Commit
·
f9b6141
1
Parent(s):
e3d89d4
Upload tokenizer
Browse files- special_tokens_map.json +8 -0
- tokenizer.json +54 -0
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,12 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"cls_token": "<cls>",
|
| 4 |
"eos_token": "</s>",
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<url>",
|
| 4 |
+
"<email>",
|
| 5 |
+
"<number>",
|
| 6 |
+
"<digit>",
|
| 7 |
+
"<punc>",
|
| 8 |
+
"<foreign>"
|
| 9 |
+
],
|
| 10 |
"bos_token": "<s>",
|
| 11 |
"cls_token": "<cls>",
|
| 12 |
"eos_token": "</s>",
|
tokenizer.json
CHANGED
|
@@ -65,6 +65,60 @@
|
|
| 65 |
"rstrip": false,
|
| 66 |
"normalized": false,
|
| 67 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 68 |
}
|
| 69 |
],
|
| 70 |
"normalizer": null,
|
|
|
|
| 65 |
"rstrip": false,
|
| 66 |
"normalized": false,
|
| 67 |
"special": true
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"id": 32000,
|
| 71 |
+
"content": "<url>",
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"lstrip": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"normalized": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"id": 32001,
|
| 80 |
+
"content": "<email>",
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"lstrip": false,
|
| 83 |
+
"rstrip": false,
|
| 84 |
+
"normalized": false,
|
| 85 |
+
"special": true
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"id": 32002,
|
| 89 |
+
"content": "<number>",
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"lstrip": false,
|
| 92 |
+
"rstrip": false,
|
| 93 |
+
"normalized": false,
|
| 94 |
+
"special": true
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"id": 32003,
|
| 98 |
+
"content": "<digit>",
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"lstrip": false,
|
| 101 |
+
"rstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"special": true
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"id": 32004,
|
| 107 |
+
"content": "<punc>",
|
| 108 |
+
"single_word": false,
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"rstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"special": true
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"id": 32005,
|
| 116 |
+
"content": "<foreign>",
|
| 117 |
+
"single_word": false,
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"special": true
|
| 122 |
}
|
| 123 |
],
|
| 124 |
"normalizer": null,
|