BKforKorea commited on
Commit
4dad352
1 Parent(s): 9c104c2

commit-success

Browse files
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "[CLS]": 2,
3
+ "[MASK]": 4,
4
+ "[PAD]": 0,
5
+ "[SEP]": 3,
6
+ "[UNK]": 1
7
+ }
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "beomi/KcELECTRA-base-v2022",
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": "\ubd84\ub178",
14
+ "1": "\uc2ac\ud514",
15
+ "2": "\ubd88\uc548",
16
+ "3": "\uc0c1\ucc98",
17
+ "4": "\uae30\uc068"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "\uae30\uc068": 4,
23
+ "\ubd84\ub178": 0,
24
+ "\ubd88\uc548": 2,
25
+ "\uc0c1\ucc98": 3,
26
+ "\uc2ac\ud514": 1
27
+ },
28
+ "layer_norm_eps": 1e-12,
29
+ "max_position_embeddings": 512,
30
+ "model_type": "electra",
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
+ "pad_token_id": 0,
34
+ "position_embedding_type": "absolute",
35
+ "problem_type": "single_label_classification",
36
+ "summary_activation": "gelu",
37
+ "summary_last_dropout": 0.1,
38
+ "summary_type": "first",
39
+ "summary_use_proj": true,
40
+ "tokenizer_class": "BertTokenizer",
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.34.0",
43
+ "type_vocab_size": 2,
44
+ "use_cache": true,
45
+ "vocab_size": 54343
46
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0994d29384990640f4bfb4ed7e5d39e9a404c9f13c700c120fa9fc3ea509b3e3
3
+ size 511191854
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
44
+ "additional_special_tokens": [],
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": false,
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff