amazingvince
commited on
Commit
•
315ded4
1
Parent(s):
2f3af3e
Upload tokenizer
Browse files- added_tokens.json +102 -0
- special_tokens_map.json +132 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +953 -0
added_tokens.json
ADDED
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<extra_id_0>": 48128,
|
3 |
+
"<extra_id_10>": 48138,
|
4 |
+
"<extra_id_11>": 48139,
|
5 |
+
"<extra_id_12>": 48140,
|
6 |
+
"<extra_id_13>": 48141,
|
7 |
+
"<extra_id_14>": 48142,
|
8 |
+
"<extra_id_15>": 48143,
|
9 |
+
"<extra_id_16>": 48144,
|
10 |
+
"<extra_id_17>": 48145,
|
11 |
+
"<extra_id_18>": 48146,
|
12 |
+
"<extra_id_19>": 48147,
|
13 |
+
"<extra_id_1>": 48129,
|
14 |
+
"<extra_id_20>": 48148,
|
15 |
+
"<extra_id_21>": 48149,
|
16 |
+
"<extra_id_22>": 48150,
|
17 |
+
"<extra_id_23>": 48151,
|
18 |
+
"<extra_id_24>": 48152,
|
19 |
+
"<extra_id_25>": 48153,
|
20 |
+
"<extra_id_26>": 48154,
|
21 |
+
"<extra_id_27>": 48155,
|
22 |
+
"<extra_id_28>": 48156,
|
23 |
+
"<extra_id_29>": 48157,
|
24 |
+
"<extra_id_2>": 48130,
|
25 |
+
"<extra_id_30>": 48158,
|
26 |
+
"<extra_id_31>": 48159,
|
27 |
+
"<extra_id_32>": 48160,
|
28 |
+
"<extra_id_33>": 48161,
|
29 |
+
"<extra_id_34>": 48162,
|
30 |
+
"<extra_id_35>": 48163,
|
31 |
+
"<extra_id_36>": 48164,
|
32 |
+
"<extra_id_37>": 48165,
|
33 |
+
"<extra_id_38>": 48166,
|
34 |
+
"<extra_id_39>": 48167,
|
35 |
+
"<extra_id_3>": 48131,
|
36 |
+
"<extra_id_40>": 48168,
|
37 |
+
"<extra_id_41>": 48169,
|
38 |
+
"<extra_id_42>": 48170,
|
39 |
+
"<extra_id_43>": 48171,
|
40 |
+
"<extra_id_44>": 48172,
|
41 |
+
"<extra_id_45>": 48173,
|
42 |
+
"<extra_id_46>": 48174,
|
43 |
+
"<extra_id_47>": 48175,
|
44 |
+
"<extra_id_48>": 48176,
|
45 |
+
"<extra_id_49>": 48177,
|
46 |
+
"<extra_id_4>": 48132,
|
47 |
+
"<extra_id_50>": 48178,
|
48 |
+
"<extra_id_51>": 48179,
|
49 |
+
"<extra_id_52>": 48180,
|
50 |
+
"<extra_id_53>": 48181,
|
51 |
+
"<extra_id_54>": 48182,
|
52 |
+
"<extra_id_55>": 48183,
|
53 |
+
"<extra_id_56>": 48184,
|
54 |
+
"<extra_id_57>": 48185,
|
55 |
+
"<extra_id_58>": 48186,
|
56 |
+
"<extra_id_59>": 48187,
|
57 |
+
"<extra_id_5>": 48133,
|
58 |
+
"<extra_id_60>": 48188,
|
59 |
+
"<extra_id_61>": 48189,
|
60 |
+
"<extra_id_62>": 48190,
|
61 |
+
"<extra_id_63>": 48191,
|
62 |
+
"<extra_id_64>": 48192,
|
63 |
+
"<extra_id_65>": 48193,
|
64 |
+
"<extra_id_66>": 48194,
|
65 |
+
"<extra_id_67>": 48195,
|
66 |
+
"<extra_id_68>": 48196,
|
67 |
+
"<extra_id_69>": 48197,
|
68 |
+
"<extra_id_6>": 48134,
|
69 |
+
"<extra_id_70>": 48198,
|
70 |
+
"<extra_id_71>": 48199,
|
71 |
+
"<extra_id_72>": 48200,
|
72 |
+
"<extra_id_73>": 48201,
|
73 |
+
"<extra_id_74>": 48202,
|
74 |
+
"<extra_id_75>": 48203,
|
75 |
+
"<extra_id_76>": 48204,
|
76 |
+
"<extra_id_77>": 48205,
|
77 |
+
"<extra_id_78>": 48206,
|
78 |
+
"<extra_id_79>": 48207,
|
79 |
+
"<extra_id_7>": 48135,
|
80 |
+
"<extra_id_80>": 48208,
|
81 |
+
"<extra_id_81>": 48209,
|
82 |
+
"<extra_id_82>": 48210,
|
83 |
+
"<extra_id_83>": 48211,
|
84 |
+
"<extra_id_84>": 48212,
|
85 |
+
"<extra_id_85>": 48213,
|
86 |
+
"<extra_id_86>": 48214,
|
87 |
+
"<extra_id_87>": 48215,
|
88 |
+
"<extra_id_88>": 48216,
|
89 |
+
"<extra_id_89>": 48217,
|
90 |
+
"<extra_id_8>": 48136,
|
91 |
+
"<extra_id_90>": 48218,
|
92 |
+
"<extra_id_91>": 48219,
|
93 |
+
"<extra_id_92>": 48220,
|
94 |
+
"<extra_id_93>": 48221,
|
95 |
+
"<extra_id_94>": 48222,
|
96 |
+
"<extra_id_95>": 48223,
|
97 |
+
"<extra_id_96>": 48224,
|
98 |
+
"<extra_id_97>": 48225,
|
99 |
+
"<extra_id_98>": 48226,
|
100 |
+
"<extra_id_99>": 48227,
|
101 |
+
"<extra_id_9>": 48137
|
102 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
+
],
|
104 |
+
"bos_token": {
|
105 |
+
"content": "<s>",
|
106 |
+
"lstrip": false,
|
107 |
+
"normalized": true,
|
108 |
+
"rstrip": false,
|
109 |
+
"single_word": false
|
110 |
+
},
|
111 |
+
"eos_token": {
|
112 |
+
"content": "</s>",
|
113 |
+
"lstrip": false,
|
114 |
+
"normalized": true,
|
115 |
+
"rstrip": false,
|
116 |
+
"single_word": false
|
117 |
+
},
|
118 |
+
"pad_token": {
|
119 |
+
"content": "<pad>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false
|
124 |
+
},
|
125 |
+
"unk_token": {
|
126 |
+
"content": "<unk>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": true,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false
|
131 |
+
}
|
132 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:165515d67d17852d3e7c30ec22d7a745330f2cba264f40c3ea9380eddf84396f
|
3 |
+
size 1042483
|
tokenizer_config.json
ADDED
@@ -0,0 +1,953 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": true,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"3": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"48128": {
|
39 |
+
"content": "<extra_id_0>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"48129": {
|
47 |
+
"content": "<extra_id_1>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"48130": {
|
55 |
+
"content": "<extra_id_2>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"48131": {
|
63 |
+
"content": "<extra_id_3>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"48132": {
|
71 |
+
"content": "<extra_id_4>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"48133": {
|
79 |
+
"content": "<extra_id_5>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"48134": {
|
87 |
+
"content": "<extra_id_6>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"48135": {
|
95 |
+
"content": "<extra_id_7>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"48136": {
|
103 |
+
"content": "<extra_id_8>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"48137": {
|
111 |
+
"content": "<extra_id_9>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
},
|
118 |
+
"48138": {
|
119 |
+
"content": "<extra_id_10>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": true
|
125 |
+
},
|
126 |
+
"48139": {
|
127 |
+
"content": "<extra_id_11>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": true
|
133 |
+
},
|
134 |
+
"48140": {
|
135 |
+
"content": "<extra_id_12>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": true
|
141 |
+
},
|
142 |
+
"48141": {
|
143 |
+
"content": "<extra_id_13>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": true
|
149 |
+
},
|
150 |
+
"48142": {
|
151 |
+
"content": "<extra_id_14>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": true
|
157 |
+
},
|
158 |
+
"48143": {
|
159 |
+
"content": "<extra_id_15>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": true
|
165 |
+
},
|
166 |
+
"48144": {
|
167 |
+
"content": "<extra_id_16>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": false,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": true
|
173 |
+
},
|
174 |
+
"48145": {
|
175 |
+
"content": "<extra_id_17>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": true
|
181 |
+
},
|
182 |
+
"48146": {
|
183 |
+
"content": "<extra_id_18>",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": false,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": true
|
189 |
+
},
|
190 |
+
"48147": {
|
191 |
+
"content": "<extra_id_19>",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": false,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": true
|
197 |
+
},
|
198 |
+
"48148": {
|
199 |
+
"content": "<extra_id_20>",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": false,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": true
|
205 |
+
},
|
206 |
+
"48149": {
|
207 |
+
"content": "<extra_id_21>",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": true
|
213 |
+
},
|
214 |
+
"48150": {
|
215 |
+
"content": "<extra_id_22>",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": true
|
221 |
+
},
|
222 |
+
"48151": {
|
223 |
+
"content": "<extra_id_23>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": true
|
229 |
+
},
|
230 |
+
"48152": {
|
231 |
+
"content": "<extra_id_24>",
|
232 |
+
"lstrip": false,
|
233 |
+
"normalized": false,
|
234 |
+
"rstrip": false,
|
235 |
+
"single_word": false,
|
236 |
+
"special": true
|
237 |
+
},
|
238 |
+
"48153": {
|
239 |
+
"content": "<extra_id_25>",
|
240 |
+
"lstrip": false,
|
241 |
+
"normalized": false,
|
242 |
+
"rstrip": false,
|
243 |
+
"single_word": false,
|
244 |
+
"special": true
|
245 |
+
},
|
246 |
+
"48154": {
|
247 |
+
"content": "<extra_id_26>",
|
248 |
+
"lstrip": false,
|
249 |
+
"normalized": false,
|
250 |
+
"rstrip": false,
|
251 |
+
"single_word": false,
|
252 |
+
"special": true
|
253 |
+
},
|
254 |
+
"48155": {
|
255 |
+
"content": "<extra_id_27>",
|
256 |
+
"lstrip": false,
|
257 |
+
"normalized": false,
|
258 |
+
"rstrip": false,
|
259 |
+
"single_word": false,
|
260 |
+
"special": true
|
261 |
+
},
|
262 |
+
"48156": {
|
263 |
+
"content": "<extra_id_28>",
|
264 |
+
"lstrip": false,
|
265 |
+
"normalized": false,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false,
|
268 |
+
"special": true
|
269 |
+
},
|
270 |
+
"48157": {
|
271 |
+
"content": "<extra_id_29>",
|
272 |
+
"lstrip": false,
|
273 |
+
"normalized": false,
|
274 |
+
"rstrip": false,
|
275 |
+
"single_word": false,
|
276 |
+
"special": true
|
277 |
+
},
|
278 |
+
"48158": {
|
279 |
+
"content": "<extra_id_30>",
|
280 |
+
"lstrip": false,
|
281 |
+
"normalized": false,
|
282 |
+
"rstrip": false,
|
283 |
+
"single_word": false,
|
284 |
+
"special": true
|
285 |
+
},
|
286 |
+
"48159": {
|
287 |
+
"content": "<extra_id_31>",
|
288 |
+
"lstrip": false,
|
289 |
+
"normalized": false,
|
290 |
+
"rstrip": false,
|
291 |
+
"single_word": false,
|
292 |
+
"special": true
|
293 |
+
},
|
294 |
+
"48160": {
|
295 |
+
"content": "<extra_id_32>",
|
296 |
+
"lstrip": false,
|
297 |
+
"normalized": false,
|
298 |
+
"rstrip": false,
|
299 |
+
"single_word": false,
|
300 |
+
"special": true
|
301 |
+
},
|
302 |
+
"48161": {
|
303 |
+
"content": "<extra_id_33>",
|
304 |
+
"lstrip": false,
|
305 |
+
"normalized": false,
|
306 |
+
"rstrip": false,
|
307 |
+
"single_word": false,
|
308 |
+
"special": true
|
309 |
+
},
|
310 |
+
"48162": {
|
311 |
+
"content": "<extra_id_34>",
|
312 |
+
"lstrip": false,
|
313 |
+
"normalized": false,
|
314 |
+
"rstrip": false,
|
315 |
+
"single_word": false,
|
316 |
+
"special": true
|
317 |
+
},
|
318 |
+
"48163": {
|
319 |
+
"content": "<extra_id_35>",
|
320 |
+
"lstrip": false,
|
321 |
+
"normalized": false,
|
322 |
+
"rstrip": false,
|
323 |
+
"single_word": false,
|
324 |
+
"special": true
|
325 |
+
},
|
326 |
+
"48164": {
|
327 |
+
"content": "<extra_id_36>",
|
328 |
+
"lstrip": false,
|
329 |
+
"normalized": false,
|
330 |
+
"rstrip": false,
|
331 |
+
"single_word": false,
|
332 |
+
"special": true
|
333 |
+
},
|
334 |
+
"48165": {
|
335 |
+
"content": "<extra_id_37>",
|
336 |
+
"lstrip": false,
|
337 |
+
"normalized": false,
|
338 |
+
"rstrip": false,
|
339 |
+
"single_word": false,
|
340 |
+
"special": true
|
341 |
+
},
|
342 |
+
"48166": {
|
343 |
+
"content": "<extra_id_38>",
|
344 |
+
"lstrip": false,
|
345 |
+
"normalized": false,
|
346 |
+
"rstrip": false,
|
347 |
+
"single_word": false,
|
348 |
+
"special": true
|
349 |
+
},
|
350 |
+
"48167": {
|
351 |
+
"content": "<extra_id_39>",
|
352 |
+
"lstrip": false,
|
353 |
+
"normalized": false,
|
354 |
+
"rstrip": false,
|
355 |
+
"single_word": false,
|
356 |
+
"special": true
|
357 |
+
},
|
358 |
+
"48168": {
|
359 |
+
"content": "<extra_id_40>",
|
360 |
+
"lstrip": false,
|
361 |
+
"normalized": false,
|
362 |
+
"rstrip": false,
|
363 |
+
"single_word": false,
|
364 |
+
"special": true
|
365 |
+
},
|
366 |
+
"48169": {
|
367 |
+
"content": "<extra_id_41>",
|
368 |
+
"lstrip": false,
|
369 |
+
"normalized": false,
|
370 |
+
"rstrip": false,
|
371 |
+
"single_word": false,
|
372 |
+
"special": true
|
373 |
+
},
|
374 |
+
"48170": {
|
375 |
+
"content": "<extra_id_42>",
|
376 |
+
"lstrip": false,
|
377 |
+
"normalized": false,
|
378 |
+
"rstrip": false,
|
379 |
+
"single_word": false,
|
380 |
+
"special": true
|
381 |
+
},
|
382 |
+
"48171": {
|
383 |
+
"content": "<extra_id_43>",
|
384 |
+
"lstrip": false,
|
385 |
+
"normalized": false,
|
386 |
+
"rstrip": false,
|
387 |
+
"single_word": false,
|
388 |
+
"special": true
|
389 |
+
},
|
390 |
+
"48172": {
|
391 |
+
"content": "<extra_id_44>",
|
392 |
+
"lstrip": false,
|
393 |
+
"normalized": false,
|
394 |
+
"rstrip": false,
|
395 |
+
"single_word": false,
|
396 |
+
"special": true
|
397 |
+
},
|
398 |
+
"48173": {
|
399 |
+
"content": "<extra_id_45>",
|
400 |
+
"lstrip": false,
|
401 |
+
"normalized": false,
|
402 |
+
"rstrip": false,
|
403 |
+
"single_word": false,
|
404 |
+
"special": true
|
405 |
+
},
|
406 |
+
"48174": {
|
407 |
+
"content": "<extra_id_46>",
|
408 |
+
"lstrip": false,
|
409 |
+
"normalized": false,
|
410 |
+
"rstrip": false,
|
411 |
+
"single_word": false,
|
412 |
+
"special": true
|
413 |
+
},
|
414 |
+
"48175": {
|
415 |
+
"content": "<extra_id_47>",
|
416 |
+
"lstrip": false,
|
417 |
+
"normalized": false,
|
418 |
+
"rstrip": false,
|
419 |
+
"single_word": false,
|
420 |
+
"special": true
|
421 |
+
},
|
422 |
+
"48176": {
|
423 |
+
"content": "<extra_id_48>",
|
424 |
+
"lstrip": false,
|
425 |
+
"normalized": false,
|
426 |
+
"rstrip": false,
|
427 |
+
"single_word": false,
|
428 |
+
"special": true
|
429 |
+
},
|
430 |
+
"48177": {
|
431 |
+
"content": "<extra_id_49>",
|
432 |
+
"lstrip": false,
|
433 |
+
"normalized": false,
|
434 |
+
"rstrip": false,
|
435 |
+
"single_word": false,
|
436 |
+
"special": true
|
437 |
+
},
|
438 |
+
"48178": {
|
439 |
+
"content": "<extra_id_50>",
|
440 |
+
"lstrip": false,
|
441 |
+
"normalized": false,
|
442 |
+
"rstrip": false,
|
443 |
+
"single_word": false,
|
444 |
+
"special": true
|
445 |
+
},
|
446 |
+
"48179": {
|
447 |
+
"content": "<extra_id_51>",
|
448 |
+
"lstrip": false,
|
449 |
+
"normalized": false,
|
450 |
+
"rstrip": false,
|
451 |
+
"single_word": false,
|
452 |
+
"special": true
|
453 |
+
},
|
454 |
+
"48180": {
|
455 |
+
"content": "<extra_id_52>",
|
456 |
+
"lstrip": false,
|
457 |
+
"normalized": false,
|
458 |
+
"rstrip": false,
|
459 |
+
"single_word": false,
|
460 |
+
"special": true
|
461 |
+
},
|
462 |
+
"48181": {
|
463 |
+
"content": "<extra_id_53>",
|
464 |
+
"lstrip": false,
|
465 |
+
"normalized": false,
|
466 |
+
"rstrip": false,
|
467 |
+
"single_word": false,
|
468 |
+
"special": true
|
469 |
+
},
|
470 |
+
"48182": {
|
471 |
+
"content": "<extra_id_54>",
|
472 |
+
"lstrip": false,
|
473 |
+
"normalized": false,
|
474 |
+
"rstrip": false,
|
475 |
+
"single_word": false,
|
476 |
+
"special": true
|
477 |
+
},
|
478 |
+
"48183": {
|
479 |
+
"content": "<extra_id_55>",
|
480 |
+
"lstrip": false,
|
481 |
+
"normalized": false,
|
482 |
+
"rstrip": false,
|
483 |
+
"single_word": false,
|
484 |
+
"special": true
|
485 |
+
},
|
486 |
+
"48184": {
|
487 |
+
"content": "<extra_id_56>",
|
488 |
+
"lstrip": false,
|
489 |
+
"normalized": false,
|
490 |
+
"rstrip": false,
|
491 |
+
"single_word": false,
|
492 |
+
"special": true
|
493 |
+
},
|
494 |
+
"48185": {
|
495 |
+
"content": "<extra_id_57>",
|
496 |
+
"lstrip": false,
|
497 |
+
"normalized": false,
|
498 |
+
"rstrip": false,
|
499 |
+
"single_word": false,
|
500 |
+
"special": true
|
501 |
+
},
|
502 |
+
"48186": {
|
503 |
+
"content": "<extra_id_58>",
|
504 |
+
"lstrip": false,
|
505 |
+
"normalized": false,
|
506 |
+
"rstrip": false,
|
507 |
+
"single_word": false,
|
508 |
+
"special": true
|
509 |
+
},
|
510 |
+
"48187": {
|
511 |
+
"content": "<extra_id_59>",
|
512 |
+
"lstrip": false,
|
513 |
+
"normalized": false,
|
514 |
+
"rstrip": false,
|
515 |
+
"single_word": false,
|
516 |
+
"special": true
|
517 |
+
},
|
518 |
+
"48188": {
|
519 |
+
"content": "<extra_id_60>",
|
520 |
+
"lstrip": false,
|
521 |
+
"normalized": false,
|
522 |
+
"rstrip": false,
|
523 |
+
"single_word": false,
|
524 |
+
"special": true
|
525 |
+
},
|
526 |
+
"48189": {
|
527 |
+
"content": "<extra_id_61>",
|
528 |
+
"lstrip": false,
|
529 |
+
"normalized": false,
|
530 |
+
"rstrip": false,
|
531 |
+
"single_word": false,
|
532 |
+
"special": true
|
533 |
+
},
|
534 |
+
"48190": {
|
535 |
+
"content": "<extra_id_62>",
|
536 |
+
"lstrip": false,
|
537 |
+
"normalized": false,
|
538 |
+
"rstrip": false,
|
539 |
+
"single_word": false,
|
540 |
+
"special": true
|
541 |
+
},
|
542 |
+
"48191": {
|
543 |
+
"content": "<extra_id_63>",
|
544 |
+
"lstrip": false,
|
545 |
+
"normalized": false,
|
546 |
+
"rstrip": false,
|
547 |
+
"single_word": false,
|
548 |
+
"special": true
|
549 |
+
},
|
550 |
+
"48192": {
|
551 |
+
"content": "<extra_id_64>",
|
552 |
+
"lstrip": false,
|
553 |
+
"normalized": false,
|
554 |
+
"rstrip": false,
|
555 |
+
"single_word": false,
|
556 |
+
"special": true
|
557 |
+
},
|
558 |
+
"48193": {
|
559 |
+
"content": "<extra_id_65>",
|
560 |
+
"lstrip": false,
|
561 |
+
"normalized": false,
|
562 |
+
"rstrip": false,
|
563 |
+
"single_word": false,
|
564 |
+
"special": true
|
565 |
+
},
|
566 |
+
"48194": {
|
567 |
+
"content": "<extra_id_66>",
|
568 |
+
"lstrip": false,
|
569 |
+
"normalized": false,
|
570 |
+
"rstrip": false,
|
571 |
+
"single_word": false,
|
572 |
+
"special": true
|
573 |
+
},
|
574 |
+
"48195": {
|
575 |
+
"content": "<extra_id_67>",
|
576 |
+
"lstrip": false,
|
577 |
+
"normalized": false,
|
578 |
+
"rstrip": false,
|
579 |
+
"single_word": false,
|
580 |
+
"special": true
|
581 |
+
},
|
582 |
+
"48196": {
|
583 |
+
"content": "<extra_id_68>",
|
584 |
+
"lstrip": false,
|
585 |
+
"normalized": false,
|
586 |
+
"rstrip": false,
|
587 |
+
"single_word": false,
|
588 |
+
"special": true
|
589 |
+
},
|
590 |
+
"48197": {
|
591 |
+
"content": "<extra_id_69>",
|
592 |
+
"lstrip": false,
|
593 |
+
"normalized": false,
|
594 |
+
"rstrip": false,
|
595 |
+
"single_word": false,
|
596 |
+
"special": true
|
597 |
+
},
|
598 |
+
"48198": {
|
599 |
+
"content": "<extra_id_70>",
|
600 |
+
"lstrip": false,
|
601 |
+
"normalized": false,
|
602 |
+
"rstrip": false,
|
603 |
+
"single_word": false,
|
604 |
+
"special": true
|
605 |
+
},
|
606 |
+
"48199": {
|
607 |
+
"content": "<extra_id_71>",
|
608 |
+
"lstrip": false,
|
609 |
+
"normalized": false,
|
610 |
+
"rstrip": false,
|
611 |
+
"single_word": false,
|
612 |
+
"special": true
|
613 |
+
},
|
614 |
+
"48200": {
|
615 |
+
"content": "<extra_id_72>",
|
616 |
+
"lstrip": false,
|
617 |
+
"normalized": false,
|
618 |
+
"rstrip": false,
|
619 |
+
"single_word": false,
|
620 |
+
"special": true
|
621 |
+
},
|
622 |
+
"48201": {
|
623 |
+
"content": "<extra_id_73>",
|
624 |
+
"lstrip": false,
|
625 |
+
"normalized": false,
|
626 |
+
"rstrip": false,
|
627 |
+
"single_word": false,
|
628 |
+
"special": true
|
629 |
+
},
|
630 |
+
"48202": {
|
631 |
+
"content": "<extra_id_74>",
|
632 |
+
"lstrip": false,
|
633 |
+
"normalized": false,
|
634 |
+
"rstrip": false,
|
635 |
+
"single_word": false,
|
636 |
+
"special": true
|
637 |
+
},
|
638 |
+
"48203": {
|
639 |
+
"content": "<extra_id_75>",
|
640 |
+
"lstrip": false,
|
641 |
+
"normalized": false,
|
642 |
+
"rstrip": false,
|
643 |
+
"single_word": false,
|
644 |
+
"special": true
|
645 |
+
},
|
646 |
+
"48204": {
|
647 |
+
"content": "<extra_id_76>",
|
648 |
+
"lstrip": false,
|
649 |
+
"normalized": false,
|
650 |
+
"rstrip": false,
|
651 |
+
"single_word": false,
|
652 |
+
"special": true
|
653 |
+
},
|
654 |
+
"48205": {
|
655 |
+
"content": "<extra_id_77>",
|
656 |
+
"lstrip": false,
|
657 |
+
"normalized": false,
|
658 |
+
"rstrip": false,
|
659 |
+
"single_word": false,
|
660 |
+
"special": true
|
661 |
+
},
|
662 |
+
"48206": {
|
663 |
+
"content": "<extra_id_78>",
|
664 |
+
"lstrip": false,
|
665 |
+
"normalized": false,
|
666 |
+
"rstrip": false,
|
667 |
+
"single_word": false,
|
668 |
+
"special": true
|
669 |
+
},
|
670 |
+
"48207": {
|
671 |
+
"content": "<extra_id_79>",
|
672 |
+
"lstrip": false,
|
673 |
+
"normalized": false,
|
674 |
+
"rstrip": false,
|
675 |
+
"single_word": false,
|
676 |
+
"special": true
|
677 |
+
},
|
678 |
+
"48208": {
|
679 |
+
"content": "<extra_id_80>",
|
680 |
+
"lstrip": false,
|
681 |
+
"normalized": false,
|
682 |
+
"rstrip": false,
|
683 |
+
"single_word": false,
|
684 |
+
"special": true
|
685 |
+
},
|
686 |
+
"48209": {
|
687 |
+
"content": "<extra_id_81>",
|
688 |
+
"lstrip": false,
|
689 |
+
"normalized": false,
|
690 |
+
"rstrip": false,
|
691 |
+
"single_word": false,
|
692 |
+
"special": true
|
693 |
+
},
|
694 |
+
"48210": {
|
695 |
+
"content": "<extra_id_82>",
|
696 |
+
"lstrip": false,
|
697 |
+
"normalized": false,
|
698 |
+
"rstrip": false,
|
699 |
+
"single_word": false,
|
700 |
+
"special": true
|
701 |
+
},
|
702 |
+
"48211": {
|
703 |
+
"content": "<extra_id_83>",
|
704 |
+
"lstrip": false,
|
705 |
+
"normalized": false,
|
706 |
+
"rstrip": false,
|
707 |
+
"single_word": false,
|
708 |
+
"special": true
|
709 |
+
},
|
710 |
+
"48212": {
|
711 |
+
"content": "<extra_id_84>",
|
712 |
+
"lstrip": false,
|
713 |
+
"normalized": false,
|
714 |
+
"rstrip": false,
|
715 |
+
"single_word": false,
|
716 |
+
"special": true
|
717 |
+
},
|
718 |
+
"48213": {
|
719 |
+
"content": "<extra_id_85>",
|
720 |
+
"lstrip": false,
|
721 |
+
"normalized": false,
|
722 |
+
"rstrip": false,
|
723 |
+
"single_word": false,
|
724 |
+
"special": true
|
725 |
+
},
|
726 |
+
"48214": {
|
727 |
+
"content": "<extra_id_86>",
|
728 |
+
"lstrip": false,
|
729 |
+
"normalized": false,
|
730 |
+
"rstrip": false,
|
731 |
+
"single_word": false,
|
732 |
+
"special": true
|
733 |
+
},
|
734 |
+
"48215": {
|
735 |
+
"content": "<extra_id_87>",
|
736 |
+
"lstrip": false,
|
737 |
+
"normalized": false,
|
738 |
+
"rstrip": false,
|
739 |
+
"single_word": false,
|
740 |
+
"special": true
|
741 |
+
},
|
742 |
+
"48216": {
|
743 |
+
"content": "<extra_id_88>",
|
744 |
+
"lstrip": false,
|
745 |
+
"normalized": false,
|
746 |
+
"rstrip": false,
|
747 |
+
"single_word": false,
|
748 |
+
"special": true
|
749 |
+
},
|
750 |
+
"48217": {
|
751 |
+
"content": "<extra_id_89>",
|
752 |
+
"lstrip": false,
|
753 |
+
"normalized": false,
|
754 |
+
"rstrip": false,
|
755 |
+
"single_word": false,
|
756 |
+
"special": true
|
757 |
+
},
|
758 |
+
"48218": {
|
759 |
+
"content": "<extra_id_90>",
|
760 |
+
"lstrip": false,
|
761 |
+
"normalized": false,
|
762 |
+
"rstrip": false,
|
763 |
+
"single_word": false,
|
764 |
+
"special": true
|
765 |
+
},
|
766 |
+
"48219": {
|
767 |
+
"content": "<extra_id_91>",
|
768 |
+
"lstrip": false,
|
769 |
+
"normalized": false,
|
770 |
+
"rstrip": false,
|
771 |
+
"single_word": false,
|
772 |
+
"special": true
|
773 |
+
},
|
774 |
+
"48220": {
|
775 |
+
"content": "<extra_id_92>",
|
776 |
+
"lstrip": false,
|
777 |
+
"normalized": false,
|
778 |
+
"rstrip": false,
|
779 |
+
"single_word": false,
|
780 |
+
"special": true
|
781 |
+
},
|
782 |
+
"48221": {
|
783 |
+
"content": "<extra_id_93>",
|
784 |
+
"lstrip": false,
|
785 |
+
"normalized": false,
|
786 |
+
"rstrip": false,
|
787 |
+
"single_word": false,
|
788 |
+
"special": true
|
789 |
+
},
|
790 |
+
"48222": {
|
791 |
+
"content": "<extra_id_94>",
|
792 |
+
"lstrip": false,
|
793 |
+
"normalized": false,
|
794 |
+
"rstrip": false,
|
795 |
+
"single_word": false,
|
796 |
+
"special": true
|
797 |
+
},
|
798 |
+
"48223": {
|
799 |
+
"content": "<extra_id_95>",
|
800 |
+
"lstrip": false,
|
801 |
+
"normalized": false,
|
802 |
+
"rstrip": false,
|
803 |
+
"single_word": false,
|
804 |
+
"special": true
|
805 |
+
},
|
806 |
+
"48224": {
|
807 |
+
"content": "<extra_id_96>",
|
808 |
+
"lstrip": false,
|
809 |
+
"normalized": false,
|
810 |
+
"rstrip": false,
|
811 |
+
"single_word": false,
|
812 |
+
"special": true
|
813 |
+
},
|
814 |
+
"48225": {
|
815 |
+
"content": "<extra_id_97>",
|
816 |
+
"lstrip": false,
|
817 |
+
"normalized": false,
|
818 |
+
"rstrip": false,
|
819 |
+
"single_word": false,
|
820 |
+
"special": true
|
821 |
+
},
|
822 |
+
"48226": {
|
823 |
+
"content": "<extra_id_98>",
|
824 |
+
"lstrip": false,
|
825 |
+
"normalized": false,
|
826 |
+
"rstrip": false,
|
827 |
+
"single_word": false,
|
828 |
+
"special": true
|
829 |
+
},
|
830 |
+
"48227": {
|
831 |
+
"content": "<extra_id_99>",
|
832 |
+
"lstrip": false,
|
833 |
+
"normalized": false,
|
834 |
+
"rstrip": false,
|
835 |
+
"single_word": false,
|
836 |
+
"special": true
|
837 |
+
}
|
838 |
+
},
|
839 |
+
"additional_special_tokens": [
|
840 |
+
"<extra_id_0>",
|
841 |
+
"<extra_id_1>",
|
842 |
+
"<extra_id_2>",
|
843 |
+
"<extra_id_3>",
|
844 |
+
"<extra_id_4>",
|
845 |
+
"<extra_id_5>",
|
846 |
+
"<extra_id_6>",
|
847 |
+
"<extra_id_7>",
|
848 |
+
"<extra_id_8>",
|
849 |
+
"<extra_id_9>",
|
850 |
+
"<extra_id_10>",
|
851 |
+
"<extra_id_11>",
|
852 |
+
"<extra_id_12>",
|
853 |
+
"<extra_id_13>",
|
854 |
+
"<extra_id_14>",
|
855 |
+
"<extra_id_15>",
|
856 |
+
"<extra_id_16>",
|
857 |
+
"<extra_id_17>",
|
858 |
+
"<extra_id_18>",
|
859 |
+
"<extra_id_19>",
|
860 |
+
"<extra_id_20>",
|
861 |
+
"<extra_id_21>",
|
862 |
+
"<extra_id_22>",
|
863 |
+
"<extra_id_23>",
|
864 |
+
"<extra_id_24>",
|
865 |
+
"<extra_id_25>",
|
866 |
+
"<extra_id_26>",
|
867 |
+
"<extra_id_27>",
|
868 |
+
"<extra_id_28>",
|
869 |
+
"<extra_id_29>",
|
870 |
+
"<extra_id_30>",
|
871 |
+
"<extra_id_31>",
|
872 |
+
"<extra_id_32>",
|
873 |
+
"<extra_id_33>",
|
874 |
+
"<extra_id_34>",
|
875 |
+
"<extra_id_35>",
|
876 |
+
"<extra_id_36>",
|
877 |
+
"<extra_id_37>",
|
878 |
+
"<extra_id_38>",
|
879 |
+
"<extra_id_39>",
|
880 |
+
"<extra_id_40>",
|
881 |
+
"<extra_id_41>",
|
882 |
+
"<extra_id_42>",
|
883 |
+
"<extra_id_43>",
|
884 |
+
"<extra_id_44>",
|
885 |
+
"<extra_id_45>",
|
886 |
+
"<extra_id_46>",
|
887 |
+
"<extra_id_47>",
|
888 |
+
"<extra_id_48>",
|
889 |
+
"<extra_id_49>",
|
890 |
+
"<extra_id_50>",
|
891 |
+
"<extra_id_51>",
|
892 |
+
"<extra_id_52>",
|
893 |
+
"<extra_id_53>",
|
894 |
+
"<extra_id_54>",
|
895 |
+
"<extra_id_55>",
|
896 |
+
"<extra_id_56>",
|
897 |
+
"<extra_id_57>",
|
898 |
+
"<extra_id_58>",
|
899 |
+
"<extra_id_59>",
|
900 |
+
"<extra_id_60>",
|
901 |
+
"<extra_id_61>",
|
902 |
+
"<extra_id_62>",
|
903 |
+
"<extra_id_63>",
|
904 |
+
"<extra_id_64>",
|
905 |
+
"<extra_id_65>",
|
906 |
+
"<extra_id_66>",
|
907 |
+
"<extra_id_67>",
|
908 |
+
"<extra_id_68>",
|
909 |
+
"<extra_id_69>",
|
910 |
+
"<extra_id_70>",
|
911 |
+
"<extra_id_71>",
|
912 |
+
"<extra_id_72>",
|
913 |
+
"<extra_id_73>",
|
914 |
+
"<extra_id_74>",
|
915 |
+
"<extra_id_75>",
|
916 |
+
"<extra_id_76>",
|
917 |
+
"<extra_id_77>",
|
918 |
+
"<extra_id_78>",
|
919 |
+
"<extra_id_79>",
|
920 |
+
"<extra_id_80>",
|
921 |
+
"<extra_id_81>",
|
922 |
+
"<extra_id_82>",
|
923 |
+
"<extra_id_83>",
|
924 |
+
"<extra_id_84>",
|
925 |
+
"<extra_id_85>",
|
926 |
+
"<extra_id_86>",
|
927 |
+
"<extra_id_87>",
|
928 |
+
"<extra_id_88>",
|
929 |
+
"<extra_id_89>",
|
930 |
+
"<extra_id_90>",
|
931 |
+
"<extra_id_91>",
|
932 |
+
"<extra_id_92>",
|
933 |
+
"<extra_id_93>",
|
934 |
+
"<extra_id_94>",
|
935 |
+
"<extra_id_95>",
|
936 |
+
"<extra_id_96>",
|
937 |
+
"<extra_id_97>",
|
938 |
+
"<extra_id_98>",
|
939 |
+
"<extra_id_99>"
|
940 |
+
],
|
941 |
+
"bos_token": "<s>",
|
942 |
+
"chat_template": "{% for message in messages %}{{message['role'].capitalize() + ': ' + message['content'] + '\n\n'}}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
|
943 |
+
"clean_up_tokenization_spaces": false,
|
944 |
+
"eos_token": "</s>",
|
945 |
+
"legacy": false,
|
946 |
+
"model_max_length": 1000000000,
|
947 |
+
"pad_token": "<pad>",
|
948 |
+
"sp_model_kwargs": {},
|
949 |
+
"spaces_between_special_tokens": false,
|
950 |
+
"tokenizer_class": "LlamaTokenizer",
|
951 |
+
"unk_token": "<unk>",
|
952 |
+
"use_default_system_prompt": false
|
953 |
+
}
|