Update tokenizer.json
Browse files- tokenizer.json +11 -2
tokenizer.json
CHANGED
|
@@ -28,7 +28,7 @@
|
|
| 28 |
"single_word": false,
|
| 29 |
"lstrip": false,
|
| 30 |
"rstrip": false,
|
| 31 |
-
"normalized":
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 255,
|
|
@@ -445,7 +445,16 @@
|
|
| 445 |
"special": true
|
| 446 |
}
|
| 447 |
],
|
| 448 |
-
"normalizer":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 449 |
"pre_tokenizer": {
|
| 450 |
"type": "Whitespace"
|
| 451 |
},
|
|
|
|
| 28 |
"single_word": false,
|
| 29 |
"lstrip": false,
|
| 30 |
"rstrip": false,
|
| 31 |
+
"normalized": true
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 255,
|
|
|
|
| 445 |
"special": true
|
| 446 |
}
|
| 447 |
],
|
| 448 |
+
"normalizer": {
|
| 449 |
+
"type": "Sequence",
|
| 450 |
+
"normalizers": [
|
| 451 |
+
{
|
| 452 |
+
"type": "Replace",
|
| 453 |
+
"pattern": { "String": " " },
|
| 454 |
+
"content": "[SPACE]"
|
| 455 |
+
}
|
| 456 |
+
]
|
| 457 |
+
},
|
| 458 |
"pre_tokenizer": {
|
| 459 |
"type": "Whitespace"
|
| 460 |
},
|