Hugging Face's logo

hongssi
/
final_abuse_manual_model

Safetensors
Korean
electra
abuse-detection
korean
classification
unsmile
Model card Files
xet
Community
hongssi commited on
Commit
1b50025
·
1 Parent(s): 1c159ac

Initial commit with LFS model

Browse files
Files changed (4) hide show
  1. config.json +58 -0
  2. special_tokens_map.json +37 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +57 -0
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "beomi/KcELECTRA-base",
3
+ "architectures": [
4
+ "ElectraForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 768,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8",
22
+ "9": "LABEL_9",
23
+ "10": "LABEL_10"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 3072,
27
+ "label2id": {
28
+ "LABEL_0": 0,
29
+ "LABEL_1": 1,
30
+ "LABEL_10": 10,
31
+ "LABEL_2": 2,
32
+ "LABEL_3": 3,
33
+ "LABEL_4": 4,
34
+ "LABEL_5": 5,
35
+ "LABEL_6": 6,
36
+ "LABEL_7": 7,
37
+ "LABEL_8": 8,
38
+ "LABEL_9": 9
39
+ },
40
+ "layer_norm_eps": 1e-12,
41
+ "max_position_embeddings": 512,
42
+ "model_type": "electra",
43
+ "num_attention_heads": 12,
44
+ "num_hidden_layers": 12,
45
+ "pad_token_id": 3,
46
+ "position_embedding_type": "absolute",
47
+ "problem_type": "multi_label_classification",
48
+ "summary_activation": "gelu",
49
+ "summary_last_dropout": 0.1,
50
+ "summary_type": "first",
51
+ "summary_use_proj": true,
52
+ "tokenizer_class": "PreTrainedTokenizerFast",
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.38.2",
55
+ "type_vocab_size": 2,
56
+ "use_cache": true,
57
+ "vocab_size": 30000
58
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[PAD]",
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
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "PreTrainedTokenizerFast",
56
+ "unk_token": "[UNK]"
57
+ }