Upload folder using huggingface_hub
Browse files- open-pii-masking-500k-ai4privacy-augmented/bert-crf-bio-bert-base-multilingual-cased/config.json +116 -0
- open-pii-masking-500k-ai4privacy-augmented/bert-crf-bio-bert-base-multilingual-cased/model.safetensors +3 -0
- open-pii-masking-500k-ai4privacy-augmented/bert-crf-bio-bert-base-multilingual-cased/special_tokens_map.json +7 -0
- open-pii-masking-500k-ai4privacy-augmented/bert-crf-bio-bert-base-multilingual-cased/tokenizer.json +0 -0
- open-pii-masking-500k-ai4privacy-augmented/bert-crf-bio-bert-base-multilingual-cased/tokenizer_config.json +57 -0
- open-pii-masking-500k-ai4privacy-augmented/bert-crf-bio-bert-base-multilingual-cased/training_args.bin +3 -0
- open-pii-masking-500k-ai4privacy-augmented/bert-crf-bio-bert-base-multilingual-cased/training_meta.json +52 -0
- open-pii-masking-500k-ai4privacy-augmented/bert-crf-bio-bert-base-multilingual-cased/vocab.txt +0 -0
open-pii-masking-500k-ai4privacy-augmented/bert-crf-bio-bert-base-multilingual-cased/config.json
ADDED
|
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"TransformerCrfForTokenClassification"
|
| 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-AGE",
|
| 15 |
+
"2": "I-AGE",
|
| 16 |
+
"3": "B-BUILDINGNUM",
|
| 17 |
+
"4": "I-BUILDINGNUM",
|
| 18 |
+
"5": "B-CITY",
|
| 19 |
+
"6": "I-CITY",
|
| 20 |
+
"7": "B-CREDITCARDNUMBER",
|
| 21 |
+
"8": "I-CREDITCARDNUMBER",
|
| 22 |
+
"9": "B-DATE",
|
| 23 |
+
"10": "I-DATE",
|
| 24 |
+
"11": "B-DRIVERLICENSENUM",
|
| 25 |
+
"12": "I-DRIVERLICENSENUM",
|
| 26 |
+
"13": "B-EMAIL",
|
| 27 |
+
"14": "I-EMAIL",
|
| 28 |
+
"15": "B-GENDER",
|
| 29 |
+
"16": "I-GENDER",
|
| 30 |
+
"17": "B-GIVENNAME",
|
| 31 |
+
"18": "I-GIVENNAME",
|
| 32 |
+
"19": "B-IDCARDNUM",
|
| 33 |
+
"20": "I-IDCARDNUM",
|
| 34 |
+
"21": "B-PASSPORTNUM",
|
| 35 |
+
"22": "I-PASSPORTNUM",
|
| 36 |
+
"23": "B-SEX",
|
| 37 |
+
"24": "I-SEX",
|
| 38 |
+
"25": "B-SOCIALNUM",
|
| 39 |
+
"26": "I-SOCIALNUM",
|
| 40 |
+
"27": "B-STREET",
|
| 41 |
+
"28": "I-STREET",
|
| 42 |
+
"29": "B-SURNAME",
|
| 43 |
+
"30": "I-SURNAME",
|
| 44 |
+
"31": "B-TAXNUM",
|
| 45 |
+
"32": "I-TAXNUM",
|
| 46 |
+
"33": "B-TELEPHONENUM",
|
| 47 |
+
"34": "I-TELEPHONENUM",
|
| 48 |
+
"35": "B-TIME",
|
| 49 |
+
"36": "I-TIME",
|
| 50 |
+
"37": "B-TITLE",
|
| 51 |
+
"38": "I-TITLE",
|
| 52 |
+
"39": "B-ZIPCODE",
|
| 53 |
+
"40": "I-ZIPCODE"
|
| 54 |
+
},
|
| 55 |
+
"initializer_range": 0.02,
|
| 56 |
+
"intermediate_size": 3072,
|
| 57 |
+
"label2id": {
|
| 58 |
+
"B-AGE": 1,
|
| 59 |
+
"B-BUILDINGNUM": 3,
|
| 60 |
+
"B-CITY": 5,
|
| 61 |
+
"B-CREDITCARDNUMBER": 7,
|
| 62 |
+
"B-DATE": 9,
|
| 63 |
+
"B-DRIVERLICENSENUM": 11,
|
| 64 |
+
"B-EMAIL": 13,
|
| 65 |
+
"B-GENDER": 15,
|
| 66 |
+
"B-GIVENNAME": 17,
|
| 67 |
+
"B-IDCARDNUM": 19,
|
| 68 |
+
"B-PASSPORTNUM": 21,
|
| 69 |
+
"B-SEX": 23,
|
| 70 |
+
"B-SOCIALNUM": 25,
|
| 71 |
+
"B-STREET": 27,
|
| 72 |
+
"B-SURNAME": 29,
|
| 73 |
+
"B-TAXNUM": 31,
|
| 74 |
+
"B-TELEPHONENUM": 33,
|
| 75 |
+
"B-TIME": 35,
|
| 76 |
+
"B-TITLE": 37,
|
| 77 |
+
"B-ZIPCODE": 39,
|
| 78 |
+
"I-AGE": 2,
|
| 79 |
+
"I-BUILDINGNUM": 4,
|
| 80 |
+
"I-CITY": 6,
|
| 81 |
+
"I-CREDITCARDNUMBER": 8,
|
| 82 |
+
"I-DATE": 10,
|
| 83 |
+
"I-DRIVERLICENSENUM": 12,
|
| 84 |
+
"I-EMAIL": 14,
|
| 85 |
+
"I-GENDER": 16,
|
| 86 |
+
"I-GIVENNAME": 18,
|
| 87 |
+
"I-IDCARDNUM": 20,
|
| 88 |
+
"I-PASSPORTNUM": 22,
|
| 89 |
+
"I-SEX": 24,
|
| 90 |
+
"I-SOCIALNUM": 26,
|
| 91 |
+
"I-STREET": 28,
|
| 92 |
+
"I-SURNAME": 30,
|
| 93 |
+
"I-TAXNUM": 32,
|
| 94 |
+
"I-TELEPHONENUM": 34,
|
| 95 |
+
"I-TIME": 36,
|
| 96 |
+
"I-TITLE": 38,
|
| 97 |
+
"I-ZIPCODE": 40,
|
| 98 |
+
"O": 0
|
| 99 |
+
},
|
| 100 |
+
"layer_norm_eps": 1e-12,
|
| 101 |
+
"max_position_embeddings": 512,
|
| 102 |
+
"model_type": "bert",
|
| 103 |
+
"num_attention_heads": 12,
|
| 104 |
+
"num_hidden_layers": 12,
|
| 105 |
+
"pad_token_id": 0,
|
| 106 |
+
"pooler_fc_size": 768,
|
| 107 |
+
"pooler_num_attention_heads": 12,
|
| 108 |
+
"pooler_num_fc_layers": 3,
|
| 109 |
+
"pooler_size_per_head": 128,
|
| 110 |
+
"pooler_type": "first_token_transform",
|
| 111 |
+
"position_embedding_type": "absolute",
|
| 112 |
+
"transformers_version": "4.57.6",
|
| 113 |
+
"type_vocab_size": 2,
|
| 114 |
+
"use_cache": true,
|
| 115 |
+
"vocab_size": 119547
|
| 116 |
+
}
|
open-pii-masking-500k-ai4privacy-augmented/bert-crf-bio-bert-base-multilingual-cased/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3449a44ea4b877b2a49ac3ddc284cc97368e45bbd75281a4bb0496975d7a3d86
|
| 3 |
+
size 711572104
|
open-pii-masking-500k-ai4privacy-augmented/bert-crf-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 |
+
}
|
open-pii-masking-500k-ai4privacy-augmented/bert-crf-bio-bert-base-multilingual-cased/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
open-pii-masking-500k-ai4privacy-augmented/bert-crf-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 |
+
}
|
open-pii-masking-500k-ai4privacy-augmented/bert-crf-bio-bert-base-multilingual-cased/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:673ad6cb9aa84d1bf1c78aabb5add05cb7cc7ce63279c699fb06c9bdac12a682
|
| 3 |
+
size 5969
|
open-pii-masking-500k-ai4privacy-augmented/bert-crf-bio-bert-base-multilingual-cased/training_meta.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architecture": "token_based",
|
| 3 |
+
"base_model": "google-bert/bert-base-multilingual-cased",
|
| 4 |
+
"tagging_scheme": "bio",
|
| 5 |
+
"use_crf": true,
|
| 6 |
+
"dataset": "open-pii-masking-500k-ai4privacy-augmented",
|
| 7 |
+
"label_list": [
|
| 8 |
+
"O",
|
| 9 |
+
"B-AGE",
|
| 10 |
+
"I-AGE",
|
| 11 |
+
"B-BUILDINGNUM",
|
| 12 |
+
"I-BUILDINGNUM",
|
| 13 |
+
"B-CITY",
|
| 14 |
+
"I-CITY",
|
| 15 |
+
"B-CREDITCARDNUMBER",
|
| 16 |
+
"I-CREDITCARDNUMBER",
|
| 17 |
+
"B-DATE",
|
| 18 |
+
"I-DATE",
|
| 19 |
+
"B-DRIVERLICENSENUM",
|
| 20 |
+
"I-DRIVERLICENSENUM",
|
| 21 |
+
"B-EMAIL",
|
| 22 |
+
"I-EMAIL",
|
| 23 |
+
"B-GENDER",
|
| 24 |
+
"I-GENDER",
|
| 25 |
+
"B-GIVENNAME",
|
| 26 |
+
"I-GIVENNAME",
|
| 27 |
+
"B-IDCARDNUM",
|
| 28 |
+
"I-IDCARDNUM",
|
| 29 |
+
"B-PASSPORTNUM",
|
| 30 |
+
"I-PASSPORTNUM",
|
| 31 |
+
"B-SEX",
|
| 32 |
+
"I-SEX",
|
| 33 |
+
"B-SOCIALNUM",
|
| 34 |
+
"I-SOCIALNUM",
|
| 35 |
+
"B-STREET",
|
| 36 |
+
"I-STREET",
|
| 37 |
+
"B-SURNAME",
|
| 38 |
+
"I-SURNAME",
|
| 39 |
+
"B-TAXNUM",
|
| 40 |
+
"I-TAXNUM",
|
| 41 |
+
"B-TELEPHONENUM",
|
| 42 |
+
"I-TELEPHONENUM",
|
| 43 |
+
"B-TIME",
|
| 44 |
+
"I-TIME",
|
| 45 |
+
"B-TITLE",
|
| 46 |
+
"I-TITLE",
|
| 47 |
+
"B-ZIPCODE",
|
| 48 |
+
"I-ZIPCODE"
|
| 49 |
+
],
|
| 50 |
+
"max_seq_length": 512,
|
| 51 |
+
"timestamp": "2026-04-07T15:11:55.028841"
|
| 52 |
+
}
|
open-pii-masking-500k-ai4privacy-augmented/bert-crf-bio-bert-base-multilingual-cased/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|