Token Classification
ONNX
Safetensors
English
bert
MikeG27 commited on
Commit
98dbadf
·
verified ·
1 Parent(s): 7b93af0

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "prajjwal1/bert-small",
3
+ "architectures": [
4
+ "BertForTokenClassification"
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": 512,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-AGE",
14
+ "2": "I-AGE",
15
+ "3": "B-COORDINATE",
16
+ "4": "I-COORDINATE",
17
+ "5": "B-CREDIT_CARD",
18
+ "6": "I-CREDIT_CARD",
19
+ "7": "B-DATE_TIME",
20
+ "8": "I-DATE_TIME",
21
+ "9": "B-EMAIL_ADDRESS",
22
+ "10": "I-EMAIL_ADDRESS",
23
+ "11": "B-FINANCIAL",
24
+ "12": "I-FINANCIAL",
25
+ "13": "B-IBAN_CODE",
26
+ "14": "I-IBAN_CODE",
27
+ "15": "B-IMEI",
28
+ "16": "I-IMEI",
29
+ "17": "B-IP_ADDRESS",
30
+ "18": "I-IP_ADDRESS",
31
+ "19": "B-LOCATION",
32
+ "20": "I-LOCATION",
33
+ "21": "B-MAC_ADDRESS",
34
+ "22": "I-MAC_ADDRESS",
35
+ "23": "B-NRP",
36
+ "24": "I-NRP",
37
+ "25": "B-ORGANIZATION",
38
+ "26": "I-ORGANIZATION",
39
+ "27": "B-PASSWORD",
40
+ "28": "I-PASSWORD",
41
+ "29": "B-PERSON",
42
+ "30": "I-PERSON",
43
+ "31": "B-PHONE_NUMBER",
44
+ "32": "I-PHONE_NUMBER",
45
+ "33": "B-TITLE",
46
+ "34": "I-TITLE",
47
+ "35": "B-URL",
48
+ "36": "I-URL",
49
+ "37": "B-US_BANK_NUMBER",
50
+ "38": "I-US_BANK_NUMBER",
51
+ "39": "B-US_DRIVER_LICENSE",
52
+ "40": "I-US_DRIVER_LICENSE",
53
+ "41": "B-US_ITIN",
54
+ "42": "I-US_ITIN",
55
+ "43": "B-US_LICENSE_PLATE",
56
+ "44": "I-US_LICENSE_PLATE",
57
+ "45": "B-US_PASSPORT",
58
+ "46": "I-US_PASSPORT",
59
+ "47": "B-US_SSN",
60
+ "48": "I-US_SSN"
61
+ },
62
+ "initializer_range": 0.02,
63
+ "intermediate_size": 2048,
64
+ "label2id": {
65
+ "B-AGE": 1,
66
+ "B-COORDINATE": 3,
67
+ "B-CREDIT_CARD": 5,
68
+ "B-DATE_TIME": 7,
69
+ "B-EMAIL_ADDRESS": 9,
70
+ "B-FINANCIAL": 11,
71
+ "B-IBAN_CODE": 13,
72
+ "B-IMEI": 15,
73
+ "B-IP_ADDRESS": 17,
74
+ "B-LOCATION": 19,
75
+ "B-MAC_ADDRESS": 21,
76
+ "B-NRP": 23,
77
+ "B-ORGANIZATION": 25,
78
+ "B-PASSWORD": 27,
79
+ "B-PERSON": 29,
80
+ "B-PHONE_NUMBER": 31,
81
+ "B-TITLE": 33,
82
+ "B-URL": 35,
83
+ "B-US_BANK_NUMBER": 37,
84
+ "B-US_DRIVER_LICENSE": 39,
85
+ "B-US_ITIN": 41,
86
+ "B-US_LICENSE_PLATE": 43,
87
+ "B-US_PASSPORT": 45,
88
+ "B-US_SSN": 47,
89
+ "I-AGE": 2,
90
+ "I-COORDINATE": 4,
91
+ "I-CREDIT_CARD": 6,
92
+ "I-DATE_TIME": 8,
93
+ "I-EMAIL_ADDRESS": 10,
94
+ "I-FINANCIAL": 12,
95
+ "I-IBAN_CODE": 14,
96
+ "I-IMEI": 16,
97
+ "I-IP_ADDRESS": 18,
98
+ "I-LOCATION": 20,
99
+ "I-MAC_ADDRESS": 22,
100
+ "I-NRP": 24,
101
+ "I-ORGANIZATION": 26,
102
+ "I-PASSWORD": 28,
103
+ "I-PERSON": 30,
104
+ "I-PHONE_NUMBER": 32,
105
+ "I-TITLE": 34,
106
+ "I-URL": 36,
107
+ "I-US_BANK_NUMBER": 38,
108
+ "I-US_DRIVER_LICENSE": 40,
109
+ "I-US_ITIN": 42,
110
+ "I-US_LICENSE_PLATE": 44,
111
+ "I-US_PASSPORT": 46,
112
+ "I-US_SSN": 48,
113
+ "O": 0
114
+ },
115
+ "layer_norm_eps": 1e-12,
116
+ "max_position_embeddings": 512,
117
+ "model_type": "bert",
118
+ "num_attention_heads": 8,
119
+ "num_hidden_layers": 4,
120
+ "pad_token_id": 0,
121
+ "position_embedding_type": "absolute",
122
+ "torch_dtype": "float32",
123
+ "transformers_version": "4.41.0",
124
+ "type_vocab_size": 2,
125
+ "use_cache": true,
126
+ "vocab_size": 30522
127
+ }
model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5806bda3f4ba0b79bd39257382c4ceb508a4b683f12dc3d5b36623eaa9f3e124
3
+ size 114202366
model.quant.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a239c348b8249388bf55801d057b8d1294bf357757774c7c30febed0f2a2a5ac
3
+ size 28837321
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09be1b3b49663c94e7b038b2dae6f195ef3425db5edd3cf883db96ce6ec42bf4
3
+ size 114112684
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff