douy commited on
Commit
0e3a376
1 Parent(s): 620e7a2

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<DR_0.15>": 32167,
3
+ "<DR_0.25>": 32145,
4
+ "<DR_0.2>": 32214,
5
+ "<DR_0.35>": 32100,
6
+ "<DR_0.3>": 32138,
7
+ "<DR_0.45>": 32210,
8
+ "<DR_0.4>": 32106,
9
+ "<DR_0.55>": 32101,
10
+ "<DR_0.5>": 32200,
11
+ "<DR_0.65>": 32114,
12
+ "<DR_0.6>": 32111,
13
+ "<DR_0.75>": 32181,
14
+ "<DR_0.7>": 32201,
15
+ "<DR_0.85>": 32136,
16
+ "<DR_0.8>": 32141,
17
+ "<DR_0.95>": 32205,
18
+ "<DR_0.9>": 32168,
19
+ "<DR_1.05>": 32193,
20
+ "<DR_1.0>": 32216,
21
+ "<DR_1.15>": 32128,
22
+ "<DR_1.1>": 32113,
23
+ "<DR_1.25>": 32219,
24
+ "<DR_1.2>": 32151,
25
+ "<DR_1.35>": 32129,
26
+ "<DR_1.3>": 32186,
27
+ "<DR_1.45>": 32226,
28
+ "<DR_1.4>": 32218,
29
+ "<DR_1.55>": 32171,
30
+ "<DR_1.5>": 32177,
31
+ "<DR_1.65>": 32132,
32
+ "<DR_1.6>": 32194,
33
+ "<DR_1.75>": 32166,
34
+ "<DR_1.7>": 32215,
35
+ "<DR_1.85>": 32104,
36
+ "<DR_1.8>": 32103,
37
+ "<DR_1.95>": 32191,
38
+ "<DR_1.9>": 32150,
39
+ "<DR_2.0>": 32134,
40
+ "<LS_0.25>": 32160,
41
+ "<LS_0.2>": 32146,
42
+ "<LS_0.35>": 32208,
43
+ "<LS_0.3>": 32212,
44
+ "<LS_0.45>": 32165,
45
+ "<LS_0.4>": 32133,
46
+ "<LS_0.55>": 32155,
47
+ "<LS_0.5>": 32206,
48
+ "<LS_0.65>": 32123,
49
+ "<LS_0.6>": 32180,
50
+ "<LS_0.75>": 32164,
51
+ "<LS_0.7>": 32188,
52
+ "<LS_0.85>": 32195,
53
+ "<LS_0.8>": 32190,
54
+ "<LS_0.95>": 32115,
55
+ "<LS_0.9>": 32158,
56
+ "<LS_1.0>": 32221,
57
+ "<NC_0.15>": 32225,
58
+ "<NC_0.1>": 32137,
59
+ "<NC_0.25>": 32185,
60
+ "<NC_0.2>": 32144,
61
+ "<NC_0.35>": 32118,
62
+ "<NC_0.3>": 32105,
63
+ "<NC_0.45>": 32125,
64
+ "<NC_0.4>": 32140,
65
+ "<NC_0.55>": 32170,
66
+ "<NC_0.5>": 32107,
67
+ "<NC_0.65>": 32213,
68
+ "<NC_0.6>": 32179,
69
+ "<NC_0.75>": 32217,
70
+ "<NC_0.7>": 32197,
71
+ "<NC_0.85>": 32135,
72
+ "<NC_0.8>": 32227,
73
+ "<NC_0.95>": 32109,
74
+ "<NC_0.9>": 32209,
75
+ "<NC_1.05>": 32127,
76
+ "<NC_1.0>": 32211,
77
+ "<NC_1.15>": 32223,
78
+ "<NC_1.1>": 32156,
79
+ "<NC_1.25>": 32178,
80
+ "<NC_1.2>": 32207,
81
+ "<NC_1.35>": 32176,
82
+ "<NC_1.3>": 32199,
83
+ "<NC_1.45>": 32117,
84
+ "<NC_1.4>": 32184,
85
+ "<NC_1.55>": 32162,
86
+ "<NC_1.5>": 32169,
87
+ "<NC_1.65>": 32139,
88
+ "<NC_1.6>": 32163,
89
+ "<NC_1.75>": 32183,
90
+ "<NC_1.7>": 32121,
91
+ "<NC_1.85>": 32174,
92
+ "<NC_1.8>": 32147,
93
+ "<NC_1.95>": 32182,
94
+ "<NC_1.9>": 32157,
95
+ "<NC_2.0>": 32204,
96
+ "<WR_0.35>": 32222,
97
+ "<WR_0.45>": 32110,
98
+ "<WR_0.4>": 32153,
99
+ "<WR_0.55>": 32143,
100
+ "<WR_0.5>": 32192,
101
+ "<WR_0.65>": 32187,
102
+ "<WR_0.6>": 32198,
103
+ "<WR_0.75>": 32202,
104
+ "<WR_0.7>": 32108,
105
+ "<WR_0.85>": 32142,
106
+ "<WR_0.8>": 32189,
107
+ "<WR_0.95>": 32149,
108
+ "<WR_0.9>": 32196,
109
+ "<WR_1.05>": 32120,
110
+ "<WR_1.0>": 32112,
111
+ "<WR_1.15>": 32130,
112
+ "<WR_1.1>": 32173,
113
+ "<WR_1.25>": 32172,
114
+ "<WR_1.2>": 32119,
115
+ "<WR_1.35>": 32152,
116
+ "<WR_1.3>": 32122,
117
+ "<WR_1.45>": 32224,
118
+ "<WR_1.4>": 32102,
119
+ "<WR_1.55>": 32131,
120
+ "<WR_1.5>": 32154,
121
+ "<WR_1.65>": 32126,
122
+ "<WR_1.6>": 32116,
123
+ "<WR_1.75>": 32148,
124
+ "<WR_1.7>": 32175,
125
+ "<WR_1.85>": 32159,
126
+ "<WR_1.8>": 32161,
127
+ "<WR_1.95>": 32220,
128
+ "<WR_1.9>": 32203,
129
+ "<WR_2.0>": 32124
130
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<DR_0.35>",
4
+ "<DR_0.55>",
5
+ "<WR_1.4>",
6
+ "<DR_1.8>",
7
+ "<DR_1.85>",
8
+ "<NC_0.3>",
9
+ "<DR_0.4>",
10
+ "<NC_0.5>",
11
+ "<WR_0.7>",
12
+ "<NC_0.95>",
13
+ "<WR_0.45>",
14
+ "<DR_0.6>",
15
+ "<WR_1.0>",
16
+ "<DR_1.1>",
17
+ "<DR_0.65>",
18
+ "<LS_0.95>",
19
+ "<WR_1.6>",
20
+ "<NC_1.45>",
21
+ "<NC_0.35>",
22
+ "<WR_1.2>",
23
+ "<WR_1.05>",
24
+ "<NC_1.7>",
25
+ "<WR_1.3>",
26
+ "<LS_0.65>",
27
+ "<WR_2.0>",
28
+ "<NC_0.45>",
29
+ "<WR_1.65>",
30
+ "<NC_1.05>",
31
+ "<DR_1.15>",
32
+ "<DR_1.35>",
33
+ "<WR_1.15>",
34
+ "<WR_1.55>",
35
+ "<DR_1.65>",
36
+ "<LS_0.4>",
37
+ "<DR_2.0>",
38
+ "<NC_0.85>",
39
+ "<DR_0.85>",
40
+ "<NC_0.1>",
41
+ "<DR_0.3>",
42
+ "<NC_1.65>",
43
+ "<NC_0.4>",
44
+ "<DR_0.8>",
45
+ "<WR_0.85>",
46
+ "<WR_0.55>",
47
+ "<NC_0.2>",
48
+ "<DR_0.25>",
49
+ "<LS_0.2>",
50
+ "<NC_1.8>",
51
+ "<WR_1.75>",
52
+ "<WR_0.95>",
53
+ "<DR_1.9>",
54
+ "<DR_1.2>",
55
+ "<WR_1.35>",
56
+ "<WR_0.4>",
57
+ "<WR_1.5>",
58
+ "<LS_0.55>",
59
+ "<NC_1.1>",
60
+ "<NC_1.9>",
61
+ "<LS_0.9>",
62
+ "<WR_1.85>",
63
+ "<LS_0.25>",
64
+ "<WR_1.8>",
65
+ "<NC_1.55>",
66
+ "<NC_1.6>",
67
+ "<LS_0.75>",
68
+ "<LS_0.45>",
69
+ "<DR_1.75>",
70
+ "<DR_0.15>",
71
+ "<DR_0.9>",
72
+ "<NC_1.5>",
73
+ "<NC_0.55>",
74
+ "<DR_1.55>",
75
+ "<WR_1.25>",
76
+ "<WR_1.1>",
77
+ "<NC_1.85>",
78
+ "<WR_1.7>",
79
+ "<NC_1.35>",
80
+ "<DR_1.5>",
81
+ "<NC_1.25>",
82
+ "<NC_0.6>",
83
+ "<LS_0.6>",
84
+ "<DR_0.75>",
85
+ "<NC_1.95>",
86
+ "<NC_1.75>",
87
+ "<NC_1.4>",
88
+ "<NC_0.25>",
89
+ "<DR_1.3>",
90
+ "<WR_0.65>",
91
+ "<LS_0.7>",
92
+ "<WR_0.8>",
93
+ "<LS_0.8>",
94
+ "<DR_1.95>",
95
+ "<WR_0.5>",
96
+ "<DR_1.05>",
97
+ "<DR_1.6>",
98
+ "<LS_0.85>",
99
+ "<WR_0.9>",
100
+ "<NC_0.7>",
101
+ "<WR_0.6>",
102
+ "<NC_1.3>",
103
+ "<DR_0.5>",
104
+ "<DR_0.7>",
105
+ "<WR_0.75>",
106
+ "<WR_1.9>",
107
+ "<NC_2.0>",
108
+ "<DR_0.95>",
109
+ "<LS_0.5>",
110
+ "<NC_1.2>",
111
+ "<LS_0.35>",
112
+ "<NC_0.9>",
113
+ "<DR_0.45>",
114
+ "<NC_1.0>",
115
+ "<LS_0.3>",
116
+ "<NC_0.65>",
117
+ "<DR_0.2>",
118
+ "<DR_1.7>",
119
+ "<DR_1.0>",
120
+ "<NC_0.75>",
121
+ "<DR_1.4>",
122
+ "<DR_1.25>",
123
+ "<WR_1.95>",
124
+ "<LS_1.0>",
125
+ "<WR_0.35>",
126
+ "<NC_1.15>",
127
+ "<WR_1.45>",
128
+ "<NC_0.15>",
129
+ "<DR_1.45>",
130
+ "<NC_0.8>"
131
+ ],
132
+ "eos_token": "</s>",
133
+ "pad_token": "<pad>",
134
+ "unk_token": "<unk>"
135
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
105
+ "eos_token": "</s>",
106
+ "extra_ids": 100,
107
+ "model_max_length": 512,
108
+ "pad_token": "<pad>",
109
+ "sp_model_kwargs": {},
110
+ "tokenizer_class": "T5Tokenizer",
111
+ "unk_token": "<unk>"
112
+ }