Upload tokenizer
Browse files- added_tokens.json +0 -0
- merges.txt +0 -0
- special_tokens_map.json +153 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_99>",
|
| 4 |
+
"<extra_id_98>",
|
| 5 |
+
"<extra_id_97>",
|
| 6 |
+
"<extra_id_96>",
|
| 7 |
+
"<extra_id_95>",
|
| 8 |
+
"<extra_id_94>",
|
| 9 |
+
"<extra_id_93>",
|
| 10 |
+
"<extra_id_92>",
|
| 11 |
+
"<extra_id_91>",
|
| 12 |
+
"<extra_id_90>",
|
| 13 |
+
"<extra_id_89>",
|
| 14 |
+
"<extra_id_88>",
|
| 15 |
+
"<extra_id_87>",
|
| 16 |
+
"<extra_id_86>",
|
| 17 |
+
"<extra_id_85>",
|
| 18 |
+
"<extra_id_84>",
|
| 19 |
+
"<extra_id_83>",
|
| 20 |
+
"<extra_id_82>",
|
| 21 |
+
"<extra_id_81>",
|
| 22 |
+
"<extra_id_80>",
|
| 23 |
+
"<extra_id_79>",
|
| 24 |
+
"<extra_id_78>",
|
| 25 |
+
"<extra_id_77>",
|
| 26 |
+
"<extra_id_76>",
|
| 27 |
+
"<extra_id_75>",
|
| 28 |
+
"<extra_id_74>",
|
| 29 |
+
"<extra_id_73>",
|
| 30 |
+
"<extra_id_72>",
|
| 31 |
+
"<extra_id_71>",
|
| 32 |
+
"<extra_id_70>",
|
| 33 |
+
"<extra_id_69>",
|
| 34 |
+
"<extra_id_68>",
|
| 35 |
+
"<extra_id_67>",
|
| 36 |
+
"<extra_id_66>",
|
| 37 |
+
"<extra_id_65>",
|
| 38 |
+
"<extra_id_64>",
|
| 39 |
+
"<extra_id_63>",
|
| 40 |
+
"<extra_id_62>",
|
| 41 |
+
"<extra_id_61>",
|
| 42 |
+
"<extra_id_60>",
|
| 43 |
+
"<extra_id_59>",
|
| 44 |
+
"<extra_id_58>",
|
| 45 |
+
"<extra_id_57>",
|
| 46 |
+
"<extra_id_56>",
|
| 47 |
+
"<extra_id_55>",
|
| 48 |
+
"<extra_id_54>",
|
| 49 |
+
"<extra_id_53>",
|
| 50 |
+
"<extra_id_52>",
|
| 51 |
+
"<extra_id_51>",
|
| 52 |
+
"<extra_id_50>",
|
| 53 |
+
"<extra_id_49>",
|
| 54 |
+
"<extra_id_48>",
|
| 55 |
+
"<extra_id_47>",
|
| 56 |
+
"<extra_id_46>",
|
| 57 |
+
"<extra_id_45>",
|
| 58 |
+
"<extra_id_44>",
|
| 59 |
+
"<extra_id_43>",
|
| 60 |
+
"<extra_id_42>",
|
| 61 |
+
"<extra_id_41>",
|
| 62 |
+
"<extra_id_40>",
|
| 63 |
+
"<extra_id_39>",
|
| 64 |
+
"<extra_id_38>",
|
| 65 |
+
"<extra_id_37>",
|
| 66 |
+
"<extra_id_36>",
|
| 67 |
+
"<extra_id_35>",
|
| 68 |
+
"<extra_id_34>",
|
| 69 |
+
"<extra_id_33>",
|
| 70 |
+
"<extra_id_32>",
|
| 71 |
+
"<extra_id_31>",
|
| 72 |
+
"<extra_id_30>",
|
| 73 |
+
"<extra_id_29>",
|
| 74 |
+
"<extra_id_28>",
|
| 75 |
+
"<extra_id_27>",
|
| 76 |
+
"<extra_id_26>",
|
| 77 |
+
"<extra_id_25>",
|
| 78 |
+
"<extra_id_24>",
|
| 79 |
+
"<extra_id_23>",
|
| 80 |
+
"<extra_id_22>",
|
| 81 |
+
"<extra_id_21>",
|
| 82 |
+
"<extra_id_20>",
|
| 83 |
+
"<extra_id_19>",
|
| 84 |
+
"<extra_id_18>",
|
| 85 |
+
"<extra_id_17>",
|
| 86 |
+
"<extra_id_16>",
|
| 87 |
+
"<extra_id_15>",
|
| 88 |
+
"<extra_id_14>",
|
| 89 |
+
"<extra_id_13>",
|
| 90 |
+
"<extra_id_12>",
|
| 91 |
+
"<extra_id_11>",
|
| 92 |
+
"<extra_id_10>",
|
| 93 |
+
"<extra_id_9>",
|
| 94 |
+
"<extra_id_8>",
|
| 95 |
+
"<extra_id_7>",
|
| 96 |
+
"<extra_id_6>",
|
| 97 |
+
"<extra_id_5>",
|
| 98 |
+
"<extra_id_4>",
|
| 99 |
+
"<extra_id_3>",
|
| 100 |
+
"<extra_id_2>",
|
| 101 |
+
"<extra_id_1>",
|
| 102 |
+
"<extra_id_0>"
|
| 103 |
+
],
|
| 104 |
+
"bos_token": {
|
| 105 |
+
"content": "<s>",
|
| 106 |
+
"lstrip": false,
|
| 107 |
+
"normalized": true,
|
| 108 |
+
"rstrip": false,
|
| 109 |
+
"single_word": false
|
| 110 |
+
},
|
| 111 |
+
"cls_token": {
|
| 112 |
+
"content": "<s>",
|
| 113 |
+
"lstrip": false,
|
| 114 |
+
"normalized": true,
|
| 115 |
+
"rstrip": false,
|
| 116 |
+
"single_word": false
|
| 117 |
+
},
|
| 118 |
+
"eos_token": {
|
| 119 |
+
"content": "</s>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false
|
| 124 |
+
},
|
| 125 |
+
"mask_token": {
|
| 126 |
+
"content": "<mask>",
|
| 127 |
+
"lstrip": true,
|
| 128 |
+
"normalized": true,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false
|
| 131 |
+
},
|
| 132 |
+
"pad_token": {
|
| 133 |
+
"content": "<pad>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": true,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false
|
| 138 |
+
},
|
| 139 |
+
"sep_token": {
|
| 140 |
+
"content": "</s>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": true,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false
|
| 145 |
+
},
|
| 146 |
+
"unk_token": {
|
| 147 |
+
"content": "<unk>",
|
| 148 |
+
"lstrip": false,
|
| 149 |
+
"normalized": true,
|
| 150 |
+
"rstrip": false,
|
| 151 |
+
"single_word": false
|
| 152 |
+
}
|
| 153 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|