mrmoor commited on
Commit
bf139c1
1 Parent(s): d06231b

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "/business/company/advisors": 32130,
3
+ "/business/company/founders": 32128,
4
+ "/business/company/industry": 32139,
5
+ "/business/company/major_shareholders": 32135,
6
+ "/business/company/place_founded": 32126,
7
+ "/business/company_shareholder/major_shareholder_of": 32134,
8
+ "/business/person/company": 32118,
9
+ "/location/administrative_division/country": 32120,
10
+ "/location/country/administrative_divisions": 32121,
11
+ "/location/country/capital": 32125,
12
+ "/location/location/contains": 32116,
13
+ "/location/neighborhood/neighborhood_of": 32129,
14
+ "/people/deceased_person/place_of_death": 32127,
15
+ "/people/ethnicity/geographic_distribution": 32131,
16
+ "/people/ethnicity/people": 32137,
17
+ "/people/person/children": 32124,
18
+ "/people/person/ethnicity": 32136,
19
+ "/people/person/nationality": 32123,
20
+ "/people/person/place_lived": 32119,
21
+ "/people/person/place_of_birth": 32117,
22
+ "/people/person/profession": 32138,
23
+ "/people/person/religion": 32122,
24
+ "/sports/sports_team/location": 32133,
25
+ "/sports/sports_team_location/teams": 32132,
26
+ "</apt>": 32179,
27
+ "</attack-pattern>": 32161,
28
+ "</campaign>": 32172,
29
+ "</domain>": 32170,
30
+ "</email>": 32175,
31
+ "</filepath>": 32167,
32
+ "</head>": 32110,
33
+ "</identity>": 32163,
34
+ "</infrastucture>": 32173,
35
+ "</ipv4>": 32174,
36
+ "</location>": 32114,
37
+ "</malware>": 32160,
38
+ "</md5>": 32178,
39
+ "</organization>": 32113,
40
+ "</person>": 32115,
41
+ "</registrykey>": 32176,
42
+ "</rel>": 32112,
43
+ "</sha1>": 32177,
44
+ "</sha2>": 32168,
45
+ "</software>": 32164,
46
+ "</subj>": 32111,
47
+ "</text-to-xml>": 32108,
48
+ "</threat-actor>": 32165,
49
+ "</time>": 32162,
50
+ "</tools>": 32166,
51
+ "</triplet>": 32109,
52
+ "</url>": 32171,
53
+ "</vulnerability>": 32169,
54
+ "<apt>": 32159,
55
+ "<attack-pattern>": 32141,
56
+ "<campaign>": 32152,
57
+ "<domain>": 32150,
58
+ "<email>": 32155,
59
+ "<filepath>": 32147,
60
+ "<head>": 32102,
61
+ "<identity>": 32143,
62
+ "<infrastucture>": 32153,
63
+ "<ipv4>": 32154,
64
+ "<location>": 32106,
65
+ "<malware>": 32140,
66
+ "<md5>": 32158,
67
+ "<organization>": 32105,
68
+ "<person>": 32107,
69
+ "<registrykey>": 32156,
70
+ "<rel>": 32104,
71
+ "<sha1>": 32157,
72
+ "<sha2>": 32148,
73
+ "<software>": 32144,
74
+ "<subj>": 32103,
75
+ "<text-to-xml>": 32100,
76
+ "<threat-actor>": 32145,
77
+ "<time>": 32142,
78
+ "<tools>": 32146,
79
+ "<triplet>": 32101,
80
+ "<url>": 32151,
81
+ "<vulnerability>": 32149
82
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<malware>",
4
+ "<attack-pattern>",
5
+ "<time>",
6
+ "<identity>",
7
+ "<software>",
8
+ "<threat-actor>",
9
+ "<location>",
10
+ "<tools>",
11
+ "<filepath>",
12
+ "<sha2>",
13
+ "<vulnerability>",
14
+ "<domain>",
15
+ "<url>",
16
+ "<campaign>",
17
+ "<infrastucture>",
18
+ "<ipv4>",
19
+ "<email>",
20
+ "<registrykey>",
21
+ "<sha1>",
22
+ "<md5>",
23
+ "<apt>",
24
+ "</malware>",
25
+ "</attack-pattern>",
26
+ "</time>",
27
+ "</identity>",
28
+ "</software>",
29
+ "</threat-actor>",
30
+ "</location>",
31
+ "</tools>",
32
+ "</filepath>",
33
+ "</sha2>",
34
+ "</vulnerability>",
35
+ "</domain>",
36
+ "</url>",
37
+ "</campaign>",
38
+ "</infrastucture>",
39
+ "</ipv4>",
40
+ "</email>",
41
+ "</registrykey>",
42
+ "</sha1>",
43
+ "</md5>",
44
+ "</apt>"
45
+ ],
46
+ "eos_token": "</s>",
47
+ "pad_token": "<pad>",
48
+ "unk_token": "<unk>"
49
+ }
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 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "eos_token": "</s>",
105
+ "extra_ids": 100,
106
+ "model_max_length": 512,
107
+ "name_or_path": "mrmoor/cti-t5-NER-NYT",
108
+ "pad_token": "<pad>",
109
+ "sp_model_kwargs": {},
110
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--google--t5-v1_1-base/snapshots/650d7745bf1e502d6949b22cc19155cd656d3d4e/special_tokens_map.json",
111
+ "tokenizer_class": "T5Tokenizer",
112
+ "unk_token": "<unk>"
113
+ }