Shaltiel commited on
Commit
068c29f
·
verified ·
1 Parent(s): b515ba9

Upload tokenizer.json

Browse files
Files changed (1) hide show
  1. tokenizer.json +1 -1
tokenizer.json CHANGED
@@ -89,7 +89,7 @@
89
  "pre_tokenizer": {
90
  "type": "Split",
91
  "pattern": {
92
- "Regex": "([\\s\\S])"
93
  },
94
  "behavior": "Removed",
95
  "invert": true
 
89
  "pre_tokenizer": {
90
  "type": "Split",
91
  "pattern": {
92
+ "Regex": "(\\[UNK\\]|[\\s\\S])"
93
  },
94
  "behavior": "Removed",
95
  "invert": true