Upload tokenizer.json
Browse files- tokenizer.json +57 -6
tokenizer.json
CHANGED
|
@@ -2,7 +2,62 @@
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": null,
|
| 4 |
"padding": null,
|
| 5 |
-
"added_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"normalizer": null,
|
| 7 |
"pre_tokenizer": {
|
| 8 |
"type": "BertPreTokenizer"
|
|
@@ -49,11 +104,7 @@
|
|
| 49 |
}
|
| 50 |
}
|
| 51 |
},
|
| 52 |
-
"decoder":
|
| 53 |
-
"type": "WordPiece",
|
| 54 |
-
"prefix": "",
|
| 55 |
-
"cleanup": true
|
| 56 |
-
},
|
| 57 |
"model": {
|
| 58 |
"type": "WordPiece",
|
| 59 |
"unk_token": "<unk>",
|
|
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": null,
|
| 4 |
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "<unk>",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 1,
|
| 17 |
+
"content": "<pad>",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 2,
|
| 26 |
+
"content": "<mask>",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 3,
|
| 35 |
+
"content": "<cls>",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 4105,
|
| 44 |
+
"content": "<eos>",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"id": 4106,
|
| 53 |
+
"content": "<bos>",
|
| 54 |
+
"single_word": false,
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"special": true
|
| 59 |
+
}
|
| 60 |
+
],
|
| 61 |
"normalizer": null,
|
| 62 |
"pre_tokenizer": {
|
| 63 |
"type": "BertPreTokenizer"
|
|
|
|
| 104 |
}
|
| 105 |
}
|
| 106 |
},
|
| 107 |
+
"decoder": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 108 |
"model": {
|
| 109 |
"type": "WordPiece",
|
| 110 |
"unk_token": "<unk>",
|