Upload tokenizer
Browse files- .gitattributes +1 -0
- added_tokens.json +95 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +1594 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</O:ANA>": 250185,
|
3 |
+
"</O:Age>": 250129,
|
4 |
+
"</O:CHE>": 250161,
|
5 |
+
"</O:CON>": 250153,
|
6 |
+
"</O:DEV>": 250113,
|
7 |
+
"</O:DIS>": 250121,
|
8 |
+
"</O:Dat>": 250181,
|
9 |
+
"</O:Dos>": 250193,
|
10 |
+
"</O:Dur>": 250141,
|
11 |
+
"</O:Foo>": 250117,
|
12 |
+
"</O:For>": 250105,
|
13 |
+
"</O:Fre>": 250173,
|
14 |
+
"</O:GEN>": 250133,
|
15 |
+
"</O:LIV>": 250177,
|
16 |
+
"</O:Neg>": 250169,
|
17 |
+
"</O:Obs>": 250149,
|
18 |
+
"</O:PHY>": 250165,
|
19 |
+
"</O:PRO>": 250157,
|
20 |
+
"</O:Qua>": 250137,
|
21 |
+
"</O:Res>": 250125,
|
22 |
+
"</O:Rou>": 250189,
|
23 |
+
"</O:Spe>": 250145,
|
24 |
+
"</O:Tim>": 250109,
|
25 |
+
"</S:ANA>": 250183,
|
26 |
+
"</S:Age>": 250127,
|
27 |
+
"</S:CHE>": 250159,
|
28 |
+
"</S:CON>": 250151,
|
29 |
+
"</S:DEV>": 250111,
|
30 |
+
"</S:DIS>": 250119,
|
31 |
+
"</S:Dat>": 250179,
|
32 |
+
"</S:Dos>": 250191,
|
33 |
+
"</S:Dur>": 250139,
|
34 |
+
"</S:Foo>": 250115,
|
35 |
+
"</S:For>": 250103,
|
36 |
+
"</S:Fre>": 250171,
|
37 |
+
"</S:GEN>": 250131,
|
38 |
+
"</S:LIV>": 250175,
|
39 |
+
"</S:Neg>": 250167,
|
40 |
+
"</S:Obs>": 250147,
|
41 |
+
"</S:PHY>": 250163,
|
42 |
+
"</S:PRO>": 250155,
|
43 |
+
"</S:Qua>": 250135,
|
44 |
+
"</S:Res>": 250123,
|
45 |
+
"</S:Rou>": 250187,
|
46 |
+
"</S:Spe>": 250143,
|
47 |
+
"</S:Tim>": 250107,
|
48 |
+
"<O:ANA>": 250184,
|
49 |
+
"<O:Age>": 250128,
|
50 |
+
"<O:CHE>": 250160,
|
51 |
+
"<O:CON>": 250152,
|
52 |
+
"<O:DEV>": 250112,
|
53 |
+
"<O:DIS>": 250120,
|
54 |
+
"<O:Dat>": 250180,
|
55 |
+
"<O:Dos>": 250192,
|
56 |
+
"<O:Dur>": 250140,
|
57 |
+
"<O:Foo>": 250116,
|
58 |
+
"<O:For>": 250104,
|
59 |
+
"<O:Fre>": 250172,
|
60 |
+
"<O:GEN>": 250132,
|
61 |
+
"<O:LIV>": 250176,
|
62 |
+
"<O:Neg>": 250168,
|
63 |
+
"<O:Obs>": 250148,
|
64 |
+
"<O:PHY>": 250164,
|
65 |
+
"<O:PRO>": 250156,
|
66 |
+
"<O:Qua>": 250136,
|
67 |
+
"<O:Res>": 250124,
|
68 |
+
"<O:Rou>": 250188,
|
69 |
+
"<O:Spe>": 250144,
|
70 |
+
"<O:Tim>": 250108,
|
71 |
+
"<S:ANA>": 250182,
|
72 |
+
"<S:Age>": 250126,
|
73 |
+
"<S:CHE>": 250158,
|
74 |
+
"<S:CON>": 250150,
|
75 |
+
"<S:DEV>": 250110,
|
76 |
+
"<S:DIS>": 250118,
|
77 |
+
"<S:Dat>": 250178,
|
78 |
+
"<S:Dos>": 250190,
|
79 |
+
"<S:Dur>": 250138,
|
80 |
+
"<S:Foo>": 250114,
|
81 |
+
"<S:For>": 250102,
|
82 |
+
"<S:Fre>": 250170,
|
83 |
+
"<S:GEN>": 250130,
|
84 |
+
"<S:LIV>": 250174,
|
85 |
+
"<S:Neg>": 250166,
|
86 |
+
"<S:Obs>": 250146,
|
87 |
+
"<S:PHY>": 250162,
|
88 |
+
"<S:PRO>": 250154,
|
89 |
+
"<S:Qua>": 250134,
|
90 |
+
"<S:Res>": 250122,
|
91 |
+
"<S:Rou>": 250186,
|
92 |
+
"<S:Spe>": 250142,
|
93 |
+
"<S:Tim>": 250106,
|
94 |
+
"[MASK]": 250101
|
95 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": {
|
9 |
+
"content": "[UNK]",
|
10 |
+
"lstrip": false,
|
11 |
+
"normalized": true,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
}
|
15 |
+
}
|
spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
|
3 |
+
size 4305025
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:293c40096fbf7f2a490bcd92c560c9ef25ee1db66fc14379ceda125086ae0242
|
3 |
+
size 16367738
|
tokenizer_config.json
ADDED
@@ -0,0 +1,1594 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[CLS]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[SEP]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[UNK]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "▁<extra_id_99>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": false
|
42 |
+
},
|
43 |
+
"250002": {
|
44 |
+
"content": "▁<extra_id_98>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
"250003": {
|
52 |
+
"content": "▁<extra_id_97>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": false
|
58 |
+
},
|
59 |
+
"250004": {
|
60 |
+
"content": "▁<extra_id_96>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": false
|
66 |
+
},
|
67 |
+
"250005": {
|
68 |
+
"content": "▁<extra_id_95>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": false
|
74 |
+
},
|
75 |
+
"250006": {
|
76 |
+
"content": "▁<extra_id_94>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": false
|
82 |
+
},
|
83 |
+
"250007": {
|
84 |
+
"content": "▁<extra_id_93>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": false
|
90 |
+
},
|
91 |
+
"250008": {
|
92 |
+
"content": "▁<extra_id_92>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": false
|
98 |
+
},
|
99 |
+
"250009": {
|
100 |
+
"content": "▁<extra_id_91>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": false
|
106 |
+
},
|
107 |
+
"250010": {
|
108 |
+
"content": "▁<extra_id_90>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": false
|
114 |
+
},
|
115 |
+
"250011": {
|
116 |
+
"content": "▁<extra_id_89>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": false
|
122 |
+
},
|
123 |
+
"250012": {
|
124 |
+
"content": "▁<extra_id_88>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": false
|
130 |
+
},
|
131 |
+
"250013": {
|
132 |
+
"content": "▁<extra_id_87>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": false
|
138 |
+
},
|
139 |
+
"250014": {
|
140 |
+
"content": "▁<extra_id_86>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": false
|
146 |
+
},
|
147 |
+
"250015": {
|
148 |
+
"content": "▁<extra_id_85>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": false
|
154 |
+
},
|
155 |
+
"250016": {
|
156 |
+
"content": "▁<extra_id_84>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": false
|
162 |
+
},
|
163 |
+
"250017": {
|
164 |
+
"content": "▁<extra_id_83>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": false
|
170 |
+
},
|
171 |
+
"250018": {
|
172 |
+
"content": "▁<extra_id_82>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": false
|
178 |
+
},
|
179 |
+
"250019": {
|
180 |
+
"content": "▁<extra_id_81>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": false
|
186 |
+
},
|
187 |
+
"250020": {
|
188 |
+
"content": "▁<extra_id_80>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": false
|
194 |
+
},
|
195 |
+
"250021": {
|
196 |
+
"content": "▁<extra_id_79>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": false
|
202 |
+
},
|
203 |
+
"250022": {
|
204 |
+
"content": "▁<extra_id_78>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": false
|
210 |
+
},
|
211 |
+
"250023": {
|
212 |
+
"content": "▁<extra_id_77>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": false
|
218 |
+
},
|
219 |
+
"250024": {
|
220 |
+
"content": "▁<extra_id_76>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": false
|
226 |
+
},
|
227 |
+
"250025": {
|
228 |
+
"content": "▁<extra_id_75>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": false
|
234 |
+
},
|
235 |
+
"250026": {
|
236 |
+
"content": "▁<extra_id_74>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": false
|
242 |
+
},
|
243 |
+
"250027": {
|
244 |
+
"content": "▁<extra_id_73>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": false
|
250 |
+
},
|
251 |
+
"250028": {
|
252 |
+
"content": "▁<extra_id_72>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": false
|
258 |
+
},
|
259 |
+
"250029": {
|
260 |
+
"content": "▁<extra_id_71>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": false
|
266 |
+
},
|
267 |
+
"250030": {
|
268 |
+
"content": "▁<extra_id_70>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": false
|
274 |
+
},
|
275 |
+
"250031": {
|
276 |
+
"content": "▁<extra_id_69>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": false
|
282 |
+
},
|
283 |
+
"250032": {
|
284 |
+
"content": "▁<extra_id_68>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": false
|
290 |
+
},
|
291 |
+
"250033": {
|
292 |
+
"content": "▁<extra_id_67>",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": false
|
298 |
+
},
|
299 |
+
"250034": {
|
300 |
+
"content": "▁<extra_id_66>",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": false
|
306 |
+
},
|
307 |
+
"250035": {
|
308 |
+
"content": "▁<extra_id_65>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": false
|
314 |
+
},
|
315 |
+
"250036": {
|
316 |
+
"content": "▁<extra_id_64>",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": false
|
322 |
+
},
|
323 |
+
"250037": {
|
324 |
+
"content": "▁<extra_id_63>",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": false
|
330 |
+
},
|
331 |
+
"250038": {
|
332 |
+
"content": "▁<extra_id_62>",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": false
|
338 |
+
},
|
339 |
+
"250039": {
|
340 |
+
"content": "▁<extra_id_61>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": false
|
346 |
+
},
|
347 |
+
"250040": {
|
348 |
+
"content": "▁<extra_id_60>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": false
|
354 |
+
},
|
355 |
+
"250041": {
|
356 |
+
"content": "▁<extra_id_59>",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": false
|
362 |
+
},
|
363 |
+
"250042": {
|
364 |
+
"content": "▁<extra_id_58>",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": false
|
370 |
+
},
|
371 |
+
"250043": {
|
372 |
+
"content": "▁<extra_id_57>",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": false
|
378 |
+
},
|
379 |
+
"250044": {
|
380 |
+
"content": "▁<extra_id_56>",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": false
|
386 |
+
},
|
387 |
+
"250045": {
|
388 |
+
"content": "▁<extra_id_55>",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": false
|
394 |
+
},
|
395 |
+
"250046": {
|
396 |
+
"content": "▁<extra_id_54>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": false
|
402 |
+
},
|
403 |
+
"250047": {
|
404 |
+
"content": "▁<extra_id_53>",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": false
|
410 |
+
},
|
411 |
+
"250048": {
|
412 |
+
"content": "▁<extra_id_52>",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": false
|
418 |
+
},
|
419 |
+
"250049": {
|
420 |
+
"content": "▁<extra_id_51>",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": false
|
426 |
+
},
|
427 |
+
"250050": {
|
428 |
+
"content": "▁<extra_id_50>",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": false
|
434 |
+
},
|
435 |
+
"250051": {
|
436 |
+
"content": "▁<extra_id_49>",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": false
|
442 |
+
},
|
443 |
+
"250052": {
|
444 |
+
"content": "▁<extra_id_48>",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": false
|
450 |
+
},
|
451 |
+
"250053": {
|
452 |
+
"content": "▁<extra_id_47>",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": false,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": false
|
458 |
+
},
|
459 |
+
"250054": {
|
460 |
+
"content": "▁<extra_id_46>",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": false,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": false
|
466 |
+
},
|
467 |
+
"250055": {
|
468 |
+
"content": "▁<extra_id_45>",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": false,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": false
|
474 |
+
},
|
475 |
+
"250056": {
|
476 |
+
"content": "▁<extra_id_44>",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": false,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": false
|
482 |
+
},
|
483 |
+
"250057": {
|
484 |
+
"content": "▁<extra_id_43>",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": false,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": false
|
490 |
+
},
|
491 |
+
"250058": {
|
492 |
+
"content": "▁<extra_id_42>",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": false,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": false
|
498 |
+
},
|
499 |
+
"250059": {
|
500 |
+
"content": "▁<extra_id_41>",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": false,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": false
|
506 |
+
},
|
507 |
+
"250060": {
|
508 |
+
"content": "▁<extra_id_40>",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": false,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": false
|
514 |
+
},
|
515 |
+
"250061": {
|
516 |
+
"content": "▁<extra_id_39>",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": false,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": false
|
522 |
+
},
|
523 |
+
"250062": {
|
524 |
+
"content": "▁<extra_id_38>",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": false,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": false
|
530 |
+
},
|
531 |
+
"250063": {
|
532 |
+
"content": "▁<extra_id_37>",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": false,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": false
|
538 |
+
},
|
539 |
+
"250064": {
|
540 |
+
"content": "▁<extra_id_36>",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": false,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": false
|
546 |
+
},
|
547 |
+
"250065": {
|
548 |
+
"content": "▁<extra_id_35>",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": false,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": false
|
554 |
+
},
|
555 |
+
"250066": {
|
556 |
+
"content": "▁<extra_id_34>",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": false,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": false
|
562 |
+
},
|
563 |
+
"250067": {
|
564 |
+
"content": "▁<extra_id_33>",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": false,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": false
|
570 |
+
},
|
571 |
+
"250068": {
|
572 |
+
"content": "▁<extra_id_32>",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": false,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": false
|
578 |
+
},
|
579 |
+
"250069": {
|
580 |
+
"content": "▁<extra_id_31>",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": false,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": false
|
586 |
+
},
|
587 |
+
"250070": {
|
588 |
+
"content": "▁<extra_id_30>",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": false,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": false
|
594 |
+
},
|
595 |
+
"250071": {
|
596 |
+
"content": "▁<extra_id_29>",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": false,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": false
|
602 |
+
},
|
603 |
+
"250072": {
|
604 |
+
"content": "▁<extra_id_28>",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": false,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": false
|
610 |
+
},
|
611 |
+
"250073": {
|
612 |
+
"content": "▁<extra_id_27>",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": false,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": false
|
618 |
+
},
|
619 |
+
"250074": {
|
620 |
+
"content": "▁<extra_id_26>",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": false,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": false
|
626 |
+
},
|
627 |
+
"250075": {
|
628 |
+
"content": "▁<extra_id_25>",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": false,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": false
|
634 |
+
},
|
635 |
+
"250076": {
|
636 |
+
"content": "▁<extra_id_24>",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": false,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": false
|
642 |
+
},
|
643 |
+
"250077": {
|
644 |
+
"content": "▁<extra_id_23>",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": false,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": false
|
650 |
+
},
|
651 |
+
"250078": {
|
652 |
+
"content": "▁<extra_id_22>",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": false,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": false
|
658 |
+
},
|
659 |
+
"250079": {
|
660 |
+
"content": "▁<extra_id_21>",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": false,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": false
|
666 |
+
},
|
667 |
+
"250080": {
|
668 |
+
"content": "▁<extra_id_20>",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": false,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": false
|
674 |
+
},
|
675 |
+
"250081": {
|
676 |
+
"content": "▁<extra_id_19>",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": false,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": false
|
682 |
+
},
|
683 |
+
"250082": {
|
684 |
+
"content": "▁<extra_id_18>",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": false,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": false
|
690 |
+
},
|
691 |
+
"250083": {
|
692 |
+
"content": "▁<extra_id_17>",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": false,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": false
|
698 |
+
},
|
699 |
+
"250084": {
|
700 |
+
"content": "▁<extra_id_16>",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": false,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": false
|
706 |
+
},
|
707 |
+
"250085": {
|
708 |
+
"content": "▁<extra_id_15>",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": false,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": false
|
714 |
+
},
|
715 |
+
"250086": {
|
716 |
+
"content": "▁<extra_id_14>",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": false,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": false
|
722 |
+
},
|
723 |
+
"250087": {
|
724 |
+
"content": "▁<extra_id_13>",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": false,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": false
|
730 |
+
},
|
731 |
+
"250088": {
|
732 |
+
"content": "▁<extra_id_12>",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": false,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": false
|
738 |
+
},
|
739 |
+
"250089": {
|
740 |
+
"content": "▁<extra_id_11>",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": false,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": false
|
746 |
+
},
|
747 |
+
"250090": {
|
748 |
+
"content": "▁<extra_id_10>",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": false,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": false
|
754 |
+
},
|
755 |
+
"250091": {
|
756 |
+
"content": "▁<extra_id_9>",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": false,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": false
|
762 |
+
},
|
763 |
+
"250092": {
|
764 |
+
"content": "▁<extra_id_8>",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": false,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": false
|
770 |
+
},
|
771 |
+
"250093": {
|
772 |
+
"content": "▁<extra_id_7>",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": false,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": false
|
778 |
+
},
|
779 |
+
"250094": {
|
780 |
+
"content": "▁<extra_id_6>",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": false,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": false
|
786 |
+
},
|
787 |
+
"250095": {
|
788 |
+
"content": "▁<extra_id_5>",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": false,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": false
|
794 |
+
},
|
795 |
+
"250096": {
|
796 |
+
"content": "▁<extra_id_4>",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": false,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": false
|
802 |
+
},
|
803 |
+
"250097": {
|
804 |
+
"content": "▁<extra_id_3>",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": false,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": false
|
810 |
+
},
|
811 |
+
"250098": {
|
812 |
+
"content": "▁<extra_id_2>",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": false,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": false
|
818 |
+
},
|
819 |
+
"250099": {
|
820 |
+
"content": "▁<extra_id_1>",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": false,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": false
|
826 |
+
},
|
827 |
+
"250100": {
|
828 |
+
"content": "▁<extra_id_0>",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": false,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": false
|
834 |
+
},
|
835 |
+
"250101": {
|
836 |
+
"content": "[MASK]",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": false,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": true
|
842 |
+
},
|
843 |
+
"250102": {
|
844 |
+
"content": "<S:For>",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": true,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": false
|
850 |
+
},
|
851 |
+
"250103": {
|
852 |
+
"content": "</S:For>",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": true,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": false
|
858 |
+
},
|
859 |
+
"250104": {
|
860 |
+
"content": "<O:For>",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": true,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": false
|
866 |
+
},
|
867 |
+
"250105": {
|
868 |
+
"content": "</O:For>",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": true,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": false
|
874 |
+
},
|
875 |
+
"250106": {
|
876 |
+
"content": "<S:Tim>",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": true,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": false
|
882 |
+
},
|
883 |
+
"250107": {
|
884 |
+
"content": "</S:Tim>",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": true,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": false
|
890 |
+
},
|
891 |
+
"250108": {
|
892 |
+
"content": "<O:Tim>",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": true,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": false
|
898 |
+
},
|
899 |
+
"250109": {
|
900 |
+
"content": "</O:Tim>",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": true,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": false
|
906 |
+
},
|
907 |
+
"250110": {
|
908 |
+
"content": "<S:DEV>",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": true,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": false
|
914 |
+
},
|
915 |
+
"250111": {
|
916 |
+
"content": "</S:DEV>",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": true,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": false
|
922 |
+
},
|
923 |
+
"250112": {
|
924 |
+
"content": "<O:DEV>",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": true,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": false
|
930 |
+
},
|
931 |
+
"250113": {
|
932 |
+
"content": "</O:DEV>",
|
933 |
+
"lstrip": false,
|
934 |
+
"normalized": true,
|
935 |
+
"rstrip": false,
|
936 |
+
"single_word": false,
|
937 |
+
"special": false
|
938 |
+
},
|
939 |
+
"250114": {
|
940 |
+
"content": "<S:Foo>",
|
941 |
+
"lstrip": false,
|
942 |
+
"normalized": true,
|
943 |
+
"rstrip": false,
|
944 |
+
"single_word": false,
|
945 |
+
"special": false
|
946 |
+
},
|
947 |
+
"250115": {
|
948 |
+
"content": "</S:Foo>",
|
949 |
+
"lstrip": false,
|
950 |
+
"normalized": true,
|
951 |
+
"rstrip": false,
|
952 |
+
"single_word": false,
|
953 |
+
"special": false
|
954 |
+
},
|
955 |
+
"250116": {
|
956 |
+
"content": "<O:Foo>",
|
957 |
+
"lstrip": false,
|
958 |
+
"normalized": true,
|
959 |
+
"rstrip": false,
|
960 |
+
"single_word": false,
|
961 |
+
"special": false
|
962 |
+
},
|
963 |
+
"250117": {
|
964 |
+
"content": "</O:Foo>",
|
965 |
+
"lstrip": false,
|
966 |
+
"normalized": true,
|
967 |
+
"rstrip": false,
|
968 |
+
"single_word": false,
|
969 |
+
"special": false
|
970 |
+
},
|
971 |
+
"250118": {
|
972 |
+
"content": "<S:DIS>",
|
973 |
+
"lstrip": false,
|
974 |
+
"normalized": true,
|
975 |
+
"rstrip": false,
|
976 |
+
"single_word": false,
|
977 |
+
"special": false
|
978 |
+
},
|
979 |
+
"250119": {
|
980 |
+
"content": "</S:DIS>",
|
981 |
+
"lstrip": false,
|
982 |
+
"normalized": true,
|
983 |
+
"rstrip": false,
|
984 |
+
"single_word": false,
|
985 |
+
"special": false
|
986 |
+
},
|
987 |
+
"250120": {
|
988 |
+
"content": "<O:DIS>",
|
989 |
+
"lstrip": false,
|
990 |
+
"normalized": true,
|
991 |
+
"rstrip": false,
|
992 |
+
"single_word": false,
|
993 |
+
"special": false
|
994 |
+
},
|
995 |
+
"250121": {
|
996 |
+
"content": "</O:DIS>",
|
997 |
+
"lstrip": false,
|
998 |
+
"normalized": true,
|
999 |
+
"rstrip": false,
|
1000 |
+
"single_word": false,
|
1001 |
+
"special": false
|
1002 |
+
},
|
1003 |
+
"250122": {
|
1004 |
+
"content": "<S:Res>",
|
1005 |
+
"lstrip": false,
|
1006 |
+
"normalized": true,
|
1007 |
+
"rstrip": false,
|
1008 |
+
"single_word": false,
|
1009 |
+
"special": false
|
1010 |
+
},
|
1011 |
+
"250123": {
|
1012 |
+
"content": "</S:Res>",
|
1013 |
+
"lstrip": false,
|
1014 |
+
"normalized": true,
|
1015 |
+
"rstrip": false,
|
1016 |
+
"single_word": false,
|
1017 |
+
"special": false
|
1018 |
+
},
|
1019 |
+
"250124": {
|
1020 |
+
"content": "<O:Res>",
|
1021 |
+
"lstrip": false,
|
1022 |
+
"normalized": true,
|
1023 |
+
"rstrip": false,
|
1024 |
+
"single_word": false,
|
1025 |
+
"special": false
|
1026 |
+
},
|
1027 |
+
"250125": {
|
1028 |
+
"content": "</O:Res>",
|
1029 |
+
"lstrip": false,
|
1030 |
+
"normalized": true,
|
1031 |
+
"rstrip": false,
|
1032 |
+
"single_word": false,
|
1033 |
+
"special": false
|
1034 |
+
},
|
1035 |
+
"250126": {
|
1036 |
+
"content": "<S:Age>",
|
1037 |
+
"lstrip": false,
|
1038 |
+
"normalized": true,
|
1039 |
+
"rstrip": false,
|
1040 |
+
"single_word": false,
|
1041 |
+
"special": false
|
1042 |
+
},
|
1043 |
+
"250127": {
|
1044 |
+
"content": "</S:Age>",
|
1045 |
+
"lstrip": false,
|
1046 |
+
"normalized": true,
|
1047 |
+
"rstrip": false,
|
1048 |
+
"single_word": false,
|
1049 |
+
"special": false
|
1050 |
+
},
|
1051 |
+
"250128": {
|
1052 |
+
"content": "<O:Age>",
|
1053 |
+
"lstrip": false,
|
1054 |
+
"normalized": true,
|
1055 |
+
"rstrip": false,
|
1056 |
+
"single_word": false,
|
1057 |
+
"special": false
|
1058 |
+
},
|
1059 |
+
"250129": {
|
1060 |
+
"content": "</O:Age>",
|
1061 |
+
"lstrip": false,
|
1062 |
+
"normalized": true,
|
1063 |
+
"rstrip": false,
|
1064 |
+
"single_word": false,
|
1065 |
+
"special": false
|
1066 |
+
},
|
1067 |
+
"250130": {
|
1068 |
+
"content": "<S:GEN>",
|
1069 |
+
"lstrip": false,
|
1070 |
+
"normalized": true,
|
1071 |
+
"rstrip": false,
|
1072 |
+
"single_word": false,
|
1073 |
+
"special": false
|
1074 |
+
},
|
1075 |
+
"250131": {
|
1076 |
+
"content": "</S:GEN>",
|
1077 |
+
"lstrip": false,
|
1078 |
+
"normalized": true,
|
1079 |
+
"rstrip": false,
|
1080 |
+
"single_word": false,
|
1081 |
+
"special": false
|
1082 |
+
},
|
1083 |
+
"250132": {
|
1084 |
+
"content": "<O:GEN>",
|
1085 |
+
"lstrip": false,
|
1086 |
+
"normalized": true,
|
1087 |
+
"rstrip": false,
|
1088 |
+
"single_word": false,
|
1089 |
+
"special": false
|
1090 |
+
},
|
1091 |
+
"250133": {
|
1092 |
+
"content": "</O:GEN>",
|
1093 |
+
"lstrip": false,
|
1094 |
+
"normalized": true,
|
1095 |
+
"rstrip": false,
|
1096 |
+
"single_word": false,
|
1097 |
+
"special": false
|
1098 |
+
},
|
1099 |
+
"250134": {
|
1100 |
+
"content": "<S:Qua>",
|
1101 |
+
"lstrip": false,
|
1102 |
+
"normalized": true,
|
1103 |
+
"rstrip": false,
|
1104 |
+
"single_word": false,
|
1105 |
+
"special": false
|
1106 |
+
},
|
1107 |
+
"250135": {
|
1108 |
+
"content": "</S:Qua>",
|
1109 |
+
"lstrip": false,
|
1110 |
+
"normalized": true,
|
1111 |
+
"rstrip": false,
|
1112 |
+
"single_word": false,
|
1113 |
+
"special": false
|
1114 |
+
},
|
1115 |
+
"250136": {
|
1116 |
+
"content": "<O:Qua>",
|
1117 |
+
"lstrip": false,
|
1118 |
+
"normalized": true,
|
1119 |
+
"rstrip": false,
|
1120 |
+
"single_word": false,
|
1121 |
+
"special": false
|
1122 |
+
},
|
1123 |
+
"250137": {
|
1124 |
+
"content": "</O:Qua>",
|
1125 |
+
"lstrip": false,
|
1126 |
+
"normalized": true,
|
1127 |
+
"rstrip": false,
|
1128 |
+
"single_word": false,
|
1129 |
+
"special": false
|
1130 |
+
},
|
1131 |
+
"250138": {
|
1132 |
+
"content": "<S:Dur>",
|
1133 |
+
"lstrip": false,
|
1134 |
+
"normalized": true,
|
1135 |
+
"rstrip": false,
|
1136 |
+
"single_word": false,
|
1137 |
+
"special": false
|
1138 |
+
},
|
1139 |
+
"250139": {
|
1140 |
+
"content": "</S:Dur>",
|
1141 |
+
"lstrip": false,
|
1142 |
+
"normalized": true,
|
1143 |
+
"rstrip": false,
|
1144 |
+
"single_word": false,
|
1145 |
+
"special": false
|
1146 |
+
},
|
1147 |
+
"250140": {
|
1148 |
+
"content": "<O:Dur>",
|
1149 |
+
"lstrip": false,
|
1150 |
+
"normalized": true,
|
1151 |
+
"rstrip": false,
|
1152 |
+
"single_word": false,
|
1153 |
+
"special": false
|
1154 |
+
},
|
1155 |
+
"250141": {
|
1156 |
+
"content": "</O:Dur>",
|
1157 |
+
"lstrip": false,
|
1158 |
+
"normalized": true,
|
1159 |
+
"rstrip": false,
|
1160 |
+
"single_word": false,
|
1161 |
+
"special": false
|
1162 |
+
},
|
1163 |
+
"250142": {
|
1164 |
+
"content": "<S:Spe>",
|
1165 |
+
"lstrip": false,
|
1166 |
+
"normalized": true,
|
1167 |
+
"rstrip": false,
|
1168 |
+
"single_word": false,
|
1169 |
+
"special": false
|
1170 |
+
},
|
1171 |
+
"250143": {
|
1172 |
+
"content": "</S:Spe>",
|
1173 |
+
"lstrip": false,
|
1174 |
+
"normalized": true,
|
1175 |
+
"rstrip": false,
|
1176 |
+
"single_word": false,
|
1177 |
+
"special": false
|
1178 |
+
},
|
1179 |
+
"250144": {
|
1180 |
+
"content": "<O:Spe>",
|
1181 |
+
"lstrip": false,
|
1182 |
+
"normalized": true,
|
1183 |
+
"rstrip": false,
|
1184 |
+
"single_word": false,
|
1185 |
+
"special": false
|
1186 |
+
},
|
1187 |
+
"250145": {
|
1188 |
+
"content": "</O:Spe>",
|
1189 |
+
"lstrip": false,
|
1190 |
+
"normalized": true,
|
1191 |
+
"rstrip": false,
|
1192 |
+
"single_word": false,
|
1193 |
+
"special": false
|
1194 |
+
},
|
1195 |
+
"250146": {
|
1196 |
+
"content": "<S:Obs>",
|
1197 |
+
"lstrip": false,
|
1198 |
+
"normalized": true,
|
1199 |
+
"rstrip": false,
|
1200 |
+
"single_word": false,
|
1201 |
+
"special": false
|
1202 |
+
},
|
1203 |
+
"250147": {
|
1204 |
+
"content": "</S:Obs>",
|
1205 |
+
"lstrip": false,
|
1206 |
+
"normalized": true,
|
1207 |
+
"rstrip": false,
|
1208 |
+
"single_word": false,
|
1209 |
+
"special": false
|
1210 |
+
},
|
1211 |
+
"250148": {
|
1212 |
+
"content": "<O:Obs>",
|
1213 |
+
"lstrip": false,
|
1214 |
+
"normalized": true,
|
1215 |
+
"rstrip": false,
|
1216 |
+
"single_word": false,
|
1217 |
+
"special": false
|
1218 |
+
},
|
1219 |
+
"250149": {
|
1220 |
+
"content": "</O:Obs>",
|
1221 |
+
"lstrip": false,
|
1222 |
+
"normalized": true,
|
1223 |
+
"rstrip": false,
|
1224 |
+
"single_word": false,
|
1225 |
+
"special": false
|
1226 |
+
},
|
1227 |
+
"250150": {
|
1228 |
+
"content": "<S:CON>",
|
1229 |
+
"lstrip": false,
|
1230 |
+
"normalized": true,
|
1231 |
+
"rstrip": false,
|
1232 |
+
"single_word": false,
|
1233 |
+
"special": false
|
1234 |
+
},
|
1235 |
+
"250151": {
|
1236 |
+
"content": "</S:CON>",
|
1237 |
+
"lstrip": false,
|
1238 |
+
"normalized": true,
|
1239 |
+
"rstrip": false,
|
1240 |
+
"single_word": false,
|
1241 |
+
"special": false
|
1242 |
+
},
|
1243 |
+
"250152": {
|
1244 |
+
"content": "<O:CON>",
|
1245 |
+
"lstrip": false,
|
1246 |
+
"normalized": true,
|
1247 |
+
"rstrip": false,
|
1248 |
+
"single_word": false,
|
1249 |
+
"special": false
|
1250 |
+
},
|
1251 |
+
"250153": {
|
1252 |
+
"content": "</O:CON>",
|
1253 |
+
"lstrip": false,
|
1254 |
+
"normalized": true,
|
1255 |
+
"rstrip": false,
|
1256 |
+
"single_word": false,
|
1257 |
+
"special": false
|
1258 |
+
},
|
1259 |
+
"250154": {
|
1260 |
+
"content": "<S:PRO>",
|
1261 |
+
"lstrip": false,
|
1262 |
+
"normalized": true,
|
1263 |
+
"rstrip": false,
|
1264 |
+
"single_word": false,
|
1265 |
+
"special": false
|
1266 |
+
},
|
1267 |
+
"250155": {
|
1268 |
+
"content": "</S:PRO>",
|
1269 |
+
"lstrip": false,
|
1270 |
+
"normalized": true,
|
1271 |
+
"rstrip": false,
|
1272 |
+
"single_word": false,
|
1273 |
+
"special": false
|
1274 |
+
},
|
1275 |
+
"250156": {
|
1276 |
+
"content": "<O:PRO>",
|
1277 |
+
"lstrip": false,
|
1278 |
+
"normalized": true,
|
1279 |
+
"rstrip": false,
|
1280 |
+
"single_word": false,
|
1281 |
+
"special": false
|
1282 |
+
},
|
1283 |
+
"250157": {
|
1284 |
+
"content": "</O:PRO>",
|
1285 |
+
"lstrip": false,
|
1286 |
+
"normalized": true,
|
1287 |
+
"rstrip": false,
|
1288 |
+
"single_word": false,
|
1289 |
+
"special": false
|
1290 |
+
},
|
1291 |
+
"250158": {
|
1292 |
+
"content": "<S:CHE>",
|
1293 |
+
"lstrip": false,
|
1294 |
+
"normalized": true,
|
1295 |
+
"rstrip": false,
|
1296 |
+
"single_word": false,
|
1297 |
+
"special": false
|
1298 |
+
},
|
1299 |
+
"250159": {
|
1300 |
+
"content": "</S:CHE>",
|
1301 |
+
"lstrip": false,
|
1302 |
+
"normalized": true,
|
1303 |
+
"rstrip": false,
|
1304 |
+
"single_word": false,
|
1305 |
+
"special": false
|
1306 |
+
},
|
1307 |
+
"250160": {
|
1308 |
+
"content": "<O:CHE>",
|
1309 |
+
"lstrip": false,
|
1310 |
+
"normalized": true,
|
1311 |
+
"rstrip": false,
|
1312 |
+
"single_word": false,
|
1313 |
+
"special": false
|
1314 |
+
},
|
1315 |
+
"250161": {
|
1316 |
+
"content": "</O:CHE>",
|
1317 |
+
"lstrip": false,
|
1318 |
+
"normalized": true,
|
1319 |
+
"rstrip": false,
|
1320 |
+
"single_word": false,
|
1321 |
+
"special": false
|
1322 |
+
},
|
1323 |
+
"250162": {
|
1324 |
+
"content": "<S:PHY>",
|
1325 |
+
"lstrip": false,
|
1326 |
+
"normalized": true,
|
1327 |
+
"rstrip": false,
|
1328 |
+
"single_word": false,
|
1329 |
+
"special": false
|
1330 |
+
},
|
1331 |
+
"250163": {
|
1332 |
+
"content": "</S:PHY>",
|
1333 |
+
"lstrip": false,
|
1334 |
+
"normalized": true,
|
1335 |
+
"rstrip": false,
|
1336 |
+
"single_word": false,
|
1337 |
+
"special": false
|
1338 |
+
},
|
1339 |
+
"250164": {
|
1340 |
+
"content": "<O:PHY>",
|
1341 |
+
"lstrip": false,
|
1342 |
+
"normalized": true,
|
1343 |
+
"rstrip": false,
|
1344 |
+
"single_word": false,
|
1345 |
+
"special": false
|
1346 |
+
},
|
1347 |
+
"250165": {
|
1348 |
+
"content": "</O:PHY>",
|
1349 |
+
"lstrip": false,
|
1350 |
+
"normalized": true,
|
1351 |
+
"rstrip": false,
|
1352 |
+
"single_word": false,
|
1353 |
+
"special": false
|
1354 |
+
},
|
1355 |
+
"250166": {
|
1356 |
+
"content": "<S:Neg>",
|
1357 |
+
"lstrip": false,
|
1358 |
+
"normalized": true,
|
1359 |
+
"rstrip": false,
|
1360 |
+
"single_word": false,
|
1361 |
+
"special": false
|
1362 |
+
},
|
1363 |
+
"250167": {
|
1364 |
+
"content": "</S:Neg>",
|
1365 |
+
"lstrip": false,
|
1366 |
+
"normalized": true,
|
1367 |
+
"rstrip": false,
|
1368 |
+
"single_word": false,
|
1369 |
+
"special": false
|
1370 |
+
},
|
1371 |
+
"250168": {
|
1372 |
+
"content": "<O:Neg>",
|
1373 |
+
"lstrip": false,
|
1374 |
+
"normalized": true,
|
1375 |
+
"rstrip": false,
|
1376 |
+
"single_word": false,
|
1377 |
+
"special": false
|
1378 |
+
},
|
1379 |
+
"250169": {
|
1380 |
+
"content": "</O:Neg>",
|
1381 |
+
"lstrip": false,
|
1382 |
+
"normalized": true,
|
1383 |
+
"rstrip": false,
|
1384 |
+
"single_word": false,
|
1385 |
+
"special": false
|
1386 |
+
},
|
1387 |
+
"250170": {
|
1388 |
+
"content": "<S:Fre>",
|
1389 |
+
"lstrip": false,
|
1390 |
+
"normalized": true,
|
1391 |
+
"rstrip": false,
|
1392 |
+
"single_word": false,
|
1393 |
+
"special": false
|
1394 |
+
},
|
1395 |
+
"250171": {
|
1396 |
+
"content": "</S:Fre>",
|
1397 |
+
"lstrip": false,
|
1398 |
+
"normalized": true,
|
1399 |
+
"rstrip": false,
|
1400 |
+
"single_word": false,
|
1401 |
+
"special": false
|
1402 |
+
},
|
1403 |
+
"250172": {
|
1404 |
+
"content": "<O:Fre>",
|
1405 |
+
"lstrip": false,
|
1406 |
+
"normalized": true,
|
1407 |
+
"rstrip": false,
|
1408 |
+
"single_word": false,
|
1409 |
+
"special": false
|
1410 |
+
},
|
1411 |
+
"250173": {
|
1412 |
+
"content": "</O:Fre>",
|
1413 |
+
"lstrip": false,
|
1414 |
+
"normalized": true,
|
1415 |
+
"rstrip": false,
|
1416 |
+
"single_word": false,
|
1417 |
+
"special": false
|
1418 |
+
},
|
1419 |
+
"250174": {
|
1420 |
+
"content": "<S:LIV>",
|
1421 |
+
"lstrip": false,
|
1422 |
+
"normalized": true,
|
1423 |
+
"rstrip": false,
|
1424 |
+
"single_word": false,
|
1425 |
+
"special": false
|
1426 |
+
},
|
1427 |
+
"250175": {
|
1428 |
+
"content": "</S:LIV>",
|
1429 |
+
"lstrip": false,
|
1430 |
+
"normalized": true,
|
1431 |
+
"rstrip": false,
|
1432 |
+
"single_word": false,
|
1433 |
+
"special": false
|
1434 |
+
},
|
1435 |
+
"250176": {
|
1436 |
+
"content": "<O:LIV>",
|
1437 |
+
"lstrip": false,
|
1438 |
+
"normalized": true,
|
1439 |
+
"rstrip": false,
|
1440 |
+
"single_word": false,
|
1441 |
+
"special": false
|
1442 |
+
},
|
1443 |
+
"250177": {
|
1444 |
+
"content": "</O:LIV>",
|
1445 |
+
"lstrip": false,
|
1446 |
+
"normalized": true,
|
1447 |
+
"rstrip": false,
|
1448 |
+
"single_word": false,
|
1449 |
+
"special": false
|
1450 |
+
},
|
1451 |
+
"250178": {
|
1452 |
+
"content": "<S:Dat>",
|
1453 |
+
"lstrip": false,
|
1454 |
+
"normalized": true,
|
1455 |
+
"rstrip": false,
|
1456 |
+
"single_word": false,
|
1457 |
+
"special": false
|
1458 |
+
},
|
1459 |
+
"250179": {
|
1460 |
+
"content": "</S:Dat>",
|
1461 |
+
"lstrip": false,
|
1462 |
+
"normalized": true,
|
1463 |
+
"rstrip": false,
|
1464 |
+
"single_word": false,
|
1465 |
+
"special": false
|
1466 |
+
},
|
1467 |
+
"250180": {
|
1468 |
+
"content": "<O:Dat>",
|
1469 |
+
"lstrip": false,
|
1470 |
+
"normalized": true,
|
1471 |
+
"rstrip": false,
|
1472 |
+
"single_word": false,
|
1473 |
+
"special": false
|
1474 |
+
},
|
1475 |
+
"250181": {
|
1476 |
+
"content": "</O:Dat>",
|
1477 |
+
"lstrip": false,
|
1478 |
+
"normalized": true,
|
1479 |
+
"rstrip": false,
|
1480 |
+
"single_word": false,
|
1481 |
+
"special": false
|
1482 |
+
},
|
1483 |
+
"250182": {
|
1484 |
+
"content": "<S:ANA>",
|
1485 |
+
"lstrip": false,
|
1486 |
+
"normalized": true,
|
1487 |
+
"rstrip": false,
|
1488 |
+
"single_word": false,
|
1489 |
+
"special": false
|
1490 |
+
},
|
1491 |
+
"250183": {
|
1492 |
+
"content": "</S:ANA>",
|
1493 |
+
"lstrip": false,
|
1494 |
+
"normalized": true,
|
1495 |
+
"rstrip": false,
|
1496 |
+
"single_word": false,
|
1497 |
+
"special": false
|
1498 |
+
},
|
1499 |
+
"250184": {
|
1500 |
+
"content": "<O:ANA>",
|
1501 |
+
"lstrip": false,
|
1502 |
+
"normalized": true,
|
1503 |
+
"rstrip": false,
|
1504 |
+
"single_word": false,
|
1505 |
+
"special": false
|
1506 |
+
},
|
1507 |
+
"250185": {
|
1508 |
+
"content": "</O:ANA>",
|
1509 |
+
"lstrip": false,
|
1510 |
+
"normalized": true,
|
1511 |
+
"rstrip": false,
|
1512 |
+
"single_word": false,
|
1513 |
+
"special": false
|
1514 |
+
},
|
1515 |
+
"250186": {
|
1516 |
+
"content": "<S:Rou>",
|
1517 |
+
"lstrip": false,
|
1518 |
+
"normalized": true,
|
1519 |
+
"rstrip": false,
|
1520 |
+
"single_word": false,
|
1521 |
+
"special": false
|
1522 |
+
},
|
1523 |
+
"250187": {
|
1524 |
+
"content": "</S:Rou>",
|
1525 |
+
"lstrip": false,
|
1526 |
+
"normalized": true,
|
1527 |
+
"rstrip": false,
|
1528 |
+
"single_word": false,
|
1529 |
+
"special": false
|
1530 |
+
},
|
1531 |
+
"250188": {
|
1532 |
+
"content": "<O:Rou>",
|
1533 |
+
"lstrip": false,
|
1534 |
+
"normalized": true,
|
1535 |
+
"rstrip": false,
|
1536 |
+
"single_word": false,
|
1537 |
+
"special": false
|
1538 |
+
},
|
1539 |
+
"250189": {
|
1540 |
+
"content": "</O:Rou>",
|
1541 |
+
"lstrip": false,
|
1542 |
+
"normalized": true,
|
1543 |
+
"rstrip": false,
|
1544 |
+
"single_word": false,
|
1545 |
+
"special": false
|
1546 |
+
},
|
1547 |
+
"250190": {
|
1548 |
+
"content": "<S:Dos>",
|
1549 |
+
"lstrip": false,
|
1550 |
+
"normalized": true,
|
1551 |
+
"rstrip": false,
|
1552 |
+
"single_word": false,
|
1553 |
+
"special": false
|
1554 |
+
},
|
1555 |
+
"250191": {
|
1556 |
+
"content": "</S:Dos>",
|
1557 |
+
"lstrip": false,
|
1558 |
+
"normalized": true,
|
1559 |
+
"rstrip": false,
|
1560 |
+
"single_word": false,
|
1561 |
+
"special": false
|
1562 |
+
},
|
1563 |
+
"250192": {
|
1564 |
+
"content": "<O:Dos>",
|
1565 |
+
"lstrip": false,
|
1566 |
+
"normalized": true,
|
1567 |
+
"rstrip": false,
|
1568 |
+
"single_word": false,
|
1569 |
+
"special": false
|
1570 |
+
},
|
1571 |
+
"250193": {
|
1572 |
+
"content": "</O:Dos>",
|
1573 |
+
"lstrip": false,
|
1574 |
+
"normalized": true,
|
1575 |
+
"rstrip": false,
|
1576 |
+
"single_word": false,
|
1577 |
+
"special": false
|
1578 |
+
}
|
1579 |
+
},
|
1580 |
+
"bos_token": "[CLS]",
|
1581 |
+
"clean_up_tokenization_spaces": true,
|
1582 |
+
"cls_token": "[CLS]",
|
1583 |
+
"do_lower_case": false,
|
1584 |
+
"eos_token": "[SEP]",
|
1585 |
+
"mask_token": "[MASK]",
|
1586 |
+
"model_max_length": 1000000000000000019884624838656,
|
1587 |
+
"pad_token": "[PAD]",
|
1588 |
+
"sep_token": "[SEP]",
|
1589 |
+
"sp_model_kwargs": {},
|
1590 |
+
"split_by_punct": false,
|
1591 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
1592 |
+
"unk_token": "[UNK]",
|
1593 |
+
"vocab_type": "spm"
|
1594 |
+
}
|