Create added_tokens.json
Browse files- added_tokens.json +110 -0
added_tokens.json
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|af|>": 50327,
|
3 |
+
"<|am|>": 50334,
|
4 |
+
"<|ar|>": 50272,
|
5 |
+
"<|as|>": 50350,
|
6 |
+
"<|az|>": 50304,
|
7 |
+
"<|ba|>": 50355,
|
8 |
+
"<|be|>": 50330,
|
9 |
+
"<|bg|>": 50292,
|
10 |
+
"<|bn|>": 50302,
|
11 |
+
"<|bo|>": 50347,
|
12 |
+
"<|br|>": 50309,
|
13 |
+
"<|bs|>": 50315,
|
14 |
+
"<|ca|>": 50270,
|
15 |
+
"<|cs|>": 50283,
|
16 |
+
"<|cy|>": 50297,
|
17 |
+
"<|da|>": 50285,
|
18 |
+
"<|de|>": 50261,
|
19 |
+
"<|el|>": 50281,
|
20 |
+
"<|endoftext|>": 50257,
|
21 |
+
"<|en|>": 50259,
|
22 |
+
"<|es|>": 50262,
|
23 |
+
"<|et|>": 50307,
|
24 |
+
"<|eu|>": 50310,
|
25 |
+
"<|fa|>": 50300,
|
26 |
+
"<|fi|>": 50277,
|
27 |
+
"<|fo|>": 50338,
|
28 |
+
"<|fr|>": 50265,
|
29 |
+
"<|gl|>": 50319,
|
30 |
+
"<|gu|>": 50333,
|
31 |
+
"<|haw|>": 50352,
|
32 |
+
"<|ha|>": 50354,
|
33 |
+
"<|hi|>": 50276,
|
34 |
+
"<|hr|>": 50291,
|
35 |
+
"<|ht|>": 50339,
|
36 |
+
"<|hu|>": 50286,
|
37 |
+
"<|hy|>": 50312,
|
38 |
+
"<|id|>": 50275,
|
39 |
+
"<|is|>": 50311,
|
40 |
+
"<|it|>": 50274,
|
41 |
+
"<|iw|>": 50279,
|
42 |
+
"<|ja|>": 50266,
|
43 |
+
"<|jw|>": 50356,
|
44 |
+
"<|kab|>": 50470,
|
45 |
+
"<|ka|>": 50329,
|
46 |
+
"<|kk|>": 50316,
|
47 |
+
"<|km|>": 50323,
|
48 |
+
"<|kn|>": 50306,
|
49 |
+
"<|ko|>": 50264,
|
50 |
+
"<|la|>": 50294,
|
51 |
+
"<|lb|>": 50345,
|
52 |
+
"<|ln|>": 50353,
|
53 |
+
"<|lo|>": 50336,
|
54 |
+
"<|lt|>": 50293,
|
55 |
+
"<|lv|>": 50301,
|
56 |
+
"<|mg|>": 50349,
|
57 |
+
"<|mi|>": 50295,
|
58 |
+
"<|mk|>": 50308,
|
59 |
+
"<|ml|>": 50296,
|
60 |
+
"<|mn|>": 50314,
|
61 |
+
"<|mr|>": 50320,
|
62 |
+
"<|ms|>": 50282,
|
63 |
+
"<|mt|>": 50343,
|
64 |
+
"<|my|>": 50346,
|
65 |
+
"<|ne|>": 50313,
|
66 |
+
"<|nl|>": 50271,
|
67 |
+
"<|nn|>": 50342,
|
68 |
+
"<|nocaptions|>": 50362,
|
69 |
+
"<|notimestamps|>": 50363,
|
70 |
+
"<|no|>": 50288,
|
71 |
+
"<|oc|>": 50328,
|
72 |
+
"<|pa|>": 50321,
|
73 |
+
"<|pl|>": 50269,
|
74 |
+
"<|ps|>": 50340,
|
75 |
+
"<|pt|>": 50267,
|
76 |
+
"<|ro|>": 50284,
|
77 |
+
"<|ru|>": 50263,
|
78 |
+
"<|sa|>": 50344,
|
79 |
+
"<|sd|>": 50332,
|
80 |
+
"<|si|>": 50322,
|
81 |
+
"<|sk|>": 50298,
|
82 |
+
"<|sl|>": 50305,
|
83 |
+
"<|sn|>": 50324,
|
84 |
+
"<|so|>": 50326,
|
85 |
+
"<|sq|>": 50317,
|
86 |
+
"<|sr|>": 50303,
|
87 |
+
"<|startoflm|>": 50360,
|
88 |
+
"<|startofprev|>": 50361,
|
89 |
+
"<|startoftranscript|>": 50258,
|
90 |
+
"<|su|>": 50357,
|
91 |
+
"<|sv|>": 50273,
|
92 |
+
"<|sw|>": 50318,
|
93 |
+
"<|ta|>": 50287,
|
94 |
+
"<|te|>": 50299,
|
95 |
+
"<|tg|>": 50331,
|
96 |
+
"<|th|>": 50289,
|
97 |
+
"<|tk|>": 50341,
|
98 |
+
"<|tl|>": 50348,
|
99 |
+
"<|transcribe|>": 50359,
|
100 |
+
"<|translate|>": 50358,
|
101 |
+
"<|tr|>": 50268,
|
102 |
+
"<|tt|>": 50351,
|
103 |
+
"<|uk|>": 50280,
|
104 |
+
"<|ur|>": 50290,
|
105 |
+
"<|uz|>": 50337,
|
106 |
+
"<|vi|>": 50278,
|
107 |
+
"<|yi|>": 50335,
|
108 |
+
"<|yo|>": 50325,
|
109 |
+
"<|zh|>": 50260
|
110 |
+
}
|