Hugging Face's logo

SHSK0118
/
BERT-basedDomainClassification_ComplaintTexts_ja

Safetensors
Japanese
bert
Model card Files
xet
Community
SHSK0118 commited on
Commit
3523032
·
verified ·
1 Parent(s): 25dbc00

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. config.json +48 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +51 -0
  4. spiece.model +3 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +85 -0
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/drive/MyDrive/Text2Text/BERT/wikipedia_20231101_ja",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 1,
8
+ "classifier_dropout": null,
9
+ "cls_token_id": 4,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2",
18
+ "3": "LABEL_3",
19
+ "4": "LABEL_4",
20
+ "5": "LABEL_5"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 768,
24
+ "label2id": {
25
+ "LABEL_0": 0,
26
+ "LABEL_1": 1,
27
+ "LABEL_2": 2,
28
+ "LABEL_3": 3,
29
+ "LABEL_4": 4,
30
+ "LABEL_5": 5
31
+ },
32
+ "layer_norm_eps": 1e-12,
33
+ "mask_token_id": 6,
34
+ "max_position_embeddings": 524,
35
+ "model_type": "bert",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 12,
38
+ "pad_token_id": 3,
39
+ "position_embedding_type": "absolute",
40
+ "problem_type": "single_label_classification",
41
+ "sep_token_id": 5,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.47.1",
44
+ "type_vocab_size": 2,
45
+ "unk_token_id": 0,
46
+ "use_cache": true,
47
+ "vocab_size": 34003
48
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45be381b4bfbfaa2d0ab0f3a6fb6011f827ce39194499c175f5c8f70ab0301fe
3
+ size 278721520
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[BOS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[EOS]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29f01f7a8e0151dba8588690e471d61a9ca243c91c7fec44338113d8d00d4b71
3
+ size 848185
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[BOS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[EOS]",
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": "[CLS]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "[SEP]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "[MASK]",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [],
61
+ "bos_token": "[BOS]",
62
+ "bos_token_id": 1,
63
+ "clean_up_tokenization_spaces": false,
64
+ "cls_token": "[CLS]",
65
+ "cls_token_id": 4,
66
+ "do_lower_case": true,
67
+ "eos_token": "[EOS]",
68
+ "eos_token_id": 2,
69
+ "extra_special_tokens": {},
70
+ "keep_accents": true,
71
+ "mask_token": "[MASK]",
72
+ "mask_token_id": 6,
73
+ "model_max_length": 1000000000000000019884624838656,
74
+ "pad_token": "[PAD]",
75
+ "pad_token_id": 3,
76
+ "padding": "max_length",
77
+ "remove_space": true,
78
+ "sep_token": "[SEP]",
79
+ "sep_token_id": 5,
80
+ "sp_model_kwargs": {},
81
+ "tokenizer_class": "AlbertTokenizer",
82
+ "truncation": true,
83
+ "unk_token": "[UNK]",
84
+ "unk_token_id": 0
85
+ }