vladislavbro commited on
Commit
ffe6343
·
verified ·
1 Parent(s): 0881708

Update tokenizer.json

Browse files
Files changed (1) hide show
  1. tokenizer.json +13 -1
tokenizer.json CHANGED
@@ -447,7 +447,19 @@
447
  ],
448
  "normalizer": null,
449
  "pre_tokenizer": {
450
- "type": "Whitespace"
 
 
 
 
 
 
 
 
 
 
 
 
451
  },
452
  "post_processor": {
453
  "type": "TemplateProcessing",
 
447
  ],
448
  "normalizer": null,
449
  "pre_tokenizer": {
450
+ "type": "Sequence",
451
+ "pretokenizers": [
452
+ {
453
+ "type": "Replace",
454
+ "pattern": {
455
+ "String": " "
456
+ },
457
+ "content": "[SPACE]"
458
+ },
459
+ {
460
+ "type": "Whitespace"
461
+ }
462
+ ]
463
  },
464
  "post_processor": {
465
  "type": "TemplateProcessing",