Hugging Face's logo

broadfield-dev
/
bert-small-ner-pii-mobile

Token Classification
Transformers
ONNX
English
bert
optimum
onnxruntime
int8
quantized
mobile
Model card Files
xet
Community
broadfield-dev commited on
Commit
058a18e
·
verified ·
1 Parent(s): 0814cdc

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +64 -0
  2. model.onnx +3 -0
  3. ort_config.json +35 -0
  4. special_tokens_map.json +37 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +63 -0
  7. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 512,
11
+ "id2label": {
12
+ "0": "ACCOUNTNUM",
13
+ "1": "BUILDINGNUM",
14
+ "2": "CITY",
15
+ "3": "CREDITCARDNUMBER",
16
+ "4": "DATEOFBIRTH",
17
+ "5": "DRIVERLICENSENUM",
18
+ "6": "EMAIL",
19
+ "7": "GIVENNAME",
20
+ "8": "IDCARDNUM",
21
+ "9": "O",
22
+ "10": "PASSWORD",
23
+ "11": "SOCIALNUM",
24
+ "12": "STREET",
25
+ "13": "SURNAME",
26
+ "14": "TAXNUM",
27
+ "15": "TELEPHONENUM",
28
+ "16": "USERNAME",
29
+ "17": "ZIPCODE"
30
+ },
31
+ "initializer_range": 0.02,
32
+ "intermediate_size": 2048,
33
+ "label2id": {
34
+ "ACCOUNTNUM": 0,
35
+ "BUILDINGNUM": 1,
36
+ "CITY": 2,
37
+ "CREDITCARDNUMBER": 3,
38
+ "DATEOFBIRTH": 4,
39
+ "DRIVERLICENSENUM": 5,
40
+ "EMAIL": 6,
41
+ "GIVENNAME": 7,
42
+ "IDCARDNUM": 8,
43
+ "O": 9,
44
+ "PASSWORD": 10,
45
+ "SOCIALNUM": 11,
46
+ "STREET": 12,
47
+ "SURNAME": 13,
48
+ "TAXNUM": 14,
49
+ "TELEPHONENUM": 15,
50
+ "USERNAME": 16,
51
+ "ZIPCODE": 17
52
+ },
53
+ "layer_norm_eps": 1e-12,
54
+ "max_position_embeddings": 512,
55
+ "model_type": "bert",
56
+ "num_attention_heads": 8,
57
+ "num_hidden_layers": 4,
58
+ "pad_token_id": 0,
59
+ "position_embedding_type": "absolute",
60
+ "transformers_version": "4.57.3",
61
+ "type_vocab_size": 2,
62
+ "use_cache": true,
63
+ "vocab_size": 30522
64
+ }
model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81e71bfa1abc7691453b38502915dc21b89daa61bb9e164dc1ce0852957b7a68
3
+ size 114058512
ort_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "one_external_file": true,
3
+ "opset": null,
4
+ "optimization": {
5
+ "disable_attention_fusion": false,
6
+ "disable_bias_add_fusion": false,
7
+ "disable_bias_gelu_fusion": false,
8
+ "disable_bias_skip_layer_norm_fusion": false,
9
+ "disable_bias_splitgelu_fusion": false,
10
+ "disable_embed_layer_norm_fusion": true,
11
+ "disable_gelu_fusion": false,
12
+ "disable_group_norm_fusion": true,
13
+ "disable_layer_norm_fusion": false,
14
+ "disable_nhwc_conv": false,
15
+ "disable_packed_kv": true,
16
+ "disable_packed_qkv": false,
17
+ "disable_rotary_embeddings": false,
18
+ "disable_shape_inference": true,
19
+ "disable_skip_group_norm_fusion": false,
20
+ "disable_skip_layer_norm_fusion": false,
21
+ "enable_gelu_approximation": false,
22
+ "enable_gemm_fast_gelu_fusion": false,
23
+ "enable_transformers_specific_optimizations": true,
24
+ "fp16": false,
25
+ "no_attention_mask": false,
26
+ "optimization_level": 2,
27
+ "optimize_for_gpu": false,
28
+ "use_group_norm_channels_first": false,
29
+ "use_mask_index": false,
30
+ "use_multi_head_attention": false,
31
+ "use_raw_attention_mask": false
32
+ },
33
+ "quantization": {},
34
+ "use_external_data_format": false
35
+ }
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 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "100": {
13
+ "content": "[UNK]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "101": {
21
+ "content": "[CLS]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "102": {
29
+ "content": "[SEP]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "103": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": true,
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "max_length": 512,
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "never_split": null,
54
+ "pad_token": "[PAD]",
55
+ "sep_token": "[SEP]",
56
+ "stride": 0,
57
+ "strip_accents": null,
58
+ "tokenize_chinese_chars": true,
59
+ "tokenizer_class": "BertTokenizer",
60
+ "truncation_side": "right",
61
+ "truncation_strategy": "longest_first",
62
+ "unk_token": "[UNK]"
63
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff