Hugging Face's logo

devnote5676
/
schwartz-values-classifier

Text Classification
Transformers
Safetensors
English
bert
social-values
Model card Files
xet
Community
devnote5676 commited on
Commit
6606f30
·
1 Parent(s): bb5459d

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +12 -0
  2. special_tokens_map.json +49 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +147 -0
  5. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<achievement>": 30531,
3
+ "<benevolence>": 30527,
4
+ "<conformity>": 30522,
5
+ "<hedonism>": 30523,
6
+ "<power>": 30530,
7
+ "<security>": 30526,
8
+ "<self-direction>": 30525,
9
+ "<stimulation>": 30528,
10
+ "<tradition>": 30529,
11
+ "<universalism>": 30524
12
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<conformity>",
4
+ "<hedonism>",
5
+ "<universalism>",
6
+ "<self-direction>",
7
+ "<security>",
8
+ "<benevolence>",
9
+ "<stimulation>",
10
+ "<tradition>",
11
+ "<power>",
12
+ "<achievement>"
13
+ ],
14
+ "cls_token": {
15
+ "content": "[CLS]",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "mask_token": {
22
+ "content": "[MASK]",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "pad_token": {
29
+ "content": "[PAD]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "sep_token": {
36
+ "content": "[SEP]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false
41
+ },
42
+ "unk_token": {
43
+ "content": "[UNK]",
44
+ "lstrip": false,
45
+ "normalized": false,
46
+ "rstrip": false,
47
+ "single_word": false
48
+ }
49
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30522": {
44
+ "content": "<conformity>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "30523": {
52
+ "content": "<hedonism>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "30524": {
60
+ "content": "<universalism>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "30525": {
68
+ "content": "<self-direction>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "30526": {
76
+ "content": "<security>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "30527": {
84
+ "content": "<benevolence>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "30528": {
92
+ "content": "<stimulation>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "30529": {
100
+ "content": "<tradition>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "30530": {
108
+ "content": "<power>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "30531": {
116
+ "content": "<achievement>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ }
123
+ },
124
+ "additional_special_tokens": [
125
+ "<conformity>",
126
+ "<hedonism>",
127
+ "<universalism>",
128
+ "<self-direction>",
129
+ "<security>",
130
+ "<benevolence>",
131
+ "<stimulation>",
132
+ "<tradition>",
133
+ "<power>",
134
+ "<achievement>"
135
+ ],
136
+ "clean_up_tokenization_spaces": true,
137
+ "cls_token": "[CLS]",
138
+ "do_lower_case": true,
139
+ "mask_token": "[MASK]",
140
+ "model_max_length": 512,
141
+ "pad_token": "[PAD]",
142
+ "sep_token": "[SEP]",
143
+ "strip_accents": null,
144
+ "tokenize_chinese_chars": true,
145
+ "tokenizer_class": "BertTokenizer",
146
+ "unk_token": "[UNK]"
147
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff