hieunguyen1053 commited on
Commit
615f3ac
1 Parent(s): b09eec5

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 1,
3
+ "<extra_id_0>": 36095,
4
+ "<extra_id_10>": 36085,
5
+ "<extra_id_11>": 36084,
6
+ "<extra_id_12>": 36083,
7
+ "<extra_id_13>": 36082,
8
+ "<extra_id_14>": 36081,
9
+ "<extra_id_15>": 36080,
10
+ "<extra_id_16>": 36079,
11
+ "<extra_id_17>": 36078,
12
+ "<extra_id_18>": 36077,
13
+ "<extra_id_19>": 36076,
14
+ "<extra_id_1>": 36094,
15
+ "<extra_id_20>": 36075,
16
+ "<extra_id_21>": 36074,
17
+ "<extra_id_22>": 36073,
18
+ "<extra_id_23>": 36072,
19
+ "<extra_id_24>": 36071,
20
+ "<extra_id_25>": 36070,
21
+ "<extra_id_26>": 36069,
22
+ "<extra_id_27>": 36068,
23
+ "<extra_id_28>": 36067,
24
+ "<extra_id_29>": 36066,
25
+ "<extra_id_2>": 36093,
26
+ "<extra_id_30>": 36065,
27
+ "<extra_id_31>": 36064,
28
+ "<extra_id_32>": 36063,
29
+ "<extra_id_33>": 36062,
30
+ "<extra_id_34>": 36061,
31
+ "<extra_id_35>": 36060,
32
+ "<extra_id_36>": 36059,
33
+ "<extra_id_37>": 36058,
34
+ "<extra_id_38>": 36057,
35
+ "<extra_id_39>": 36056,
36
+ "<extra_id_3>": 36092,
37
+ "<extra_id_40>": 36055,
38
+ "<extra_id_41>": 36054,
39
+ "<extra_id_42>": 36053,
40
+ "<extra_id_43>": 36052,
41
+ "<extra_id_44>": 36051,
42
+ "<extra_id_45>": 36050,
43
+ "<extra_id_46>": 36049,
44
+ "<extra_id_47>": 36048,
45
+ "<extra_id_48>": 36047,
46
+ "<extra_id_49>": 36046,
47
+ "<extra_id_4>": 36091,
48
+ "<extra_id_50>": 36045,
49
+ "<extra_id_51>": 36044,
50
+ "<extra_id_52>": 36043,
51
+ "<extra_id_53>": 36042,
52
+ "<extra_id_54>": 36041,
53
+ "<extra_id_55>": 36040,
54
+ "<extra_id_56>": 36039,
55
+ "<extra_id_57>": 36038,
56
+ "<extra_id_58>": 36037,
57
+ "<extra_id_59>": 36036,
58
+ "<extra_id_5>": 36090,
59
+ "<extra_id_60>": 36035,
60
+ "<extra_id_61>": 36034,
61
+ "<extra_id_62>": 36033,
62
+ "<extra_id_63>": 36032,
63
+ "<extra_id_64>": 36031,
64
+ "<extra_id_65>": 36030,
65
+ "<extra_id_66>": 36029,
66
+ "<extra_id_67>": 36028,
67
+ "<extra_id_68>": 36027,
68
+ "<extra_id_69>": 36026,
69
+ "<extra_id_6>": 36089,
70
+ "<extra_id_70>": 36025,
71
+ "<extra_id_71>": 36024,
72
+ "<extra_id_72>": 36023,
73
+ "<extra_id_73>": 36022,
74
+ "<extra_id_74>": 36021,
75
+ "<extra_id_75>": 36020,
76
+ "<extra_id_76>": 36019,
77
+ "<extra_id_77>": 36018,
78
+ "<extra_id_78>": 36017,
79
+ "<extra_id_79>": 36016,
80
+ "<extra_id_7>": 36088,
81
+ "<extra_id_80>": 36015,
82
+ "<extra_id_81>": 36014,
83
+ "<extra_id_82>": 36013,
84
+ "<extra_id_83>": 36012,
85
+ "<extra_id_84>": 36011,
86
+ "<extra_id_85>": 36010,
87
+ "<extra_id_86>": 36009,
88
+ "<extra_id_87>": 36008,
89
+ "<extra_id_88>": 36007,
90
+ "<extra_id_89>": 36006,
91
+ "<extra_id_8>": 36087,
92
+ "<extra_id_90>": 36005,
93
+ "<extra_id_91>": 36004,
94
+ "<extra_id_92>": 36003,
95
+ "<extra_id_93>": 36002,
96
+ "<extra_id_94>": 36001,
97
+ "<extra_id_95>": 36000,
98
+ "<extra_id_9>": 36086,
99
+ "<pad>": 0,
100
+ "<unk>": 2,
101
+ "<|coQuanBanHanh|>": 36106,
102
+ "<|endoftext|>": 36096,
103
+ "<|loaiVanBan|>": 36107,
104
+ "<|maDinhDanhCaNhan_hoVaTen|>": 36105,
105
+ "<|maDinhDanhCaNhan_ngaySinh|>": 36103,
106
+ "<|maDinhDanhCaNhan|>": 36100,
107
+ "<|maDinhDanhToChuc_tenToChuc|>": 36099,
108
+ "<|maDinhDanhToChuc|>": 36108,
109
+ "<|ngayBanHanh|>": 36098,
110
+ "<|nguoiKy|>": 36102,
111
+ "<|soHieu|>": 36097,
112
+ "<|thoiHan|>": 36104,
113
+ "<|trichYeu|>": 36101
114
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<pad>",
4
+ "</s>",
5
+ "<unk>",
6
+ "<extra_id_95>",
7
+ "<extra_id_94>",
8
+ "<extra_id_93>",
9
+ "<extra_id_92>",
10
+ "<extra_id_91>",
11
+ "<extra_id_90>",
12
+ "<extra_id_89>",
13
+ "<extra_id_88>",
14
+ "<extra_id_87>",
15
+ "<extra_id_86>",
16
+ "<extra_id_85>",
17
+ "<extra_id_84>",
18
+ "<extra_id_83>",
19
+ "<extra_id_82>",
20
+ "<extra_id_81>",
21
+ "<extra_id_80>",
22
+ "<extra_id_79>",
23
+ "<extra_id_78>",
24
+ "<extra_id_77>",
25
+ "<extra_id_76>",
26
+ "<extra_id_75>",
27
+ "<extra_id_74>",
28
+ "<extra_id_73>",
29
+ "<extra_id_72>",
30
+ "<extra_id_71>",
31
+ "<extra_id_70>",
32
+ "<extra_id_69>",
33
+ "<extra_id_68>",
34
+ "<extra_id_67>",
35
+ "<extra_id_66>",
36
+ "<extra_id_65>",
37
+ "<extra_id_64>",
38
+ "<extra_id_63>",
39
+ "<extra_id_62>",
40
+ "<extra_id_61>",
41
+ "<extra_id_60>",
42
+ "<extra_id_59>",
43
+ "<extra_id_58>",
44
+ "<extra_id_57>",
45
+ "<extra_id_56>",
46
+ "<extra_id_55>",
47
+ "<extra_id_54>",
48
+ "<extra_id_53>",
49
+ "<extra_id_52>",
50
+ "<extra_id_51>",
51
+ "<extra_id_50>",
52
+ "<extra_id_49>",
53
+ "<extra_id_48>",
54
+ "<extra_id_47>",
55
+ "<extra_id_46>",
56
+ "<extra_id_45>",
57
+ "<extra_id_44>",
58
+ "<extra_id_43>",
59
+ "<extra_id_42>",
60
+ "<extra_id_41>",
61
+ "<extra_id_40>",
62
+ "<extra_id_39>",
63
+ "<extra_id_38>",
64
+ "<extra_id_37>",
65
+ "<extra_id_36>",
66
+ "<extra_id_35>",
67
+ "<extra_id_34>",
68
+ "<extra_id_33>",
69
+ "<extra_id_32>",
70
+ "<extra_id_31>",
71
+ "<extra_id_30>",
72
+ "<extra_id_29>",
73
+ "<extra_id_28>",
74
+ "<extra_id_27>",
75
+ "<extra_id_26>",
76
+ "<extra_id_25>",
77
+ "<extra_id_24>",
78
+ "<extra_id_23>",
79
+ "<extra_id_22>",
80
+ "<extra_id_21>",
81
+ "<extra_id_20>",
82
+ "<extra_id_19>",
83
+ "<extra_id_18>",
84
+ "<extra_id_17>",
85
+ "<extra_id_16>",
86
+ "<extra_id_15>",
87
+ "<extra_id_14>",
88
+ "<extra_id_13>",
89
+ "<extra_id_12>",
90
+ "<extra_id_11>",
91
+ "<extra_id_10>",
92
+ "<extra_id_9>",
93
+ "<extra_id_8>",
94
+ "<extra_id_7>",
95
+ "<extra_id_6>",
96
+ "<extra_id_5>",
97
+ "<extra_id_4>",
98
+ "<extra_id_3>",
99
+ "<extra_id_2>",
100
+ "<extra_id_1>",
101
+ "<extra_id_0>",
102
+ "<|endoftext|>",
103
+ "<|soHieu|>",
104
+ "<|ngayBanHanh|>",
105
+ "<|maDinhDanhToChuc_tenToChuc|>",
106
+ "<|maDinhDanhCaNhan|>",
107
+ "<|trichYeu|>",
108
+ "<|nguoiKy|>",
109
+ "<|maDinhDanhCaNhan_ngaySinh|>",
110
+ "<|thoiHan|>",
111
+ "<|maDinhDanhCaNhan_hoVaTen|>",
112
+ "<|coQuanBanHanh|>",
113
+ "<|loaiVanBan|>",
114
+ "<|maDinhDanhToChuc|>"
115
+ ],
116
+ "eos_token": "</s>",
117
+ "pad_token": "<pad>",
118
+ "unk_token": "<unk>"
119
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59986b62f9f0b90edafb9b073ea7b93d21114a5841219a1ea2399ade73f729c6
3
+ size 820370
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,1022 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "36000": {
28
+ "content": "<extra_id_95>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "36001": {
36
+ "content": "<extra_id_94>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "36002": {
44
+ "content": "<extra_id_93>",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "36003": {
52
+ "content": "<extra_id_92>",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "36004": {
60
+ "content": "<extra_id_91>",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "36005": {
68
+ "content": "<extra_id_90>",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "36006": {
76
+ "content": "<extra_id_89>",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "36007": {
84
+ "content": "<extra_id_88>",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "36008": {
92
+ "content": "<extra_id_87>",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "36009": {
100
+ "content": "<extra_id_86>",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "36010": {
108
+ "content": "<extra_id_85>",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "36011": {
116
+ "content": "<extra_id_84>",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "36012": {
124
+ "content": "<extra_id_83>",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "36013": {
132
+ "content": "<extra_id_82>",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "36014": {
140
+ "content": "<extra_id_81>",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "36015": {
148
+ "content": "<extra_id_80>",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "36016": {
156
+ "content": "<extra_id_79>",
157
+ "lstrip": true,
158
+ "normalized": false,
159
+ "rstrip": true,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "36017": {
164
+ "content": "<extra_id_78>",
165
+ "lstrip": true,
166
+ "normalized": false,
167
+ "rstrip": true,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "36018": {
172
+ "content": "<extra_id_77>",
173
+ "lstrip": true,
174
+ "normalized": false,
175
+ "rstrip": true,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "36019": {
180
+ "content": "<extra_id_76>",
181
+ "lstrip": true,
182
+ "normalized": false,
183
+ "rstrip": true,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "36020": {
188
+ "content": "<extra_id_75>",
189
+ "lstrip": true,
190
+ "normalized": false,
191
+ "rstrip": true,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "36021": {
196
+ "content": "<extra_id_74>",
197
+ "lstrip": true,
198
+ "normalized": false,
199
+ "rstrip": true,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "36022": {
204
+ "content": "<extra_id_73>",
205
+ "lstrip": true,
206
+ "normalized": false,
207
+ "rstrip": true,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "36023": {
212
+ "content": "<extra_id_72>",
213
+ "lstrip": true,
214
+ "normalized": false,
215
+ "rstrip": true,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "36024": {
220
+ "content": "<extra_id_71>",
221
+ "lstrip": true,
222
+ "normalized": false,
223
+ "rstrip": true,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "36025": {
228
+ "content": "<extra_id_70>",
229
+ "lstrip": true,
230
+ "normalized": false,
231
+ "rstrip": true,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "36026": {
236
+ "content": "<extra_id_69>",
237
+ "lstrip": true,
238
+ "normalized": false,
239
+ "rstrip": true,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "36027": {
244
+ "content": "<extra_id_68>",
245
+ "lstrip": true,
246
+ "normalized": false,
247
+ "rstrip": true,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "36028": {
252
+ "content": "<extra_id_67>",
253
+ "lstrip": true,
254
+ "normalized": false,
255
+ "rstrip": true,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "36029": {
260
+ "content": "<extra_id_66>",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": true,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "36030": {
268
+ "content": "<extra_id_65>",
269
+ "lstrip": true,
270
+ "normalized": false,
271
+ "rstrip": true,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "36031": {
276
+ "content": "<extra_id_64>",
277
+ "lstrip": true,
278
+ "normalized": false,
279
+ "rstrip": true,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "36032": {
284
+ "content": "<extra_id_63>",
285
+ "lstrip": true,
286
+ "normalized": false,
287
+ "rstrip": true,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "36033": {
292
+ "content": "<extra_id_62>",
293
+ "lstrip": true,
294
+ "normalized": false,
295
+ "rstrip": true,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "36034": {
300
+ "content": "<extra_id_61>",
301
+ "lstrip": true,
302
+ "normalized": false,
303
+ "rstrip": true,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "36035": {
308
+ "content": "<extra_id_60>",
309
+ "lstrip": true,
310
+ "normalized": false,
311
+ "rstrip": true,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "36036": {
316
+ "content": "<extra_id_59>",
317
+ "lstrip": true,
318
+ "normalized": false,
319
+ "rstrip": true,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "36037": {
324
+ "content": "<extra_id_58>",
325
+ "lstrip": true,
326
+ "normalized": false,
327
+ "rstrip": true,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "36038": {
332
+ "content": "<extra_id_57>",
333
+ "lstrip": true,
334
+ "normalized": false,
335
+ "rstrip": true,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "36039": {
340
+ "content": "<extra_id_56>",
341
+ "lstrip": true,
342
+ "normalized": false,
343
+ "rstrip": true,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "36040": {
348
+ "content": "<extra_id_55>",
349
+ "lstrip": true,
350
+ "normalized": false,
351
+ "rstrip": true,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "36041": {
356
+ "content": "<extra_id_54>",
357
+ "lstrip": true,
358
+ "normalized": false,
359
+ "rstrip": true,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "36042": {
364
+ "content": "<extra_id_53>",
365
+ "lstrip": true,
366
+ "normalized": false,
367
+ "rstrip": true,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "36043": {
372
+ "content": "<extra_id_52>",
373
+ "lstrip": true,
374
+ "normalized": false,
375
+ "rstrip": true,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "36044": {
380
+ "content": "<extra_id_51>",
381
+ "lstrip": true,
382
+ "normalized": false,
383
+ "rstrip": true,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "36045": {
388
+ "content": "<extra_id_50>",
389
+ "lstrip": true,
390
+ "normalized": false,
391
+ "rstrip": true,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "36046": {
396
+ "content": "<extra_id_49>",
397
+ "lstrip": true,
398
+ "normalized": false,
399
+ "rstrip": true,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "36047": {
404
+ "content": "<extra_id_48>",
405
+ "lstrip": true,
406
+ "normalized": false,
407
+ "rstrip": true,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "36048": {
412
+ "content": "<extra_id_47>",
413
+ "lstrip": true,
414
+ "normalized": false,
415
+ "rstrip": true,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "36049": {
420
+ "content": "<extra_id_46>",
421
+ "lstrip": true,
422
+ "normalized": false,
423
+ "rstrip": true,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "36050": {
428
+ "content": "<extra_id_45>",
429
+ "lstrip": true,
430
+ "normalized": false,
431
+ "rstrip": true,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "36051": {
436
+ "content": "<extra_id_44>",
437
+ "lstrip": true,
438
+ "normalized": false,
439
+ "rstrip": true,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "36052": {
444
+ "content": "<extra_id_43>",
445
+ "lstrip": true,
446
+ "normalized": false,
447
+ "rstrip": true,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "36053": {
452
+ "content": "<extra_id_42>",
453
+ "lstrip": true,
454
+ "normalized": false,
455
+ "rstrip": true,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "36054": {
460
+ "content": "<extra_id_41>",
461
+ "lstrip": true,
462
+ "normalized": false,
463
+ "rstrip": true,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "36055": {
468
+ "content": "<extra_id_40>",
469
+ "lstrip": true,
470
+ "normalized": false,
471
+ "rstrip": true,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "36056": {
476
+ "content": "<extra_id_39>",
477
+ "lstrip": true,
478
+ "normalized": false,
479
+ "rstrip": true,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "36057": {
484
+ "content": "<extra_id_38>",
485
+ "lstrip": true,
486
+ "normalized": false,
487
+ "rstrip": true,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "36058": {
492
+ "content": "<extra_id_37>",
493
+ "lstrip": true,
494
+ "normalized": false,
495
+ "rstrip": true,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "36059": {
500
+ "content": "<extra_id_36>",
501
+ "lstrip": true,
502
+ "normalized": false,
503
+ "rstrip": true,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "36060": {
508
+ "content": "<extra_id_35>",
509
+ "lstrip": true,
510
+ "normalized": false,
511
+ "rstrip": true,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "36061": {
516
+ "content": "<extra_id_34>",
517
+ "lstrip": true,
518
+ "normalized": false,
519
+ "rstrip": true,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "36062": {
524
+ "content": "<extra_id_33>",
525
+ "lstrip": true,
526
+ "normalized": false,
527
+ "rstrip": true,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "36063": {
532
+ "content": "<extra_id_32>",
533
+ "lstrip": true,
534
+ "normalized": false,
535
+ "rstrip": true,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "36064": {
540
+ "content": "<extra_id_31>",
541
+ "lstrip": true,
542
+ "normalized": false,
543
+ "rstrip": true,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "36065": {
548
+ "content": "<extra_id_30>",
549
+ "lstrip": true,
550
+ "normalized": false,
551
+ "rstrip": true,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "36066": {
556
+ "content": "<extra_id_29>",
557
+ "lstrip": true,
558
+ "normalized": false,
559
+ "rstrip": true,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "36067": {
564
+ "content": "<extra_id_28>",
565
+ "lstrip": true,
566
+ "normalized": false,
567
+ "rstrip": true,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "36068": {
572
+ "content": "<extra_id_27>",
573
+ "lstrip": true,
574
+ "normalized": false,
575
+ "rstrip": true,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "36069": {
580
+ "content": "<extra_id_26>",
581
+ "lstrip": true,
582
+ "normalized": false,
583
+ "rstrip": true,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "36070": {
588
+ "content": "<extra_id_25>",
589
+ "lstrip": true,
590
+ "normalized": false,
591
+ "rstrip": true,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "36071": {
596
+ "content": "<extra_id_24>",
597
+ "lstrip": true,
598
+ "normalized": false,
599
+ "rstrip": true,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "36072": {
604
+ "content": "<extra_id_23>",
605
+ "lstrip": true,
606
+ "normalized": false,
607
+ "rstrip": true,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "36073": {
612
+ "content": "<extra_id_22>",
613
+ "lstrip": true,
614
+ "normalized": false,
615
+ "rstrip": true,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "36074": {
620
+ "content": "<extra_id_21>",
621
+ "lstrip": true,
622
+ "normalized": false,
623
+ "rstrip": true,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "36075": {
628
+ "content": "<extra_id_20>",
629
+ "lstrip": true,
630
+ "normalized": false,
631
+ "rstrip": true,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "36076": {
636
+ "content": "<extra_id_19>",
637
+ "lstrip": true,
638
+ "normalized": false,
639
+ "rstrip": true,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "36077": {
644
+ "content": "<extra_id_18>",
645
+ "lstrip": true,
646
+ "normalized": false,
647
+ "rstrip": true,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "36078": {
652
+ "content": "<extra_id_17>",
653
+ "lstrip": true,
654
+ "normalized": false,
655
+ "rstrip": true,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "36079": {
660
+ "content": "<extra_id_16>",
661
+ "lstrip": true,
662
+ "normalized": false,
663
+ "rstrip": true,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "36080": {
668
+ "content": "<extra_id_15>",
669
+ "lstrip": true,
670
+ "normalized": false,
671
+ "rstrip": true,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "36081": {
676
+ "content": "<extra_id_14>",
677
+ "lstrip": true,
678
+ "normalized": false,
679
+ "rstrip": true,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "36082": {
684
+ "content": "<extra_id_13>",
685
+ "lstrip": true,
686
+ "normalized": false,
687
+ "rstrip": true,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "36083": {
692
+ "content": "<extra_id_12>",
693
+ "lstrip": true,
694
+ "normalized": false,
695
+ "rstrip": true,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "36084": {
700
+ "content": "<extra_id_11>",
701
+ "lstrip": true,
702
+ "normalized": false,
703
+ "rstrip": true,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "36085": {
708
+ "content": "<extra_id_10>",
709
+ "lstrip": true,
710
+ "normalized": false,
711
+ "rstrip": true,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "36086": {
716
+ "content": "<extra_id_9>",
717
+ "lstrip": true,
718
+ "normalized": false,
719
+ "rstrip": true,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "36087": {
724
+ "content": "<extra_id_8>",
725
+ "lstrip": true,
726
+ "normalized": false,
727
+ "rstrip": true,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "36088": {
732
+ "content": "<extra_id_7>",
733
+ "lstrip": true,
734
+ "normalized": false,
735
+ "rstrip": true,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "36089": {
740
+ "content": "<extra_id_6>",
741
+ "lstrip": true,
742
+ "normalized": false,
743
+ "rstrip": true,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "36090": {
748
+ "content": "<extra_id_5>",
749
+ "lstrip": true,
750
+ "normalized": false,
751
+ "rstrip": true,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "36091": {
756
+ "content": "<extra_id_4>",
757
+ "lstrip": true,
758
+ "normalized": false,
759
+ "rstrip": true,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "36092": {
764
+ "content": "<extra_id_3>",
765
+ "lstrip": true,
766
+ "normalized": false,
767
+ "rstrip": true,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "36093": {
772
+ "content": "<extra_id_2>",
773
+ "lstrip": true,
774
+ "normalized": false,
775
+ "rstrip": true,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "36094": {
780
+ "content": "<extra_id_1>",
781
+ "lstrip": true,
782
+ "normalized": false,
783
+ "rstrip": true,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "36095": {
788
+ "content": "<extra_id_0>",
789
+ "lstrip": true,
790
+ "normalized": false,
791
+ "rstrip": true,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "36096": {
796
+ "content": "<|endoftext|>",
797
+ "lstrip": true,
798
+ "normalized": false,
799
+ "rstrip": true,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "36097": {
804
+ "content": "<|soHieu|>",
805
+ "lstrip": true,
806
+ "normalized": false,
807
+ "rstrip": true,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "36098": {
812
+ "content": "<|ngayBanHanh|>",
813
+ "lstrip": true,
814
+ "normalized": false,
815
+ "rstrip": true,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "36099": {
820
+ "content": "<|maDinhDanhToChuc_tenToChuc|>",
821
+ "lstrip": true,
822
+ "normalized": false,
823
+ "rstrip": true,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "36100": {
828
+ "content": "<|maDinhDanhCaNhan|>",
829
+ "lstrip": true,
830
+ "normalized": false,
831
+ "rstrip": true,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "36101": {
836
+ "content": "<|trichYeu|>",
837
+ "lstrip": true,
838
+ "normalized": false,
839
+ "rstrip": true,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "36102": {
844
+ "content": "<|nguoiKy|>",
845
+ "lstrip": true,
846
+ "normalized": false,
847
+ "rstrip": true,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "36103": {
852
+ "content": "<|maDinhDanhCaNhan_ngaySinh|>",
853
+ "lstrip": true,
854
+ "normalized": false,
855
+ "rstrip": true,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "36104": {
860
+ "content": "<|thoiHan|>",
861
+ "lstrip": true,
862
+ "normalized": false,
863
+ "rstrip": true,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "36105": {
868
+ "content": "<|maDinhDanhCaNhan_hoVaTen|>",
869
+ "lstrip": true,
870
+ "normalized": false,
871
+ "rstrip": true,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "36106": {
876
+ "content": "<|coQuanBanHanh|>",
877
+ "lstrip": true,
878
+ "normalized": false,
879
+ "rstrip": true,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "36107": {
884
+ "content": "<|loaiVanBan|>",
885
+ "lstrip": true,
886
+ "normalized": false,
887
+ "rstrip": true,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "36108": {
892
+ "content": "<|maDinhDanhToChuc|>",
893
+ "lstrip": true,
894
+ "normalized": false,
895
+ "rstrip": true,
896
+ "single_word": false,
897
+ "special": true
898
+ }
899
+ },
900
+ "additional_special_tokens": [
901
+ "<pad>",
902
+ "</s>",
903
+ "<unk>",
904
+ "<extra_id_95>",
905
+ "<extra_id_94>",
906
+ "<extra_id_93>",
907
+ "<extra_id_92>",
908
+ "<extra_id_91>",
909
+ "<extra_id_90>",
910
+ "<extra_id_89>",
911
+ "<extra_id_88>",
912
+ "<extra_id_87>",
913
+ "<extra_id_86>",
914
+ "<extra_id_85>",
915
+ "<extra_id_84>",
916
+ "<extra_id_83>",
917
+ "<extra_id_82>",
918
+ "<extra_id_81>",
919
+ "<extra_id_80>",
920
+ "<extra_id_79>",
921
+ "<extra_id_78>",
922
+ "<extra_id_77>",
923
+ "<extra_id_76>",
924
+ "<extra_id_75>",
925
+ "<extra_id_74>",
926
+ "<extra_id_73>",
927
+ "<extra_id_72>",
928
+ "<extra_id_71>",
929
+ "<extra_id_70>",
930
+ "<extra_id_69>",
931
+ "<extra_id_68>",
932
+ "<extra_id_67>",
933
+ "<extra_id_66>",
934
+ "<extra_id_65>",
935
+ "<extra_id_64>",
936
+ "<extra_id_63>",
937
+ "<extra_id_62>",
938
+ "<extra_id_61>",
939
+ "<extra_id_60>",
940
+ "<extra_id_59>",
941
+ "<extra_id_58>",
942
+ "<extra_id_57>",
943
+ "<extra_id_56>",
944
+ "<extra_id_55>",
945
+ "<extra_id_54>",
946
+ "<extra_id_53>",
947
+ "<extra_id_52>",
948
+ "<extra_id_51>",
949
+ "<extra_id_50>",
950
+ "<extra_id_49>",
951
+ "<extra_id_48>",
952
+ "<extra_id_47>",
953
+ "<extra_id_46>",
954
+ "<extra_id_45>",
955
+ "<extra_id_44>",
956
+ "<extra_id_43>",
957
+ "<extra_id_42>",
958
+ "<extra_id_41>",
959
+ "<extra_id_40>",
960
+ "<extra_id_39>",
961
+ "<extra_id_38>",
962
+ "<extra_id_37>",
963
+ "<extra_id_36>",
964
+ "<extra_id_35>",
965
+ "<extra_id_34>",
966
+ "<extra_id_33>",
967
+ "<extra_id_32>",
968
+ "<extra_id_31>",
969
+ "<extra_id_30>",
970
+ "<extra_id_29>",
971
+ "<extra_id_28>",
972
+ "<extra_id_27>",
973
+ "<extra_id_26>",
974
+ "<extra_id_25>",
975
+ "<extra_id_24>",
976
+ "<extra_id_23>",
977
+ "<extra_id_22>",
978
+ "<extra_id_21>",
979
+ "<extra_id_20>",
980
+ "<extra_id_19>",
981
+ "<extra_id_18>",
982
+ "<extra_id_17>",
983
+ "<extra_id_16>",
984
+ "<extra_id_15>",
985
+ "<extra_id_14>",
986
+ "<extra_id_13>",
987
+ "<extra_id_12>",
988
+ "<extra_id_11>",
989
+ "<extra_id_10>",
990
+ "<extra_id_9>",
991
+ "<extra_id_8>",
992
+ "<extra_id_7>",
993
+ "<extra_id_6>",
994
+ "<extra_id_5>",
995
+ "<extra_id_4>",
996
+ "<extra_id_3>",
997
+ "<extra_id_2>",
998
+ "<extra_id_1>",
999
+ "<extra_id_0>",
1000
+ "<|endoftext|>",
1001
+ "<|soHieu|>",
1002
+ "<|ngayBanHanh|>",
1003
+ "<|maDinhDanhToChuc_tenToChuc|>",
1004
+ "<|maDinhDanhCaNhan|>",
1005
+ "<|trichYeu|>",
1006
+ "<|nguoiKy|>",
1007
+ "<|maDinhDanhCaNhan_ngaySinh|>",
1008
+ "<|thoiHan|>",
1009
+ "<|maDinhDanhCaNhan_hoVaTen|>",
1010
+ "<|coQuanBanHanh|>",
1011
+ "<|loaiVanBan|>",
1012
+ "<|maDinhDanhToChuc|>"
1013
+ ],
1014
+ "clean_up_tokenization_spaces": true,
1015
+ "eos_token": "</s>",
1016
+ "extra_ids": 96,
1017
+ "model_max_length": 1000000000000000019884624838656,
1018
+ "pad_token": "<pad>",
1019
+ "sp_model_kwargs": {},
1020
+ "tokenizer_class": "T5Tokenizer",
1021
+ "unk_token": "<unk>"
1022
+ }