Delete open-pii-masking-500k-ai4privacy-augmented
Browse files- open-pii-masking-500k-ai4privacy-augmented/TokenBased-BERT/config.json +0 -112
- open-pii-masking-500k-ai4privacy-augmented/TokenBased-BERT/model.safetensors +0 -3
- open-pii-masking-500k-ai4privacy-augmented/TokenBased-BERT/special_tokens_map.json +0 -37
- open-pii-masking-500k-ai4privacy-augmented/TokenBased-BERT/tokenizer.json +0 -0
- open-pii-masking-500k-ai4privacy-augmented/TokenBased-BERT/tokenizer_config.json +0 -66
- open-pii-masking-500k-ai4privacy-augmented/TokenBased-BERT/training_args.bin +0 -3
- open-pii-masking-500k-ai4privacy-augmented/TokenBased-BERT/vocab.txt +0 -0
open-pii-masking-500k-ai4privacy-augmented/TokenBased-BERT/config.json
DELETED
|
@@ -1,112 +0,0 @@
|
|
| 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": "B-AGE",
|
| 14 |
-
"1": "B-BUILDINGNUM",
|
| 15 |
-
"2": "B-CITY",
|
| 16 |
-
"3": "B-CREDITCARDNUMBER",
|
| 17 |
-
"4": "B-DATE",
|
| 18 |
-
"5": "B-DRIVERLICENSENUM",
|
| 19 |
-
"6": "B-EMAIL",
|
| 20 |
-
"7": "B-GENDER",
|
| 21 |
-
"8": "B-GIVENNAME",
|
| 22 |
-
"9": "B-IDCARDNUM",
|
| 23 |
-
"10": "B-PASSPORTNUM",
|
| 24 |
-
"11": "B-SOCIALNUM",
|
| 25 |
-
"12": "B-STREET",
|
| 26 |
-
"13": "B-SURNAME",
|
| 27 |
-
"14": "B-TAXNUM",
|
| 28 |
-
"15": "B-TELEPHONENUM",
|
| 29 |
-
"16": "B-TIME",
|
| 30 |
-
"17": "B-TITLE",
|
| 31 |
-
"18": "B-ZIPCODE",
|
| 32 |
-
"19": "I-AGE",
|
| 33 |
-
"20": "I-BUILDINGNUM",
|
| 34 |
-
"21": "I-CITY",
|
| 35 |
-
"22": "I-CREDITCARDNUMBER",
|
| 36 |
-
"23": "I-DATE",
|
| 37 |
-
"24": "I-DRIVERLICENSENUM",
|
| 38 |
-
"25": "I-EMAIL",
|
| 39 |
-
"26": "I-GENDER",
|
| 40 |
-
"27": "I-GIVENNAME",
|
| 41 |
-
"28": "I-IDCARDNUM",
|
| 42 |
-
"29": "I-PASSPORTNUM",
|
| 43 |
-
"30": "I-SOCIALNUM",
|
| 44 |
-
"31": "I-STREET",
|
| 45 |
-
"32": "I-SURNAME",
|
| 46 |
-
"33": "I-TAXNUM",
|
| 47 |
-
"34": "I-TELEPHONENUM",
|
| 48 |
-
"35": "I-TIME",
|
| 49 |
-
"36": "I-TITLE",
|
| 50 |
-
"37": "I-ZIPCODE",
|
| 51 |
-
"38": "O"
|
| 52 |
-
},
|
| 53 |
-
"initializer_range": 0.02,
|
| 54 |
-
"intermediate_size": 3072,
|
| 55 |
-
"label2id": {
|
| 56 |
-
"B-AGE": 0,
|
| 57 |
-
"B-BUILDINGNUM": 1,
|
| 58 |
-
"B-CITY": 2,
|
| 59 |
-
"B-CREDITCARDNUMBER": 3,
|
| 60 |
-
"B-DATE": 4,
|
| 61 |
-
"B-DRIVERLICENSENUM": 5,
|
| 62 |
-
"B-EMAIL": 6,
|
| 63 |
-
"B-GENDER": 7,
|
| 64 |
-
"B-GIVENNAME": 8,
|
| 65 |
-
"B-IDCARDNUM": 9,
|
| 66 |
-
"B-PASSPORTNUM": 10,
|
| 67 |
-
"B-SOCIALNUM": 11,
|
| 68 |
-
"B-STREET": 12,
|
| 69 |
-
"B-SURNAME": 13,
|
| 70 |
-
"B-TAXNUM": 14,
|
| 71 |
-
"B-TELEPHONENUM": 15,
|
| 72 |
-
"B-TIME": 16,
|
| 73 |
-
"B-TITLE": 17,
|
| 74 |
-
"B-ZIPCODE": 18,
|
| 75 |
-
"I-AGE": 19,
|
| 76 |
-
"I-BUILDINGNUM": 20,
|
| 77 |
-
"I-CITY": 21,
|
| 78 |
-
"I-CREDITCARDNUMBER": 22,
|
| 79 |
-
"I-DATE": 23,
|
| 80 |
-
"I-DRIVERLICENSENUM": 24,
|
| 81 |
-
"I-EMAIL": 25,
|
| 82 |
-
"I-GENDER": 26,
|
| 83 |
-
"I-GIVENNAME": 27,
|
| 84 |
-
"I-IDCARDNUM": 28,
|
| 85 |
-
"I-PASSPORTNUM": 29,
|
| 86 |
-
"I-SOCIALNUM": 30,
|
| 87 |
-
"I-STREET": 31,
|
| 88 |
-
"I-SURNAME": 32,
|
| 89 |
-
"I-TAXNUM": 33,
|
| 90 |
-
"I-TELEPHONENUM": 34,
|
| 91 |
-
"I-TIME": 35,
|
| 92 |
-
"I-TITLE": 36,
|
| 93 |
-
"I-ZIPCODE": 37,
|
| 94 |
-
"O": 38
|
| 95 |
-
},
|
| 96 |
-
"layer_norm_eps": 1e-12,
|
| 97 |
-
"max_position_embeddings": 512,
|
| 98 |
-
"model_type": "bert",
|
| 99 |
-
"num_attention_heads": 12,
|
| 100 |
-
"num_hidden_layers": 12,
|
| 101 |
-
"pad_token_id": 0,
|
| 102 |
-
"pooler_fc_size": 768,
|
| 103 |
-
"pooler_num_attention_heads": 12,
|
| 104 |
-
"pooler_num_fc_layers": 3,
|
| 105 |
-
"pooler_size_per_head": 128,
|
| 106 |
-
"pooler_type": "first_token_transform",
|
| 107 |
-
"position_embedding_type": "absolute",
|
| 108 |
-
"transformers_version": "4.56.0",
|
| 109 |
-
"type_vocab_size": 2,
|
| 110 |
-
"use_cache": false,
|
| 111 |
-
"vocab_size": 119547
|
| 112 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
open-pii-masking-500k-ai4privacy-augmented/TokenBased-BERT/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:57e1805bac1c5aed2926d69611947dda5e10f7f05544f15053f72c64930a89a8
|
| 3 |
-
size 711563936
|
|
|
|
|
|
|
|
|
|
|
|
open-pii-masking-500k-ai4privacy-augmented/TokenBased-BERT/special_tokens_map.json
DELETED
|
@@ -1,37 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
open-pii-masking-500k-ai4privacy-augmented/TokenBased-BERT/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
open-pii-masking-500k-ai4privacy-augmented/TokenBased-BERT/tokenizer_config.json
DELETED
|
@@ -1,66 +0,0 @@
|
|
| 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 |
-
"backend": "tokenizers",
|
| 46 |
-
"clean_up_tokenization_spaces": false,
|
| 47 |
-
"cls_token": "[CLS]",
|
| 48 |
-
"do_lower_case": false,
|
| 49 |
-
"extra_special_tokens": {},
|
| 50 |
-
"is_local": false,
|
| 51 |
-
"mask_token": "[MASK]",
|
| 52 |
-
"max_length": 512,
|
| 53 |
-
"model_max_length": 512,
|
| 54 |
-
"pad_to_multiple_of": null,
|
| 55 |
-
"pad_token": "[PAD]",
|
| 56 |
-
"pad_token_type_id": 0,
|
| 57 |
-
"padding_side": "right",
|
| 58 |
-
"sep_token": "[SEP]",
|
| 59 |
-
"stride": 0,
|
| 60 |
-
"strip_accents": null,
|
| 61 |
-
"tokenize_chinese_chars": true,
|
| 62 |
-
"tokenizer_class": "BertTokenizer",
|
| 63 |
-
"truncation_side": "right",
|
| 64 |
-
"truncation_strategy": "longest_first",
|
| 65 |
-
"unk_token": "[UNK]"
|
| 66 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
open-pii-masking-500k-ai4privacy-augmented/TokenBased-BERT/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:8dc6b3805f46a7dae7d17eb9e449f3d125a24f9791fe8cffa979717f4adc9e61
|
| 3 |
-
size 5841
|
|
|
|
|
|
|
|
|
|
|
|
open-pii-masking-500k-ai4privacy-augmented/TokenBased-BERT/vocab.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|