Hugging Face's logo

atti433
/
minde-classifier

Text Classification
Transformers
Safetensors
Korean
bert
klue
korean
minwon
complaint
public-administration
text-embeddings-inference
Model card Files
xet
 Community
atti433 commited on
Commit
6ca8609
·
verified ·
1 Parent(s): 4669848

Upload minde-classifier weights

Browse files
Files changed (8) hide show
  1. added_tokens.json +11 -0
  2. config.json +52 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +102 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +140 -0
  7. training_args.bin +3 -0
  8. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[ACCT]": 32005,
3
+ "[ADDR]": 32000,
4
+ "[BIZ]": 32006,
5
+ "[LOC]": 32007,
6
+ "[NAME]": 32001,
7
+ "[NUM]": 32003,
8
+ "[ORG]": 32002,
9
+ "[PERSON]": 32008,
10
+ "[TEL]": 32004
11
+ }
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "klue/bert-base",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "\uad50\ud1b5",
13
+ "1": "\uac74\ucd95",
14
+ "2": "\ud589\uc815",
15
+ "3": "\ubcf4\uac74\uc704\uc0dd",
16
+ "4": "\ud658\uacbd",
17
+ "5": "\ubb38\ud654_\uc5ec\uac00",
18
+ "6": "\ub18d\ucd95\uc0b0",
19
+ "7": "\ubcf5\uc9c0",
20
+ "8": "\uc138\ubb34",
21
+ "9": "\uc0c1\ud558\uc218\ub3c4",
22
+ "10": "\uacbd\uc81c"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "label2id": {
27
+ "\uac74\ucd95": 1,
28
+ "\uacbd\uc81c": 10,
29
+ "\uad50\ud1b5": 0,
30
+ "\ub18d\ucd95\uc0b0": 6,
31
+ "\ubb38\ud654_\uc5ec\uac00": 5,
32
+ "\ubcf4\uac74\uc704\uc0dd": 3,
33
+ "\ubcf5\uc9c0": 7,
34
+ "\uc0c1\ud558\uc218\ub3c4": 9,
35
+ "\uc138\ubb34": 8,
36
+ "\ud589\uc815": 2,
37
+ "\ud658\uacbd": 4
38
+ },
39
+ "layer_norm_eps": 1e-12,
40
+ "max_position_embeddings": 512,
41
+ "model_type": "bert",
42
+ "num_attention_heads": 12,
43
+ "num_hidden_layers": 12,
44
+ "pad_token_id": 0,
45
+ "position_embedding_type": "absolute",
46
+ "problem_type": "single_label_classification",
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.46.3",
49
+ "type_vocab_size": 2,
50
+ "use_cache": true,
51
+ "vocab_size": 32009
52
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88dca210d502d38674496a5f0dd2d0e1fc2f0781902aed23cc59689e2c161179
3
+ size 442554396
special_tokens_map.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "[ADDR]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "[NAME]",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "[ORG]",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "[NUM]",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "[TEL]",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "[ACCT]",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "[BIZ]",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "[LOC]",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "[PERSON]",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ }
66
+ ],
67
+ "cls_token": {
68
+ "content": "[CLS]",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false
73
+ },
74
+ "mask_token": {
75
+ "content": "[MASK]",
76
+ "lstrip": false,
77
+ "normalized": false,
78
+ "rstrip": false,
79
+ "single_word": false
80
+ },
81
+ "pad_token": {
82
+ "content": "[PAD]",
83
+ "lstrip": false,
84
+ "normalized": false,
85
+ "rstrip": false,
86
+ "single_word": false
87
+ },
88
+ "sep_token": {
89
+ "content": "[SEP]",
90
+ "lstrip": false,
91
+ "normalized": false,
92
+ "rstrip": false,
93
+ "single_word": false
94
+ },
95
+ "unk_token": {
96
+ "content": "[UNK]",
97
+ "lstrip": false,
98
+ "normalized": false,
99
+ "rstrip": false,
100
+ "single_word": false
101
+ }
102
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32000": {
44
+ "content": "[ADDR]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32001": {
52
+ "content": "[NAME]",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32002": {
60
+ "content": "[ORG]",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "32003": {
68
+ "content": "[NUM]",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "32004": {
76
+ "content": "[TEL]",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "32005": {
84
+ "content": "[ACCT]",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "32006": {
92
+ "content": "[BIZ]",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "32007": {
100
+ "content": "[LOC]",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "32008": {
108
+ "content": "[PERSON]",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ }
115
+ },
116
+ "additional_special_tokens": [
117
+ "[ADDR]",
118
+ "[NAME]",
119
+ "[ORG]",
120
+ "[NUM]",
121
+ "[TEL]",
122
+ "[ACCT]",
123
+ "[BIZ]",
124
+ "[LOC]",
125
+ "[PERSON]"
126
+ ],
127
+ "clean_up_tokenization_spaces": false,
128
+ "cls_token": "[CLS]",
129
+ "do_basic_tokenize": true,
130
+ "do_lower_case": false,
131
+ "mask_token": "[MASK]",
132
+ "model_max_length": 512,
133
+ "never_split": null,
134
+ "pad_token": "[PAD]",
135
+ "sep_token": "[SEP]",
136
+ "strip_accents": null,
137
+ "tokenize_chinese_chars": true,
138
+ "tokenizer_class": "BertTokenizer",
139
+ "unk_token": "[UNK]"
140
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14da904259b836f2f026ca7dd689b1718871b3c687c70059119543f9aa095940
3
+ size 5280
vocab.txt ADDED
The diff for this file is too large to render. See raw diff