PuxAI commited on
Commit
a9937fd
·
verified ·
1 Parent(s): d1acd36

Upload folder using huggingface_hub

Browse files
financial-pii-ready/bert-bio-bert-base-multilingual-cased/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "directionality": "bidi",
8
+ "dtype": "float32",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-ADDRESS",
15
+ "2": "I-ADDRESS",
16
+ "3": "B-COMPANY",
17
+ "4": "I-COMPANY",
18
+ "5": "B-CREDIT_CARD",
19
+ "6": "I-CREDIT_CARD",
20
+ "7": "B-EMAIL",
21
+ "8": "I-EMAIL",
22
+ "9": "B-NAME",
23
+ "10": "I-NAME",
24
+ "11": "B-PHONE",
25
+ "12": "I-PHONE",
26
+ "13": "B-SSN",
27
+ "14": "I-SSN",
28
+ "15": "B-URL",
29
+ "16": "I-URL"
30
+ },
31
+ "initializer_range": 0.02,
32
+ "intermediate_size": 3072,
33
+ "label2id": {
34
+ "B-ADDRESS": 1,
35
+ "B-COMPANY": 3,
36
+ "B-CREDIT_CARD": 5,
37
+ "B-EMAIL": 7,
38
+ "B-NAME": 9,
39
+ "B-PHONE": 11,
40
+ "B-SSN": 13,
41
+ "B-URL": 15,
42
+ "I-ADDRESS": 2,
43
+ "I-COMPANY": 4,
44
+ "I-CREDIT_CARD": 6,
45
+ "I-EMAIL": 8,
46
+ "I-NAME": 10,
47
+ "I-PHONE": 12,
48
+ "I-SSN": 14,
49
+ "I-URL": 16,
50
+ "O": 0
51
+ },
52
+ "layer_norm_eps": 1e-12,
53
+ "max_position_embeddings": 512,
54
+ "model_type": "bert",
55
+ "num_attention_heads": 12,
56
+ "num_hidden_layers": 12,
57
+ "pad_token_id": 0,
58
+ "pooler_fc_size": 768,
59
+ "pooler_num_attention_heads": 12,
60
+ "pooler_num_fc_layers": 3,
61
+ "pooler_size_per_head": 128,
62
+ "pooler_type": "first_token_transform",
63
+ "position_embedding_type": "absolute",
64
+ "transformers_version": "4.57.6",
65
+ "type_vocab_size": 2,
66
+ "use_cache": true,
67
+ "vocab_size": 119547
68
+ }
financial-pii-ready/bert-bio-bert-base-multilingual-cased/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71cf1215e3bdc8d229f88146aa6d68033cc186e4e4f1d667d18be18ed98c10d5
3
+ size 709127044
financial-pii-ready/bert-bio-bert-base-multilingual-cased/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
+ }
financial-pii-ready/bert-bio-bert-base-multilingual-cased/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
financial-pii-ready/bert-bio-bert-base-multilingual-cased/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
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
+ }
financial-pii-ready/bert-bio-bert-base-multilingual-cased/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a449cf6f4e66c9eb27564cd5ff37f49ca404608dd0969bcc3a6278ce97ff8e38
3
+ size 5905
financial-pii-ready/bert-bio-bert-base-multilingual-cased/training_meta.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "token_based",
3
+ "base_model": "google-bert/bert-base-multilingual-cased",
4
+ "tagging_scheme": "bio",
5
+ "use_crf": false,
6
+ "dataset": "financial-pii-ready",
7
+ "label_list": [
8
+ "O",
9
+ "B-ADDRESS",
10
+ "I-ADDRESS",
11
+ "B-COMPANY",
12
+ "I-COMPANY",
13
+ "B-CREDIT_CARD",
14
+ "I-CREDIT_CARD",
15
+ "B-EMAIL",
16
+ "I-EMAIL",
17
+ "B-NAME",
18
+ "I-NAME",
19
+ "B-PHONE",
20
+ "I-PHONE",
21
+ "B-SSN",
22
+ "I-SSN",
23
+ "B-URL",
24
+ "I-URL"
25
+ ],
26
+ "max_seq_length": 512,
27
+ "timestamp": "2026-04-05T05:12:49.477989"
28
+ }
financial-pii-ready/bert-bio-bert-base-multilingual-cased/vocab.txt ADDED
The diff for this file is too large to render. See raw diff