472615f69645f32343e", "text": "<extra_id_24>", "n_bytes": 13, "is_special": true, "continuation": false}
285
+ {"id": 284, "hex": "3c65787472615f69645f32353e", "text": "<extra_id_25>", "n_bytes": 13, "is_special": true, "continuation": false}
286
+ {"id": 285, "hex": "3c65787472615f69645f32363e", "text": "<extra_id_26>", "n_bytes": 13, "is_special": true, "continuation": false}
287
+ {"id": 286, "hex": "3c65787472615f69645f32373e", "text": "<extra_id_27>", "n_bytes": 13, "is_special": true, "continuation": false}
288
+ {"id": 287, "hex": "3c65787472615f69645f32383e", "text": "<extra_id_28>", "n_bytes": 13, "is_special": true, "continuation": false}
289
+ {"id": 288, "hex": "3c65787472615f69645f32393e", "text": "<extra_id_29>", "n_bytes": 13, "is_special": true, "continuation": false}
290
+ {"id": 289, "hex": "3c65787472615f69645f33303e", "text": "<extra_id_30>", "n_bytes": 13, "is_special": true, "continuation": false}
291
+ {"id": 290, "hex": "3c65787472615f69645f33313e", "text": "<extra_id_31>", "n_bytes": 13, "is_special": true, "continuation": false}
292
+ {"id": 291, "hex": "3c65787472615f69645f33323e", "text": "<extra_id_32>", "n_bytes": 13, "is_special": true, "continuation": false}
293
+ {"id": 292, "hex": "3c65787472615f69645f33333e", "text": "<extra_id_33>", "n_bytes": 13, "is_special": true, "continuation": false}
294
+ {"id": 293, "hex": "3c65787472615f69645f33343e", "text": "<extra_id_34>", "n_bytes": 13, "is_special": true, "continuation": false}
295
+ {"id": 294, "hex": "3c65787472615f69645f33353e", "text": "<extra_id_35>", "n_bytes": 13, "is_special": true, "continuation": false}
296
+ {"id": 295, "hex": "3c65787472615f69645f33363e", "text": "<extra_id_36>", "n_bytes": 13, "is_special": true, "continuation": false}
297
+ {"id": 296, "hex": "3c65787472615f69645f33373e", "text": "<extra_id_37>", "n_bytes": 13, "is_special": true, "continuation": false}
298
+ {"id": 297, "hex": "3c65787472615f69645f33383e", "text": "<extra_id_38>", "n_bytes": 13, "is_special": true, "continuation": false}
299
+ {"id": 298, "hex": "3c65787472615f69645f33393e", "text": "<extra_id_39>", "n_bytes": 13, "is_special": true, "continuation": false}
300
+ {"id": 299, "hex": "3c65787472615f69645f34303e", "text": "<extra_id_40>", "n_bytes": 13, "is_special": true, "continuation": false}
301
+ {"id": 300, "hex": "3c65787472615f69645f34313e", "text": "<extra_id_41>", "n_bytes": 13, "is_special": true, "continuation": false}
302
+ {"id": 301, "hex": "3c65787472615f69645f34323e", "text": "<extra_id_42>", "n_bytes": 13, "is_special": true, "continuation": false}
303
+ {"id": 302, "hex": "3c65787472615f69645f34333e", "text": "<extra_id_43>", "n_bytes": 13, "is_special": true, "continuation": false}
304
+ {"id": 303, "hex": "3c65787472615f69645f34343e", "text": "<extra_id_44>", "n_bytes": 13, "is_special": true, "continuation": false}
305
+ {"id": 304, "hex": "3c65787472615f69645f34353e", "text": "<extra_id_45>", "n_bytes": 13, "is_special": true, "continuation": false}
306
+ {"id": 305, "hex": "3c65787472615f69645f34363e", "text": "<extra_id_46>", "n_bytes": 13, "is_special": true, "continuation": false}
307
+ {"id": 306, "hex": "3c65787472615f69645f34373e", "text": "<extra_id_47>", "n_bytes": 13, "is_special": true, "continuation": false}
308
+ {"id": 307, "hex": "3c65787472615f69645f34383e", "text": "<extra_id_48>", "n_bytes": 13, "is_special": true, "continuation": false}
309
+ {"id": 308, "hex": "3c65787472615f69645f34393e", "text": "<extra_id_49>", "n_bytes": 13, "is_special": true, "continuation": false}
310
+ {"id": 309, "hex": "3c65787472615f69645f35303e", "text": "<extra_id_50>", "n_bytes": 13, "is_special": true, "continuation": false}
311
+ {"id": 310, "hex": "3c65787472615f69645f35313e", "text": "<extra_id_51>", "n_bytes": 13, "is_special": true, "continuation": false}
312
+ {"id": 311, "hex": "3c65787472615f69645f35323e", "text": "<extra_id_52>", "n_bytes": 13, "is_special": true, "continuation": false}
313
+ {"id": 312, "hex": "3c65787472615f69645f35333e", "text": "<extra_id_53>", "n_bytes": 13, "is_special": true, "continuation": false}
314
+ {"id": 313, "hex": "3c65787472615f69645f35343e", "text": "<extra_id_54>", "n_bytes": 13, "is_special": true, "continuation": false}
315
+ {"id": 314, "hex": "3c65787472615f69645f35353e", "text": "<extra_id_55>", "n_bytes": 13, "is_special": true, "continuation": false}
316
+ {"id": 315, "hex": "3c65787472615f69645f35363e", "text": "<extra_id_56>", "n_bytes": 13, "is_special": true, "continuation": false}
317
+ {"id": 316, "hex": "3c65787472615f69645f35373e", "text": "<extra_id_57>", "n_bytes": 13, "is_special": true, "continuation": false}
318
+ {"id": 317, "hex": "3c65787472615f69645f35383e", "text": "<extra_id_58>", "n_bytes": 13, "is_special": true, "continuation": false}
319
+ {"id": 318, "hex": "3c65787472615f69645f35393e", "text": "<extra_id_59>", "n_bytes": 13, "is_special": true, "continuation": false}
320
+ {"id": 319, "hex": "3c65787472615f69645f36303e", "text": "<extra_id_60>", "n_bytes": 13, "is_special": true, "continuation": false}
321
+ {"id": 320, "hex": "3c65787472615f69645f36313e", "text": "<extra_id_61>", "n_bytes": 13, "is_special": true, "continuation": false}
322
+ {"id": 321, "hex": "3c65787472615f69645f36323e", "text": "<extra_id_62>", "n_bytes": 13, "is_special": true, "continuation": false}
323
+ {"id": 322, "hex": "3c65787472615f69645f36333e", "text": "<extra_id_63>", "n_bytes": 13, "is_special": true, "continuation": false}
324
+ {"id": 323, "hex": "3c65787472615f69645f36343e", "text": "<extra_id_64>", "n_bytes": 13, "is_special": true, "continuation": false}
325
+ {"id": 324, "hex": "3c65787472615f69645f36353e", "text": "<extra_id_65>", "n_bytes": 13, "is_special": true, "continuation": false}
326
+ {"id": 325, "hex": "3c65787472615f69645f36363e", "text": "<extra_id_66>", "n_bytes": 13, "is_special": true, "continuation": false}
327
+ {"id": 326, "hex": "3c65787472615f69645f36373e", "text": "<extra_id_67>", "n_bytes": 13, "is_special": true, "continuation": false}
328
+ {"id": 327, "hex": "3c65787472615f69645f36383e", "text": "<extra_id_68>", "n_bytes": 13, "is_special": true, "continuation": false}
329
+ {"id": 328, "hex": "3c65787472615f69645f36393e", "text": "<extra_id_69>", "n_bytes": 13, "is_special": true, "continuation": false}
330
+ {"id": 329, "hex": "3c65787472615f69645f37303e", "text": "<extra_id_70>", "n_bytes": 13, "is_special": true, "continuation": false}
331
+ {"id": 330, "hex": "3c65787472615f69645f37313e", "text": "<extra_id_71>", "n_bytes": 13, "is_special": true, "continuation": false}
332
+ {"id": 331, "hex": "3c65787472615f69645f37323e", "text": "<extra_id_72>", "n_bytes": 13, "is_special": true, "continuation": false}
333
+ {"id": 332, "hex": "3c65787472615f69645f37333e", "text": "<extra_id_73>", "n_bytes": 13, "is_special": true, "continuation": false}
334
+ {"id": 333, "hex": "3c65787472615f69645f37343e", "text": "<extra_id_74>", "n_bytes": 13, "is_special": true, "continuation": false}
335
+ {"id": 334, "hex": "3c65787472615f69645f37353e", "text": "<extra_id_75>", "n_bytes": 13, "is_special": true, "continuation": false}
336
+ {"id": 335, "hex": "3c65787472615f69645f37363e", "text": "<extra_id_76>", "n_bytes": 13, "is_special": true, "continuation": false}
337
+ {"id": 336, "hex": "3c65787472615f69645f37373e", "text": "<extra_id_77>", "n_bytes": 13, "is_special": true, "continuation": false}
338
+ {"id": 337, "hex": "3c65787472615f69645f37383e", "text": "<extra_id_78>", "n_bytes": 13, "is_special": true, "continuation": false}
339
+ {"id": 338, "hex": "3c65787472615f69645f37393e", "text": "<extra_id_79>", "n_bytes": 13, "is_special": true, "continuation": false}
340
+ {"id": 339, "hex": "3c65787472615f69645f38303e", "text": "<extra_id_80>", "n_bytes": 13, "is_special": true, "continuation": false}
341
+ {"id": 340, "hex": "3c65787472615f69645f38313e", "text": "<extra_id_81>", "n_bytes": 13, "is_special": true, "continuation": false}
342
+ {"id": 341, "hex": "3c65787472615f69645f38323e", "text": "<extra_id_82>", "n_bytes": 13, "is_special": true, "continuation": false}
343
+ {"id": 342, "hex": "3c65787472615f69645f38333e", "text": "<extra_id_83>", "n_bytes": 13, "is_special": true, "continuation": false}
344
+ {"id": 343, "hex": "3c65787472615f69645f38343e", "text": "<extra_id_84>", "n_bytes": 13, "is_special": true, "continuation": false}
345
+ {"id": 344, "hex": "3c65787472615f69645f38353e", "text": "<extra_id_85>", "n_bytes": 13, "is_special": true, "continuation": false}
346
+ {"id": 345, "hex": "3c65787472615f69645f38363e", "text": "<extra_id_86>", "n_bytes": 13, "is_special": true, "continuation": false}
347
+ {"id": 346, "hex": "3c65787472615f69645f38373e", "text": "<extra_id_87>", "n_bytes": 13, "is_special": true, "continuation": false}
348
+ {"id": 347, "hex": "3c65787472615f69645f38383e", "text": "<extra_id_88>", "n_bytes": 13, "is_special": true, "continuation": false}
349
+ {"id": 348, "hex": "3c65787472615f69645f38393e", "text": "<extra_id_89>", "n_bytes": 13, "is_special": true, "continuation": false}
350
+ {"id": 349, "hex": "3c65787472615f69645f39303e", "text": "<extra_id_90>", "n_bytes": 13, "is_special": true, "continuation": false}
351
+ {"id": 350, "hex": "3c65787472615f69645f39313e", "text": "<extra_id_91>", "n_bytes": 13, "is_special": true, "continuation": false}
352
+ {"id": 351, "hex": "3c65787472615f69645f39323e", "text": "<extra_id_92>", "n_bytes": 13, "is_special": true, "continuation": false}
353
+ {"id": 352, "hex": "3c65787472615f69645f39333e", "text": "<extra_id_93>", "n_bytes": 13, "is_special": true, "continuation": false}
354
+ {"id": 353, "hex": "3c65787472615f69645f39343e", "text": "<extra_id_94>", "n_bytes": 13, "is_special": true, "continuation": false}
355
+ {"id": 354, "hex": "3c65787472615f69645f39353e", "text": "<extra_id_95>", "n_bytes": 13, "is_special": true, "continuation": false}
356
+ {"id": 355, "hex": "3c65787472615f69645f39363e", "text": "<extra_id_96>", "n_bytes": 13, "is_special": true, "continuation": false}
357
+ {"id": 356, "hex": "3c65787472615f69645f39373e", "text": "<extra_id_97>", "n_bytes": 13, "is_special": true, "continuation": false}
358
+ {"id": 357, "hex": "3c65787472615f69645f39383e", "text": "<extra_id_98>", "n_bytes": 13, "is_special": true, "continuation": false}
359
+ {"id": 358, "hex": "3c65787472615f69645f39393e", "text": "<extra_id_99>", "n_bytes": 13, "is_special": true, "continuation": false}
360
+ {"id": 359, "hex": "3c65787472615f69645f3130303e", "text": "<extra_id_100>", "n_bytes": 14, "is_special": true, "continuation": false}
361
+ {"id": 360, "hex": "3c65787472615f69645f3130313e", "text": "<extra_id_101>", "n_bytes": 14, "is_special": true, "continuation": false}
362
+ {"id": 361, "hex": "3c65787472615f69645f3130323e", "text": "<extra_id_102>", "n_bytes": 14, "is_special": true, "continuation": false}
363
+ {"id": 362, "hex": "3c65787472615f69645f3130333e", "text": "<extra_id_103>", "n_bytes": 14, "is_special": true, "continuation": false}
364
+ {"id": 363, "hex": "3c65787472615f69645f3130343e", "text": "<extra_id_104>", "n_bytes": 14, "is_special": true, "continuation": false}
365
+ {"id": 364, "hex": "3c65787472615f69645f3130353e", "text": "<extra_id_105>", "n_bytes": 14, "is_special": true, "continuation": false}
366
+ {"id": 365, "hex": "3c65787472615f69645f3130363e", "text": "<extra_id_106>", "n_bytes": 14, "is_special": true, "continuation": false}
367
+ {"id": 366, "hex": "3c65787472615f69645f3130373e", "text": "<extra_id_107>", "n_bytes": 14, "is_special": true, "continuation": false}
368
+ {"id": 367, "hex": "3c65787472615f69645f3130383e", "text": "<extra_id_108>", "n_bytes": 14, "is_special": true, "continuation": false}
369
+ {"id": 368, "hex": "3c65787472615f69645f3130393e", "text": "<extra_id_109>", "n_bytes": 14, "is_special": true, "continuation": false}
370
+ {"id": 369, "hex": "3c65787472615f69645f3131303e", "text": "<extra_id_110>", "n_bytes": 14, "is_special": true, "continuation": false}
371
+ {"id": 370, "hex": "3c65787472615f69645f3131313e", "text": "<extra_id_111>", "n_bytes": 14, "is_special": true, "continuation": false}
372
+ {"id": 371, "hex": "3c65787472615f69645f3131323e", "text": "<extra_id_112>", "n_bytes": 14, "is_special": true, "continuation": false}
373
+ {"id": 372, "hex": "3c65787472615f69645f3131333e", "text": "<extra_id_113>", "n_bytes": 14, "is_special": true, "continuation": false}
374
+ {"id": 373, "hex": "3c65787472615f69645f3131343e", "text": "<extra_id_114>", "n_bytes": 14, "is_special": true, "continuation": false}
375
+ {"id": 374, "hex": "3c65787472615f69645f3131353e", "text": "<extra_id_115>", "n_bytes": 14, "is_special": true, "continuation": false}
376
+ {"id": 375, "hex": "3c65787472615f69645f3131363e", "text": "<extra_id_116>", "n_bytes": 14, "is_special": true, "continuation": false}
377
+ {"id": 376, "hex": "3c65787472615f69645f3131373e", "text": "<extra_id_117>", "n_bytes": 14, "is_special": true, "continuation": false}
378
+ {"id": 377, "hex": "3c65787472615f69645f3131383e", "text": "<extra_id_118>", "n_bytes": 14, "is_special": true, "continuation": false}
379
+ {"id": 378, "hex": "3c65787472615f69645f3131393e", "text": "<extra_id_119>", "n_bytes": 14, "is_special": true, "continuation": false}
380
+ {"id": 379, "hex": "3c65787472615f69645f3132303e", "text": "<extra_id_120>", "n_bytes": 14, "is_special": true, "continuation": false}
381
+ {"id": 380, "hex": "3c65787472615f69645f3132313e", "text": "<extra_id_121>", "n_bytes": 14, "is_special": true, "continuation": false}
382
+ {"id": 381, "hex": "3c65787472615f69645f3132323e", "text": "<extra_id_122>", "n_bytes": 14, "is_special": true, "continuation": false}
383
+ {"id": 382, "hex": "3c65787472615f69645f3132333e", "text": "<extra_id_123>", "n_bytes": 14, "is_special": true, "continuation": false}
384
+ {"id": 383, "hex": "3c65787472615f69645f3132343e", "text": "<extra_id_124>", "n_bytes": 14, "is_special": true, "continuation": false}
vocab_cl100k_base.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66ad1d4ce9b09d8cbba554e3f587a72cd39301118f571aed37de46b2df28973f
3
+ size 11466879
vocab_deepseek-v3.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3674b4ea77eaf60f28ebd59136cb09463aa09ad10b6826f81bf95403a3824192
3
+ size 14859381
vocab_gpt2.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
vocab_llama3.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b46a1db857fc2822c8c734da3e9d2af57d5ef3dedefea547c35db024a30efa4c
3
+ size 14742763
vocab_mistral-v03.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
vocab_o200k_base.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7ec297dfb425ff85bf28192041846ce96ef28587d5436f3169cf603b1447388
3
+ size 23322213
vocab_qwen3-newest.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:059b6135e6d26cb478c2515730e3e6fa7fb50c414c4941b8f4faf0b4a2e4d29f
3
+ size 29287052
vocab_smollm2.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
vocab_t5-unigram.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
vocab_xlmr.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9c016469074214b3eb5626c39663bc5e90d1043ae37225d1601aa2371cd4da5
3
+ size 30696496