acmc commited on
Commit
b66e9e5
1 Parent(s): 5a3a609

Pushing tokenizer (#2)

Browse files

- Pushing tokenizer (265df0c0f3f55197dc8fa9120444a2c09b0c35e8)

added_tokens.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " | ": 32106,
3
+ " ||| ": 32107,
4
+ "[BACKGROUND]": 32102,
5
+ "[CONCLUSIONS]": 32105,
6
+ "[CONTENT]": 32100,
7
+ "[METHODS]": 32103,
8
+ "[RESULTS]": 32104,
9
+ "[SUMMARY]": 32101
10
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "</s>",
4
+ "<unk>",
5
+ "<pad>",
6
+ "<extra_id_0>",
7
+ "<extra_id_1>",
8
+ "<extra_id_2>",
9
+ "<extra_id_3>",
10
+ "<extra_id_4>",
11
+ "<extra_id_5>",
12
+ "<extra_id_6>",
13
+ "<extra_id_7>",
14
+ "<extra_id_8>",
15
+ "<extra_id_9>",
16
+ "<extra_id_10>",
17
+ "<extra_id_11>",
18
+ "<extra_id_12>",
19
+ "<extra_id_13>",
20
+ "<extra_id_14>",
21
+ "<extra_id_15>",
22
+ "<extra_id_16>",
23
+ "<extra_id_17>",
24
+ "<extra_id_18>",
25
+ "<extra_id_19>",
26
+ "<extra_id_20>",
27
+ "<extra_id_21>",
28
+ "<extra_id_22>",
29
+ "<extra_id_23>",
30
+ "<extra_id_24>",
31
+ "<extra_id_25>",
32
+ "<extra_id_26>",
33
+ "<extra_id_27>",
34
+ "<extra_id_28>",
35
+ "<extra_id_29>",
36
+ "<extra_id_30>",
37
+ "<extra_id_31>",
38
+ "<extra_id_32>",
39
+ "<extra_id_33>",
40
+ "<extra_id_34>",
41
+ "<extra_id_35>",
42
+ "<extra_id_36>",
43
+ "<extra_id_37>",
44
+ "<extra_id_38>",
45
+ "<extra_id_39>",
46
+ "<extra_id_40>",
47
+ "<extra_id_41>",
48
+ "<extra_id_42>",
49
+ "<extra_id_43>",
50
+ "<extra_id_44>",
51
+ "<extra_id_45>",
52
+ "<extra_id_46>",
53
+ "<extra_id_47>",
54
+ "<extra_id_48>",
55
+ "<extra_id_49>",
56
+ "<extra_id_50>",
57
+ "<extra_id_51>",
58
+ "<extra_id_52>",
59
+ "<extra_id_53>",
60
+ "<extra_id_54>",
61
+ "<extra_id_55>",
62
+ "<extra_id_56>",
63
+ "<extra_id_57>",
64
+ "<extra_id_58>",
65
+ "<extra_id_59>",
66
+ "<extra_id_60>",
67
+ "<extra_id_61>",
68
+ "<extra_id_62>",
69
+ "<extra_id_63>",
70
+ "<extra_id_64>",
71
+ "<extra_id_65>",
72
+ "<extra_id_66>",
73
+ "<extra_id_67>",
74
+ "<extra_id_68>",
75
+ "<extra_id_69>",
76
+ "<extra_id_70>",
77
+ "<extra_id_71>",
78
+ "<extra_id_72>",
79
+ "<extra_id_73>",
80
+ "<extra_id_74>",
81
+ "<extra_id_75>",
82
+ "<extra_id_76>",
83
+ "<extra_id_77>",
84
+ "<extra_id_78>",
85
+ "<extra_id_79>",
86
+ "<extra_id_80>",
87
+ "<extra_id_81>",
88
+ "<extra_id_82>",
89
+ "<extra_id_83>",
90
+ "<extra_id_84>",
91
+ "<extra_id_85>",
92
+ "<extra_id_86>",
93
+ "<extra_id_87>",
94
+ "<extra_id_88>",
95
+ "<extra_id_89>",
96
+ "<extra_id_90>",
97
+ "<extra_id_91>",
98
+ "<extra_id_92>",
99
+ "<extra_id_93>",
100
+ "<extra_id_94>",
101
+ "<extra_id_95>",
102
+ "<extra_id_96>",
103
+ "<extra_id_97>",
104
+ "<extra_id_98>",
105
+ "<extra_id_99>",
106
+ "[CONTENT]",
107
+ "[SUMMARY]",
108
+ "[BACKGROUND]",
109
+ "[METHODS]",
110
+ "[RESULTS]",
111
+ "[CONCLUSIONS]",
112
+ " | ",
113
+ " ||| "
114
+ ],
115
+ "eos_token": "</s>",
116
+ "pad_token": "<pad>",
117
+ "unk_token": "<unk>"
118
+ }
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 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "tokenizer_class": "T5Tokenizer",
110
+ "unk_token": "<unk>"
111
+ }