Commit
•
d3247da
1
Parent(s):
fe78f08
Upload tokenizer
Browse files- vocab.json +36 -36
vocab.json
CHANGED
|
@@ -1,40 +1,40 @@
|
|
| 1 |
{
|
| 2 |
"[PAD]": 37,
|
| 3 |
"[UNK]": 36,
|
| 4 |
-
"h":
|
| 5 |
-
"|":
|
| 6 |
-
"а":
|
| 7 |
-
"б":
|
| 8 |
-
"в":
|
| 9 |
-
"г":
|
| 10 |
-
"д":
|
| 11 |
-
"е":
|
| 12 |
-
"ж":
|
| 13 |
-
"з":
|
| 14 |
-
"и":
|
| 15 |
-
"й":
|
| 16 |
-
"к":
|
| 17 |
-
"л":
|
| 18 |
-
"м":
|
| 19 |
-
"н":
|
| 20 |
-
"о":
|
| 21 |
-
"п":
|
| 22 |
-
"р":
|
| 23 |
-
"с":
|
| 24 |
-
"т":
|
| 25 |
-
"у":
|
| 26 |
-
"ф":
|
| 27 |
-
"х":
|
| 28 |
-
"ц":
|
| 29 |
-
"ч":
|
| 30 |
-
"ш":
|
| 31 |
-
"ъ":
|
| 32 |
-
"ы":
|
| 33 |
-
"ь":
|
| 34 |
-
"э":
|
| 35 |
-
"ю":
|
| 36 |
-
"я":
|
| 37 |
-
"ё":
|
| 38 |
-
"ү":
|
| 39 |
-
"ө":
|
| 40 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"[PAD]": 37,
|
| 3 |
"[UNK]": 36,
|
| 4 |
+
"h": 14,
|
| 5 |
+
"|": 24,
|
| 6 |
+
"а": 29,
|
| 7 |
+
"б": 34,
|
| 8 |
+
"в": 33,
|
| 9 |
+
"г": 7,
|
| 10 |
+
"д": 12,
|
| 11 |
+
"е": 1,
|
| 12 |
+
"ж": 6,
|
| 13 |
+
"з": 21,
|
| 14 |
+
"и": 4,
|
| 15 |
+
"й": 25,
|
| 16 |
+
"к": 0,
|
| 17 |
+
"л": 35,
|
| 18 |
+
"м": 13,
|
| 19 |
+
"н": 22,
|
| 20 |
+
"о": 27,
|
| 21 |
+
"п": 18,
|
| 22 |
+
"р": 8,
|
| 23 |
+
"с": 31,
|
| 24 |
+
"т": 11,
|
| 25 |
+
"у": 19,
|
| 26 |
+
"ф": 30,
|
| 27 |
+
"х": 9,
|
| 28 |
+
"ц": 28,
|
| 29 |
+
"ч": 32,
|
| 30 |
+
"ш": 10,
|
| 31 |
+
"ъ": 3,
|
| 32 |
+
"ы": 5,
|
| 33 |
+
"ь": 23,
|
| 34 |
+
"э": 26,
|
| 35 |
+
"ю": 16,
|
| 36 |
+
"я": 15,
|
| 37 |
+
"ё": 20,
|
| 38 |
+
"ү": 17,
|
| 39 |
+
"ө": 2
|
| 40 |
}
|