Upload tokenizer
Browse files- special_tokens_map.json +9 -0
- tokenizer.json +940 -0
- tokenizer_config.json +5 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<cls>",
|
| 3 |
+
"cls_token": "<cls>",
|
| 4 |
+
"eos_token": "<sep>",
|
| 5 |
+
"mask_token": "<mask>",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"sep_token": "<sep>",
|
| 8 |
+
"unk_token": "<unk>"
|
| 9 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,940 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "<pad>",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 1,
|
| 17 |
+
"content": "<cls>",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 2,
|
| 26 |
+
"content": "<sep>",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 3,
|
| 35 |
+
"content": "<unk>",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 4,
|
| 44 |
+
"content": "<mask>",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
],
|
| 52 |
+
"normalizer": null,
|
| 53 |
+
"pre_tokenizer": null,
|
| 54 |
+
"post_processor": {
|
| 55 |
+
"type": "TemplateProcessing",
|
| 56 |
+
"single": [
|
| 57 |
+
{
|
| 58 |
+
"SpecialToken": {
|
| 59 |
+
"id": "<cls>",
|
| 60 |
+
"type_id": 0
|
| 61 |
+
}
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"Sequence": {
|
| 65 |
+
"id": "A",
|
| 66 |
+
"type_id": 0
|
| 67 |
+
}
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"SpecialToken": {
|
| 71 |
+
"id": "<sep>",
|
| 72 |
+
"type_id": 0
|
| 73 |
+
}
|
| 74 |
+
}
|
| 75 |
+
],
|
| 76 |
+
"pair": [
|
| 77 |
+
{
|
| 78 |
+
"SpecialToken": {
|
| 79 |
+
"id": "<cls>",
|
| 80 |
+
"type_id": 0
|
| 81 |
+
}
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"Sequence": {
|
| 85 |
+
"id": "A",
|
| 86 |
+
"type_id": 0
|
| 87 |
+
}
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"SpecialToken": {
|
| 91 |
+
"id": "<sep>",
|
| 92 |
+
"type_id": 0
|
| 93 |
+
}
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"Sequence": {
|
| 97 |
+
"id": "B",
|
| 98 |
+
"type_id": 1
|
| 99 |
+
}
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"SpecialToken": {
|
| 103 |
+
"id": "<sep>",
|
| 104 |
+
"type_id": 1
|
| 105 |
+
}
|
| 106 |
+
}
|
| 107 |
+
],
|
| 108 |
+
"special_tokens": {
|
| 109 |
+
"<cls>": {
|
| 110 |
+
"id": "<cls>",
|
| 111 |
+
"ids": [
|
| 112 |
+
1
|
| 113 |
+
],
|
| 114 |
+
"tokens": [
|
| 115 |
+
"<cls>"
|
| 116 |
+
]
|
| 117 |
+
},
|
| 118 |
+
"<sep>": {
|
| 119 |
+
"id": "<sep>",
|
| 120 |
+
"ids": [
|
| 121 |
+
2
|
| 122 |
+
],
|
| 123 |
+
"tokens": [
|
| 124 |
+
"<sep>"
|
| 125 |
+
]
|
| 126 |
+
}
|
| 127 |
+
}
|
| 128 |
+
},
|
| 129 |
+
"decoder": {
|
| 130 |
+
"type": "Metaspace",
|
| 131 |
+
"replacement": "▁",
|
| 132 |
+
"add_prefix_space": true
|
| 133 |
+
},
|
| 134 |
+
"model": {
|
| 135 |
+
"type": "Unigram",
|
| 136 |
+
"unk_id": 3,
|
| 137 |
+
"vocab": [
|
| 138 |
+
[
|
| 139 |
+
"<pad>",
|
| 140 |
+
0.0
|
| 141 |
+
],
|
| 142 |
+
[
|
| 143 |
+
"<cls>",
|
| 144 |
+
0.0
|
| 145 |
+
],
|
| 146 |
+
[
|
| 147 |
+
"<sep>",
|
| 148 |
+
0.0
|
| 149 |
+
],
|
| 150 |
+
[
|
| 151 |
+
"<unk>",
|
| 152 |
+
0.0
|
| 153 |
+
],
|
| 154 |
+
[
|
| 155 |
+
"<mask>",
|
| 156 |
+
0.0
|
| 157 |
+
],
|
| 158 |
+
[
|
| 159 |
+
"Y",
|
| 160 |
+
-3.1509086450638755
|
| 161 |
+
],
|
| 162 |
+
[
|
| 163 |
+
"H",
|
| 164 |
+
-3.3896571454274156
|
| 165 |
+
],
|
| 166 |
+
[
|
| 167 |
+
"M",
|
| 168 |
+
-3.419833263673423
|
| 169 |
+
],
|
| 170 |
+
[
|
| 171 |
+
"Q",
|
| 172 |
+
-3.5122514279760804
|
| 173 |
+
],
|
| 174 |
+
[
|
| 175 |
+
"F",
|
| 176 |
+
-3.5318715443351483
|
| 177 |
+
],
|
| 178 |
+
[
|
| 179 |
+
"N",
|
| 180 |
+
-3.6735769356989
|
| 181 |
+
],
|
| 182 |
+
[
|
| 183 |
+
"A",
|
| 184 |
+
-3.7004076405792734
|
| 185 |
+
],
|
| 186 |
+
[
|
| 187 |
+
"L",
|
| 188 |
+
-3.7517736006002753
|
| 189 |
+
],
|
| 190 |
+
[
|
| 191 |
+
"C",
|
| 192 |
+
-3.82533728855746
|
| 193 |
+
],
|
| 194 |
+
[
|
| 195 |
+
"T",
|
| 196 |
+
-3.845094787136208
|
| 197 |
+
],
|
| 198 |
+
[
|
| 199 |
+
"R",
|
| 200 |
+
-3.85120522720325
|
| 201 |
+
],
|
| 202 |
+
[
|
| 203 |
+
"P",
|
| 204 |
+
-3.8944513102878826
|
| 205 |
+
],
|
| 206 |
+
[
|
| 207 |
+
"W",
|
| 208 |
+
-3.910536407899921
|
| 209 |
+
],
|
| 210 |
+
[
|
| 211 |
+
"K",
|
| 212 |
+
-3.9181905087306057
|
| 213 |
+
],
|
| 214 |
+
[
|
| 215 |
+
"E",
|
| 216 |
+
-3.9392286405437424
|
| 217 |
+
],
|
| 218 |
+
[
|
| 219 |
+
"G",
|
| 220 |
+
-3.9436969789665177
|
| 221 |
+
],
|
| 222 |
+
[
|
| 223 |
+
"S",
|
| 224 |
+
-3.9513056815431504
|
| 225 |
+
],
|
| 226 |
+
[
|
| 227 |
+
"V",
|
| 228 |
+
-3.9521272143039567
|
| 229 |
+
],
|
| 230 |
+
[
|
| 231 |
+
"D",
|
| 232 |
+
-4.053606203549702
|
| 233 |
+
],
|
| 234 |
+
[
|
| 235 |
+
"I",
|
| 236 |
+
-4.087833115224349
|
| 237 |
+
],
|
| 238 |
+
[
|
| 239 |
+
"AA",
|
| 240 |
+
-4.764966670027674
|
| 241 |
+
],
|
| 242 |
+
[
|
| 243 |
+
"LL",
|
| 244 |
+
-4.902886691904113
|
| 245 |
+
],
|
| 246 |
+
[
|
| 247 |
+
"LA",
|
| 248 |
+
-5.08072623495822
|
| 249 |
+
],
|
| 250 |
+
[
|
| 251 |
+
"AL",
|
| 252 |
+
-5.087271044534189
|
| 253 |
+
],
|
| 254 |
+
[
|
| 255 |
+
"SS",
|
| 256 |
+
-5.121051536194255
|
| 257 |
+
],
|
| 258 |
+
[
|
| 259 |
+
"LS",
|
| 260 |
+
-5.240240142812667
|
| 261 |
+
],
|
| 262 |
+
[
|
| 263 |
+
"SL",
|
| 264 |
+
-5.246958672682522
|
| 265 |
+
],
|
| 266 |
+
[
|
| 267 |
+
"GG",
|
| 268 |
+
-5.31104069359229
|
| 269 |
+
],
|
| 270 |
+
[
|
| 271 |
+
"AG",
|
| 272 |
+
-5.327169120628199
|
| 273 |
+
],
|
| 274 |
+
[
|
| 275 |
+
"VL",
|
| 276 |
+
-5.391035733278736
|
| 277 |
+
],
|
| 278 |
+
[
|
| 279 |
+
"RL",
|
| 280 |
+
-5.396912703019062
|
| 281 |
+
],
|
| 282 |
+
[
|
| 283 |
+
"AV",
|
| 284 |
+
-5.417974840306595
|
| 285 |
+
],
|
| 286 |
+
[
|
| 287 |
+
"GL",
|
| 288 |
+
-5.438738874872717
|
| 289 |
+
],
|
| 290 |
+
[
|
| 291 |
+
"LV",
|
| 292 |
+
-5.4539685415962555
|
| 293 |
+
],
|
| 294 |
+
[
|
| 295 |
+
"SG",
|
| 296 |
+
-5.468530821013996
|
| 297 |
+
],
|
| 298 |
+
[
|
| 299 |
+
"RR",
|
| 300 |
+
-5.469381686553186
|
| 301 |
+
],
|
| 302 |
+
[
|
| 303 |
+
"EL",
|
| 304 |
+
-5.487314422405181
|
| 305 |
+
],
|
| 306 |
+
[
|
| 307 |
+
"VA",
|
| 308 |
+
-5.500947343968374
|
| 309 |
+
],
|
| 310 |
+
[
|
| 311 |
+
"LR",
|
| 312 |
+
-5.504465608087704
|
| 313 |
+
],
|
| 314 |
+
[
|
| 315 |
+
"GA",
|
| 316 |
+
-5.508572577172163
|
| 317 |
+
],
|
| 318 |
+
[
|
| 319 |
+
"SA",
|
| 320 |
+
-5.509497866677481
|
| 321 |
+
],
|
| 322 |
+
[
|
| 323 |
+
"EE",
|
| 324 |
+
-5.509638117132358
|
| 325 |
+
],
|
| 326 |
+
[
|
| 327 |
+
"LP",
|
| 328 |
+
-5.525125791450426
|
| 329 |
+
],
|
| 330 |
+
[
|
| 331 |
+
"LG",
|
| 332 |
+
-5.531523151805965
|
| 333 |
+
],
|
| 334 |
+
[
|
| 335 |
+
"TL",
|
| 336 |
+
-5.550336580253715
|
| 337 |
+
],
|
| 338 |
+
[
|
| 339 |
+
"AS",
|
| 340 |
+
-5.555359709285966
|
| 341 |
+
],
|
| 342 |
+
[
|
| 343 |
+
"VV",
|
| 344 |
+
-5.5822783949387205
|
| 345 |
+
],
|
| 346 |
+
[
|
| 347 |
+
"LT",
|
| 348 |
+
-5.5949437276928276
|
| 349 |
+
],
|
| 350 |
+
[
|
| 351 |
+
"LD",
|
| 352 |
+
-5.609175705941702
|
| 353 |
+
],
|
| 354 |
+
[
|
| 355 |
+
"GS",
|
| 356 |
+
-5.615707589762941
|
| 357 |
+
],
|
| 358 |
+
[
|
| 359 |
+
"TA",
|
| 360 |
+
-5.6212468269382665
|
| 361 |
+
],
|
| 362 |
+
[
|
| 363 |
+
"LE",
|
| 364 |
+
-5.62152407771382
|
| 365 |
+
],
|
| 366 |
+
[
|
| 367 |
+
"DL",
|
| 368 |
+
-5.625455355831432
|
| 369 |
+
],
|
| 370 |
+
[
|
| 371 |
+
"KK",
|
| 372 |
+
-5.632789431683037
|
| 373 |
+
],
|
| 374 |
+
[
|
| 375 |
+
"EA",
|
| 376 |
+
-5.635793018508904
|
| 377 |
+
],
|
| 378 |
+
[
|
| 379 |
+
"IL",
|
| 380 |
+
-5.6365381446185285
|
| 381 |
+
],
|
| 382 |
+
[
|
| 383 |
+
"GV",
|
| 384 |
+
-5.674808795328973
|
| 385 |
+
],
|
| 386 |
+
[
|
| 387 |
+
"AR",
|
| 388 |
+
-5.681247789262706
|
| 389 |
+
],
|
| 390 |
+
[
|
| 391 |
+
"SV",
|
| 392 |
+
-5.6919674499343085
|
| 393 |
+
],
|
| 394 |
+
[
|
| 395 |
+
"RA",
|
| 396 |
+
-5.70230195746182
|
| 397 |
+
],
|
| 398 |
+
[
|
| 399 |
+
"ST",
|
| 400 |
+
-5.705482521677933
|
| 401 |
+
],
|
| 402 |
+
[
|
| 403 |
+
"AE",
|
| 404 |
+
-5.707097244257659
|
| 405 |
+
],
|
| 406 |
+
[
|
| 407 |
+
"DG",
|
| 408 |
+
-5.7111206266490395
|
| 409 |
+
],
|
| 410 |
+
[
|
| 411 |
+
"KL",
|
| 412 |
+
-5.714200191449681
|
| 413 |
+
],
|
| 414 |
+
[
|
| 415 |
+
"PA",
|
| 416 |
+
-5.714888070036569
|
| 417 |
+
],
|
| 418 |
+
[
|
| 419 |
+
"AT",
|
| 420 |
+
-5.7387016264645485
|
| 421 |
+
],
|
| 422 |
+
[
|
| 423 |
+
"VS",
|
| 424 |
+
-5.740918194807335
|
| 425 |
+
],
|
| 426 |
+
[
|
| 427 |
+
"DA",
|
| 428 |
+
-5.747346276581707
|
| 429 |
+
],
|
| 430 |
+
[
|
| 431 |
+
"SP",
|
| 432 |
+
-5.750453122200705
|
| 433 |
+
],
|
| 434 |
+
[
|
| 435 |
+
"IS",
|
| 436 |
+
-5.7575142466303255
|
| 437 |
+
],
|
| 438 |
+
[
|
| 439 |
+
"GR",
|
| 440 |
+
-5.757690327764845
|
| 441 |
+
],
|
| 442 |
+
[
|
| 443 |
+
"LI",
|
| 444 |
+
-5.76013806021334
|
| 445 |
+
],
|
| 446 |
+
[
|
| 447 |
+
"TG",
|
| 448 |
+
-5.761512737903605
|
| 449 |
+
],
|
| 450 |
+
[
|
| 451 |
+
"TV",
|
| 452 |
+
-5.764206078890442
|
| 453 |
+
],
|
| 454 |
+
[
|
| 455 |
+
"IA",
|
| 456 |
+
-5.777844220177171
|
| 457 |
+
],
|
| 458 |
+
[
|
| 459 |
+
"AD",
|
| 460 |
+
-5.780310267356683
|
| 461 |
+
],
|
| 462 |
+
[
|
| 463 |
+
"TT",
|
| 464 |
+
-5.785480977584342
|
| 465 |
+
],
|
| 466 |
+
[
|
| 467 |
+
"TS",
|
| 468 |
+
-5.791507570316087
|
| 469 |
+
],
|
| 470 |
+
[
|
| 471 |
+
"LK",
|
| 472 |
+
-5.802866544052941
|
| 473 |
+
],
|
| 474 |
+
[
|
| 475 |
+
"EK",
|
| 476 |
+
-5.804278043814918
|
| 477 |
+
],
|
| 478 |
+
[
|
| 479 |
+
"GT",
|
| 480 |
+
-5.819460987630665
|
| 481 |
+
],
|
| 482 |
+
[
|
| 483 |
+
"PP",
|
| 484 |
+
-5.821173747611947
|
| 485 |
+
],
|
| 486 |
+
[
|
| 487 |
+
"KE",
|
| 488 |
+
-5.822033413758428
|
| 489 |
+
],
|
| 490 |
+
[
|
| 491 |
+
"ER",
|
| 492 |
+
-5.852332647299409
|
| 493 |
+
],
|
| 494 |
+
[
|
| 495 |
+
"SD",
|
| 496 |
+
-5.852838901980473
|
| 497 |
+
],
|
| 498 |
+
[
|
| 499 |
+
"SI",
|
| 500 |
+
-5.8533832214242345
|
| 501 |
+
],
|
| 502 |
+
[
|
| 503 |
+
"PS",
|
| 504 |
+
-5.854586170941655
|
| 505 |
+
],
|
| 506 |
+
[
|
| 507 |
+
"AP",
|
| 508 |
+
-5.856858689030043
|
| 509 |
+
],
|
| 510 |
+
[
|
| 511 |
+
"DE",
|
| 512 |
+
-5.867028022084829
|
| 513 |
+
],
|
| 514 |
+
[
|
| 515 |
+
"GD",
|
| 516 |
+
-5.876378483403268
|
| 517 |
+
],
|
| 518 |
+
[
|
| 519 |
+
"DD",
|
| 520 |
+
-5.876725852666299
|
| 521 |
+
],
|
| 522 |
+
[
|
| 523 |
+
"NL",
|
| 524 |
+
-5.884448903872826
|
| 525 |
+
],
|
| 526 |
+
[
|
| 527 |
+
"VT",
|
| 528 |
+
-5.88772386460313
|
| 529 |
+
],
|
| 530 |
+
[
|
| 531 |
+
"PL",
|
| 532 |
+
-5.907796388921314
|
| 533 |
+
],
|
| 534 |
+
[
|
| 535 |
+
"RS",
|
| 536 |
+
-5.909472604917513
|
| 537 |
+
],
|
| 538 |
+
[
|
| 539 |
+
"TP",
|
| 540 |
+
-5.910221549171844
|
| 541 |
+
],
|
| 542 |
+
[
|
| 543 |
+
"EI",
|
| 544 |
+
-5.916003495337167
|
| 545 |
+
],
|
| 546 |
+
[
|
| 547 |
+
"SR",
|
| 548 |
+
-5.918245244245625
|
| 549 |
+
],
|
| 550 |
+
[
|
| 551 |
+
"GE",
|
| 552 |
+
-5.918941142869885
|
| 553 |
+
],
|
| 554 |
+
[
|
| 555 |
+
"VD",
|
| 556 |
+
-5.924154015576642
|
| 557 |
+
],
|
| 558 |
+
[
|
| 559 |
+
"ID",
|
| 560 |
+
-5.927743633953453
|
| 561 |
+
],
|
| 562 |
+
[
|
| 563 |
+
"EV",
|
| 564 |
+
-5.931109554224724
|
| 565 |
+
],
|
| 566 |
+
[
|
| 567 |
+
"VG",
|
| 568 |
+
-5.936172020091348
|
| 569 |
+
],
|
| 570 |
+
[
|
| 571 |
+
"VE",
|
| 572 |
+
-5.9407666092559595
|
| 573 |
+
],
|
| 574 |
+
[
|
| 575 |
+
"GI",
|
| 576 |
+
-5.953825669400469
|
| 577 |
+
],
|
| 578 |
+
[
|
| 579 |
+
"DV",
|
| 580 |
+
-5.964826749154037
|
| 581 |
+
],
|
| 582 |
+
[
|
| 583 |
+
"KI",
|
| 584 |
+
-5.965011602414927
|
| 585 |
+
],
|
| 586 |
+
[
|
| 587 |
+
"AI",
|
| 588 |
+
-5.966134585178457
|
| 589 |
+
],
|
| 590 |
+
[
|
| 591 |
+
"IV",
|
| 592 |
+
-5.966562340591041
|
| 593 |
+
],
|
| 594 |
+
[
|
| 595 |
+
"RV",
|
| 596 |
+
-5.968891258580745
|
| 597 |
+
],
|
| 598 |
+
[
|
| 599 |
+
"FL",
|
| 600 |
+
-5.973183082312524
|
| 601 |
+
],
|
| 602 |
+
[
|
| 603 |
+
"SE",
|
| 604 |
+
-5.978660102843701
|
| 605 |
+
],
|
| 606 |
+
[
|
| 607 |
+
"IE",
|
| 608 |
+
-5.990855196049141
|
| 609 |
+
],
|
| 610 |
+
[
|
| 611 |
+
"QL",
|
| 612 |
+
-5.994359870798313
|
| 613 |
+
],
|
| 614 |
+
[
|
| 615 |
+
"PV",
|
| 616 |
+
-5.995163841048182
|
| 617 |
+
],
|
| 618 |
+
[
|
| 619 |
+
"RE",
|
| 620 |
+
-5.9975055476878065
|
| 621 |
+
],
|
| 622 |
+
[
|
| 623 |
+
"ED",
|
| 624 |
+
-6.015188056772153
|
| 625 |
+
],
|
| 626 |
+
[
|
| 627 |
+
"KA",
|
| 628 |
+
-6.01643176845711
|
| 629 |
+
],
|
| 630 |
+
[
|
| 631 |
+
"LF",
|
| 632 |
+
-6.0171694056170075
|
| 633 |
+
],
|
| 634 |
+
[
|
| 635 |
+
"IG",
|
| 636 |
+
-6.020600912983243
|
| 637 |
+
],
|
| 638 |
+
[
|
| 639 |
+
"RG",
|
| 640 |
+
-6.022579399372601
|
| 641 |
+
],
|
| 642 |
+
[
|
| 643 |
+
"II",
|
| 644 |
+
-6.026894696516262
|
| 645 |
+
],
|
| 646 |
+
[
|
| 647 |
+
"PG",
|
| 648 |
+
-6.027207909959376
|
| 649 |
+
],
|
| 650 |
+
[
|
| 651 |
+
"VR",
|
| 652 |
+
-6.03105386262591
|
| 653 |
+
],
|
| 654 |
+
[
|
| 655 |
+
"KS",
|
| 656 |
+
-6.039104198463601
|
| 657 |
+
],
|
| 658 |
+
[
|
| 659 |
+
"IT",
|
| 660 |
+
-6.044874540149573
|
| 661 |
+
],
|
| 662 |
+
[
|
| 663 |
+
"LQ",
|
| 664 |
+
-6.0719229057700765
|
| 665 |
+
],
|
| 666 |
+
[
|
| 667 |
+
"VP",
|
| 668 |
+
-6.073861256741292
|
| 669 |
+
],
|
| 670 |
+
[
|
| 671 |
+
"NG",
|
| 672 |
+
-6.087855724157491
|
| 673 |
+
],
|
| 674 |
+
[
|
| 675 |
+
"DS",
|
| 676 |
+
-6.093824372411833
|
| 677 |
+
],
|
| 678 |
+
[
|
| 679 |
+
"EG",
|
| 680 |
+
-6.095757478155381
|
| 681 |
+
],
|
| 682 |
+
[
|
| 683 |
+
"GK",
|
| 684 |
+
-6.099067993197011
|
| 685 |
+
],
|
| 686 |
+
[
|
| 687 |
+
"ES",
|
| 688 |
+
-6.101068768641547
|
| 689 |
+
],
|
| 690 |
+
[
|
| 691 |
+
"TI",
|
| 692 |
+
-6.103630143225411
|
| 693 |
+
],
|
| 694 |
+
[
|
| 695 |
+
"KT",
|
| 696 |
+
-6.108252739228014
|
| 697 |
+
],
|
| 698 |
+
[
|
| 699 |
+
"ET",
|
| 700 |
+
-6.1155235309558655
|
| 701 |
+
],
|
| 702 |
+
[
|
| 703 |
+
"VI",
|
| 704 |
+
-6.115661963794853
|
| 705 |
+
],
|
| 706 |
+
[
|
| 707 |
+
"DI",
|
| 708 |
+
-6.120589231585161
|
| 709 |
+
],
|
| 710 |
+
[
|
| 711 |
+
"RP",
|
| 712 |
+
-6.121380333766949
|
| 713 |
+
],
|
| 714 |
+
[
|
| 715 |
+
"SF",
|
| 716 |
+
-6.133861651537437
|
| 717 |
+
],
|
| 718 |
+
[
|
| 719 |
+
"PE",
|
| 720 |
+
-6.138418425045256
|
| 721 |
+
],
|
| 722 |
+
[
|
| 723 |
+
"FS",
|
| 724 |
+
-6.139131547464277
|
| 725 |
+
],
|
| 726 |
+
[
|
| 727 |
+
"RI",
|
| 728 |
+
-6.1391477529387615
|
| 729 |
+
],
|
| 730 |
+
[
|
| 731 |
+
"LN",
|
| 732 |
+
-6.1404965267449985
|
| 733 |
+
],
|
| 734 |
+
[
|
| 735 |
+
"NS",
|
| 736 |
+
-6.144657817213831
|
| 737 |
+
],
|
| 738 |
+
[
|
| 739 |
+
"KV",
|
| 740 |
+
-6.152332752044504
|
| 741 |
+
],
|
| 742 |
+
[
|
| 743 |
+
"RD",
|
| 744 |
+
-6.154617866692302
|
| 745 |
+
],
|
| 746 |
+
[
|
| 747 |
+
"KR",
|
| 748 |
+
-6.155330258447307
|
| 749 |
+
],
|
| 750 |
+
[
|
| 751 |
+
"KD",
|
| 752 |
+
-6.1652649821258905
|
| 753 |
+
],
|
| 754 |
+
[
|
| 755 |
+
"SK",
|
| 756 |
+
-6.1693163139654725
|
| 757 |
+
],
|
| 758 |
+
[
|
| 759 |
+
"IP",
|
| 760 |
+
-6.1828230004197025
|
| 761 |
+
],
|
| 762 |
+
[
|
| 763 |
+
"NI",
|
| 764 |
+
-6.184849882544997
|
| 765 |
+
],
|
| 766 |
+
[
|
| 767 |
+
"DP",
|
| 768 |
+
-6.186014251325707
|
| 769 |
+
],
|
| 770 |
+
[
|
| 771 |
+
"QA",
|
| 772 |
+
-6.191570123841911
|
| 773 |
+
],
|
| 774 |
+
[
|
| 775 |
+
"PD",
|
| 776 |
+
-6.194909821917465
|
| 777 |
+
],
|
| 778 |
+
[
|
| 779 |
+
"TD",
|
| 780 |
+
-6.196392015508456
|
| 781 |
+
],
|
| 782 |
+
[
|
| 783 |
+
"RT",
|
| 784 |
+
-6.209516518529492
|
| 785 |
+
],
|
| 786 |
+
[
|
| 787 |
+
"IK",
|
| 788 |
+
-6.214740590660165
|
| 789 |
+
],
|
| 790 |
+
[
|
| 791 |
+
"PT",
|
| 792 |
+
-6.225990661106273
|
| 793 |
+
],
|
| 794 |
+
[
|
| 795 |
+
"KN",
|
| 796 |
+
-6.239211240911878
|
| 797 |
+
],
|
| 798 |
+
[
|
| 799 |
+
"RK",
|
| 800 |
+
-6.242072582821788
|
| 801 |
+
],
|
| 802 |
+
[
|
| 803 |
+
"DR",
|
| 804 |
+
-6.254359548545143
|
| 805 |
+
],
|
| 806 |
+
[
|
| 807 |
+
"NA",
|
| 808 |
+
-6.26545887359997
|
| 809 |
+
],
|
| 810 |
+
[
|
| 811 |
+
"SN",
|
| 812 |
+
-6.285562575311767
|
| 813 |
+
],
|
| 814 |
+
[
|
| 815 |
+
"GF",
|
| 816 |
+
-6.28571824602113
|
| 817 |
+
],
|
| 818 |
+
[
|
| 819 |
+
"TE",
|
| 820 |
+
-6.309775318855182
|
| 821 |
+
],
|
| 822 |
+
[
|
| 823 |
+
"IR",
|
| 824 |
+
-6.31828807247183
|
| 825 |
+
],
|
| 826 |
+
[
|
| 827 |
+
"EN",
|
| 828 |
+
-6.318322128704557
|
| 829 |
+
],
|
| 830 |
+
[
|
| 831 |
+
"KG",
|
| 832 |
+
-6.32060657047373
|
| 833 |
+
],
|
| 834 |
+
[
|
| 835 |
+
"NN",
|
| 836 |
+
-6.323083715957198
|
| 837 |
+
],
|
| 838 |
+
[
|
| 839 |
+
"KP",
|
| 840 |
+
-6.341333299431328
|
| 841 |
+
],
|
| 842 |
+
[
|
| 843 |
+
"GP",
|
| 844 |
+
-6.3491864918774095
|
| 845 |
+
],
|
| 846 |
+
[
|
| 847 |
+
"NP",
|
| 848 |
+
-6.34927814518192
|
| 849 |
+
],
|
| 850 |
+
[
|
| 851 |
+
"YL",
|
| 852 |
+
-6.351753043279688
|
| 853 |
+
],
|
| 854 |
+
[
|
| 855 |
+
"IN",
|
| 856 |
+
-6.3572834033221515
|
| 857 |
+
],
|
| 858 |
+
[
|
| 859 |
+
"NV",
|
| 860 |
+
-6.360839268616893
|
| 861 |
+
],
|
| 862 |
+
[
|
| 863 |
+
"DT",
|
| 864 |
+
-6.375617439783092
|
| 865 |
+
],
|
| 866 |
+
[
|
| 867 |
+
"AK",
|
| 868 |
+
-6.375711508198858
|
| 869 |
+
],
|
| 870 |
+
[
|
| 871 |
+
"EQ",
|
| 872 |
+
-6.376112537075828
|
| 873 |
+
],
|
| 874 |
+
[
|
| 875 |
+
"FG",
|
| 876 |
+
-6.386837832927128
|
| 877 |
+
],
|
| 878 |
+
[
|
| 879 |
+
"FD",
|
| 880 |
+
-6.394930765846015
|
| 881 |
+
],
|
| 882 |
+
[
|
| 883 |
+
"ND",
|
| 884 |
+
-6.398211625118337
|
| 885 |
+
],
|
| 886 |
+
[
|
| 887 |
+
"GN",
|
| 888 |
+
-6.40179470374931
|
| 889 |
+
],
|
| 890 |
+
[
|
| 891 |
+
"VK",
|
| 892 |
+
-6.402752834893931
|
| 893 |
+
],
|
| 894 |
+
[
|
| 895 |
+
"FV",
|
| 896 |
+
-6.409266328977472
|
| 897 |
+
],
|
| 898 |
+
[
|
| 899 |
+
"TR",
|
| 900 |
+
-6.416946537362946
|
| 901 |
+
],
|
| 902 |
+
[
|
| 903 |
+
"VF",
|
| 904 |
+
-6.417794842397651
|
| 905 |
+
],
|
| 906 |
+
[
|
| 907 |
+
"SQ",
|
| 908 |
+
-6.446275702521779
|
| 909 |
+
],
|
| 910 |
+
[
|
| 911 |
+
"PR",
|
| 912 |
+
-6.467885446120821
|
| 913 |
+
],
|
| 914 |
+
[
|
| 915 |
+
"IF",
|
| 916 |
+
-6.468539334368343
|
| 917 |
+
],
|
| 918 |
+
[
|
| 919 |
+
"X",
|
| 920 |
+
-7.375634428511613
|
| 921 |
+
],
|
| 922 |
+
[
|
| 923 |
+
"B",
|
| 924 |
+
-14.220849172973876
|
| 925 |
+
],
|
| 926 |
+
[
|
| 927 |
+
"Z",
|
| 928 |
+
-15.447814045084268
|
| 929 |
+
],
|
| 930 |
+
[
|
| 931 |
+
"U",
|
| 932 |
+
-16.127265163683706
|
| 933 |
+
],
|
| 934 |
+
[
|
| 935 |
+
"O",
|
| 936 |
+
-19.622373241931182
|
| 937 |
+
]
|
| 938 |
+
]
|
| 939 |
+
}
|
| 940 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 4 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 5 |
+
}
|