Update tokenizer.json
Browse files- tokenizer.json +144 -0
tokenizer.json
CHANGED
|
@@ -20,6 +20,150 @@
|
|
| 20 |
"rstrip": false,
|
| 21 |
"normalized": true,
|
| 22 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
}
|
| 24 |
],
|
| 25 |
"normalizer": {
|
|
|
|
| 20 |
"rstrip": false,
|
| 21 |
"normalized": true,
|
| 22 |
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 100002,
|
| 26 |
+
"content": "<|fim▁hole|>",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"special": false
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 100003,
|
| 35 |
+
"content": "<|fim▁begin|>",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"special": false
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 100004,
|
| 44 |
+
"content": "<|fim▁end|>",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": true,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"id": 100005,
|
| 53 |
+
"content": "<|completion|>",
|
| 54 |
+
"single_word": false,
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"id": 100006,
|
| 62 |
+
"content": "<|User|>",
|
| 63 |
+
"single_word": false,
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"normalized": true,
|
| 67 |
+
"special": false
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"id": 100007,
|
| 71 |
+
"content": "<|Assistant|>",
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"lstrip": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"normalized": true,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"id": 100008,
|
| 80 |
+
"content": "<|EOT|>",
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"lstrip": false,
|
| 83 |
+
"rstrip": false,
|
| 84 |
+
"normalized": true,
|
| 85 |
+
"special": true
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"id": 100009,
|
| 89 |
+
"content": "<|tool▁calls▁begin|>",
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"lstrip": false,
|
| 92 |
+
"rstrip": false,
|
| 93 |
+
"normalized": true,
|
| 94 |
+
"special": false
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"id": 100010,
|
| 98 |
+
"content": "<|tool▁calls▁end|>",
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"lstrip": false,
|
| 101 |
+
"rstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"special": false
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"id": 100011,
|
| 107 |
+
"content": "<|tool▁call▁begin|>",
|
| 108 |
+
"single_word": false,
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"rstrip": false,
|
| 111 |
+
"normalized": true,
|
| 112 |
+
"special": false
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"id": 100012,
|
| 116 |
+
"content": "<|tool▁call▁end|>",
|
| 117 |
+
"single_word": false,
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"normalized": true,
|
| 121 |
+
"special": false
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"id": 100013,
|
| 125 |
+
"content": "<|tool▁outputs▁begin|>",
|
| 126 |
+
"single_word": false,
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"id": 100014,
|
| 134 |
+
"content": "<|tool▁outputs▁end|>",
|
| 135 |
+
"single_word": false,
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"normalized": true,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"id": 100015,
|
| 143 |
+
"content": "<|tool▁output▁begin|>",
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"lstrip": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"normalized": true,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"id": 100016,
|
| 152 |
+
"content": "<|tool▁output▁end|>",
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"lstrip": false,
|
| 155 |
+
"rstrip": false,
|
| 156 |
+
"normalized": true,
|
| 157 |
+
"special": false
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"id": 100017,
|
| 161 |
+
"content": "<|tool▁sep|>",
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"lstrip": false,
|
| 164 |
+
"rstrip": false,
|
| 165 |
+
"normalized": true,
|
| 166 |
+
"special": false
|
| 167 |
}
|
| 168 |
],
|
| 169 |
"normalizer": {
|