Commit ·
802ec7e
1
Parent(s): 4b4f58c
Upload tokenizer
Browse files- tokenizer.json +52 -2
tokenizer.json
CHANGED
|
@@ -458,7 +458,32 @@
|
|
| 458 |
"mar": 396,
|
| 459 |
"name": 397,
|
| 460 |
"prive": 398,
|
| 461 |
-
"rs": 399
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 462 |
},
|
| 463 |
"merges": [
|
| 464 |
"a r",
|
|
@@ -805,7 +830,32 @@
|
|
| 805 |
"m ar",
|
| 806 |
"n ame",
|
| 807 |
"p rive",
|
| 808 |
-
"r s"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 809 |
]
|
| 810 |
}
|
| 811 |
}
|
|
|
|
| 458 |
"mar": 396,
|
| 459 |
"name": 397,
|
| 460 |
"prive": 398,
|
| 461 |
+
"rs": 399,
|
| 462 |
+
"sit": 400,
|
| 463 |
+
"uprive": 401,
|
| 464 |
+
"was": 402,
|
| 465 |
+
"ĠCAUS": 403,
|
| 466 |
+
"ĠIBM": 404,
|
| 467 |
+
"Ġsle": 405,
|
| 468 |
+
"ĠDen": 406,
|
| 469 |
+
"Ġwate": 407,
|
| 470 |
+
"Ġplac": 408,
|
| 471 |
+
"pers": 409,
|
| 472 |
+
"Ġmai": 410,
|
| 473 |
+
"ach": 411,
|
| 474 |
+
"Ġoff": 412,
|
| 475 |
+
"Ġreach": 413,
|
| 476 |
+
"Ġwhite": 414,
|
| 477 |
+
"mark": 415,
|
| 478 |
+
"upriver": 416,
|
| 479 |
+
"wash": 417,
|
| 480 |
+
"Ġsleep": 418,
|
| 481 |
+
"ĠDenmark": 419,
|
| 482 |
+
"Ġwater": 420,
|
| 483 |
+
"Ġplace": 421,
|
| 484 |
+
"person": 422,
|
| 485 |
+
"Ġmail": 423,
|
| 486 |
+
"Ġoffice": 424
|
| 487 |
},
|
| 488 |
"merges": [
|
| 489 |
"a r",
|
|
|
|
| 830 |
"m ar",
|
| 831 |
"n ame",
|
| 832 |
"p rive",
|
| 833 |
+
"r s",
|
| 834 |
+
"s it",
|
| 835 |
+
"u prive",
|
| 836 |
+
"w as",
|
| 837 |
+
"ĠC AUS",
|
| 838 |
+
"ĠI BM",
|
| 839 |
+
"Ġs le",
|
| 840 |
+
"ĠD en",
|
| 841 |
+
"Ġw ate",
|
| 842 |
+
"Ġp lac",
|
| 843 |
+
"pe rs",
|
| 844 |
+
"Ġm ai",
|
| 845 |
+
"ac h",
|
| 846 |
+
"Ġo ff",
|
| 847 |
+
"Ġre ach",
|
| 848 |
+
"Ġwh ite",
|
| 849 |
+
"mar k",
|
| 850 |
+
"uprive r",
|
| 851 |
+
"was h",
|
| 852 |
+
"Ġsle ep",
|
| 853 |
+
"ĠDen mark",
|
| 854 |
+
"Ġwate r",
|
| 855 |
+
"Ġplac e",
|
| 856 |
+
"pers on",
|
| 857 |
+
"Ġmai l",
|
| 858 |
+
"Ġoff ice"
|
| 859 |
]
|
| 860 |
}
|
| 861 |
}
|