Upload tokenizer
Browse files- added_tokens.json +2 -2
- vocab.json +38 -36
added_tokens.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"</s>":
|
3 |
-
"<s>":
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"</s>": 64,
|
3 |
+
"<s>": 63
|
4 |
}
|
vocab.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"[PAD]":
|
3 |
-
"[UNK]":
|
4 |
"|": 0,
|
5 |
"ం": 1,
|
6 |
"ః": 2,
|
@@ -26,38 +26,40 @@
|
|
26 |
"ట": 22,
|
27 |
"ఠ": 23,
|
28 |
"డ": 24,
|
29 |
-
"
|
30 |
-
"
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
45 |
-
"
|
46 |
-
"
|
47 |
-
"
|
48 |
-
"
|
49 |
-
"
|
50 |
-
"
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"
|
54 |
-
"
|
55 |
-
"
|
56 |
-
"
|
57 |
-
"
|
58 |
-
"
|
59 |
-
"
|
60 |
-
"
|
61 |
-
"
|
62 |
-
"
|
|
|
|
|
63 |
}
|
|
|
1 |
{
|
2 |
+
"[PAD]": 62,
|
3 |
+
"[UNK]": 61,
|
4 |
"|": 0,
|
5 |
"ం": 1,
|
6 |
"ః": 2,
|
|
|
26 |
"ట": 22,
|
27 |
"ఠ": 23,
|
28 |
"డ": 24,
|
29 |
+
"ఢ": 25,
|
30 |
+
"ణ": 26,
|
31 |
+
"త": 27,
|
32 |
+
"థ": 28,
|
33 |
+
"ద": 29,
|
34 |
+
"ధ": 30,
|
35 |
+
"న": 31,
|
36 |
+
"ప": 32,
|
37 |
+
"ఫ": 33,
|
38 |
+
"బ": 34,
|
39 |
+
"భ": 35,
|
40 |
+
"మ": 36,
|
41 |
+
"య": 37,
|
42 |
+
"ర": 38,
|
43 |
+
"ల": 39,
|
44 |
+
"ళ": 40,
|
45 |
+
"వ": 41,
|
46 |
+
"శ": 42,
|
47 |
+
"ష": 43,
|
48 |
+
"స": 44,
|
49 |
+
"హ": 45,
|
50 |
+
"ా": 46,
|
51 |
+
"ి": 47,
|
52 |
+
"ీ": 48,
|
53 |
+
"ు": 49,
|
54 |
+
"ూ": 50,
|
55 |
+
"ృ": 51,
|
56 |
+
"ె": 52,
|
57 |
+
"ే": 53,
|
58 |
+
"ై": 54,
|
59 |
+
"ొ": 55,
|
60 |
+
"ో": 56,
|
61 |
+
"ౌ": 57,
|
62 |
+
"్": 58,
|
63 |
+
"౩": 59,
|
64 |
+
"": 60
|
65 |
}
|