arifagustyawan
commited on
Commit
•
66421ad
1
Parent(s):
e027768
Upload tokenizer
Browse files- vocab.json +42 -42
vocab.json
CHANGED
@@ -1,47 +1,47 @@
|
|
1 |
{
|
2 |
-
"&":
|
3 |
-
"'":
|
4 |
-
"(":
|
5 |
-
")":
|
6 |
-
"[":
|
7 |
"[PAD]": 44,
|
8 |
"[UNK]": 43,
|
9 |
-
"\\":
|
10 |
-
"a":
|
11 |
-
"b":
|
12 |
-
"c":
|
13 |
-
"d":
|
14 |
-
"e":
|
15 |
-
"f":
|
16 |
-
"g":
|
17 |
-
"h":
|
18 |
-
"i":
|
19 |
-
"j":
|
20 |
-
"k":
|
21 |
-
"l":
|
22 |
-
"m":
|
23 |
-
"n":
|
24 |
-
"o":
|
25 |
-
"p":
|
26 |
-
"q":
|
27 |
-
"r":
|
28 |
-
"s":
|
29 |
-
"t":
|
30 |
-
"u":
|
31 |
-
"v":
|
32 |
-
"w":
|
33 |
-
"x":
|
34 |
"y": 10,
|
35 |
-
"z":
|
36 |
-
"|":
|
37 |
-
"á":
|
38 |
-
"é":
|
39 |
-
"ł":
|
40 |
-
"ń":
|
41 |
-
"ō":
|
42 |
-
"–":
|
43 |
-
"—":
|
44 |
-
"’":
|
45 |
-
"!":
|
46 |
-
",":
|
47 |
}
|
|
|
1 |
{
|
2 |
+
"&": 42,
|
3 |
+
"'": 33,
|
4 |
+
"(": 2,
|
5 |
+
")": 22,
|
6 |
+
"[": 6,
|
7 |
"[PAD]": 44,
|
8 |
"[UNK]": 43,
|
9 |
+
"\\": 32,
|
10 |
+
"a": 16,
|
11 |
+
"b": 41,
|
12 |
+
"c": 4,
|
13 |
+
"d": 24,
|
14 |
+
"e": 31,
|
15 |
+
"f": 40,
|
16 |
+
"g": 23,
|
17 |
+
"h": 34,
|
18 |
+
"i": 20,
|
19 |
+
"j": 12,
|
20 |
+
"k": 29,
|
21 |
+
"l": 7,
|
22 |
+
"m": 25,
|
23 |
+
"n": 36,
|
24 |
+
"o": 37,
|
25 |
+
"p": 39,
|
26 |
+
"q": 17,
|
27 |
+
"r": 38,
|
28 |
+
"s": 19,
|
29 |
+
"t": 14,
|
30 |
+
"u": 3,
|
31 |
+
"v": 5,
|
32 |
+
"w": 13,
|
33 |
+
"x": 15,
|
34 |
"y": 10,
|
35 |
+
"z": 26,
|
36 |
+
"|": 9,
|
37 |
+
"á": 0,
|
38 |
+
"é": 35,
|
39 |
+
"ł": 8,
|
40 |
+
"ń": 30,
|
41 |
+
"ō": 27,
|
42 |
+
"–": 18,
|
43 |
+
"—": 1,
|
44 |
+
"’": 21,
|
45 |
+
"!": 11,
|
46 |
+
",": 28
|
47 |
}
|