PuxAI commited on
Commit
ed8624e
·
verified ·
1 Parent(s): 6f63827

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -38,3 +38,4 @@ predictions_combined/en/span/predictions.json filter=lfs diff=lfs merge=lfs -tex
38
  nemotron-pii-ready/gliner-gliner_multi_pii-v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
  gretel-pii-ready/gliner-gliner_multi_pii-v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  financial-pii-ready/gliner-gliner_multi_pii-v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
38
  nemotron-pii-ready/gliner-gliner_multi_pii-v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
  gretel-pii-ready/gliner-gliner_multi_pii-v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  financial-pii-ready/gliner-gliner_multi_pii-v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ open-pii-masking-500k-ai4privacy/gliner-gliner_multi_pii-v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
open-pii-masking-500k-ai4privacy/gliner-gliner_multi_pii-v1/gliner_config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "class_token_index": 250103,
3
+ "dropout": 0.4,
4
+ "embed_ent_token": true,
5
+ "encoder_config": {
6
+ "_name_or_path": "microsoft/mdeberta-v3-base",
7
+ "architectures": null,
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "bos_token_id": null,
10
+ "chunk_size_feed_forward": 0,
11
+ "dtype": null,
12
+ "eos_token_id": null,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "LABEL_0",
18
+ "1": "LABEL_1"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "is_encoder_decoder": false,
23
+ "label2id": {
24
+ "LABEL_0": 0,
25
+ "LABEL_1": 1
26
+ },
27
+ "layer_norm_eps": 1e-07,
28
+ "legacy": true,
29
+ "max_position_embeddings": 512,
30
+ "max_relative_positions": -1,
31
+ "model_type": "deberta-v2",
32
+ "norm_rel_ebd": "layer_norm",
33
+ "num_attention_heads": 12,
34
+ "num_hidden_layers": 12,
35
+ "output_attentions": false,
36
+ "output_hidden_states": false,
37
+ "pad_token_id": 0,
38
+ "pooler_dropout": 0,
39
+ "pooler_hidden_act": "gelu",
40
+ "pooler_hidden_size": 768,
41
+ "pos_att_type": [
42
+ "p2c",
43
+ "c2p"
44
+ ],
45
+ "position_biased_input": false,
46
+ "position_buckets": 256,
47
+ "problem_type": null,
48
+ "relative_attention": true,
49
+ "return_dict": true,
50
+ "share_att_key": true,
51
+ "tie_word_embeddings": true,
52
+ "type_vocab_size": 0,
53
+ "vocab_size": 250105
54
+ },
55
+ "ent_token": "<<ENT>>",
56
+ "eval_every": 5000,
57
+ "fine_tune": true,
58
+ "fuse_layers": false,
59
+ "hidden_size": 512,
60
+ "lr_encoder": "5e-6",
61
+ "lr_others": "1e-5",
62
+ "max_len": 512,
63
+ "max_neg_type_ratio": 3,
64
+ "max_types": 25,
65
+ "max_width": 12,
66
+ "model_name": "microsoft/mdeberta-v3-base",
67
+ "model_type": null,
68
+ "name": "correct",
69
+ "neg_spans_ratio": 1.0,
70
+ "num_post_fusion_layers": 1,
71
+ "num_rnn_layers": 1,
72
+ "num_steps": 30000,
73
+ "post_fusion_schema": "",
74
+ "random_drop": false,
75
+ "represent_spans": false,
76
+ "sep_token": "<<SEP>>",
77
+ "shuffle_types": true,
78
+ "size_sup": -1,
79
+ "span_loss_coef": 1.0,
80
+ "span_mode": "markerV0",
81
+ "subtoken_pooling": "first",
82
+ "token_loss_coef": 1.0,
83
+ "train_batch_size": 8,
84
+ "transformers_version": "5.1.0",
85
+ "vocab_size": 250105,
86
+ "warmup_ratio": 5000,
87
+ "words_splitter_type": "whitespace"
88
+ }
open-pii-masking-500k-ai4privacy/gliner-gliner_multi_pii-v1/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4b24f99f9e1a539d5ff5f5f23b08a1ec579a4bcffb820897a422335a06e400b
3
+ size 1155879495
open-pii-masking-500k-ai4privacy/gliner-gliner_multi_pii-v1/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5b8041501fcdee792b9b112dd592861f04391a24633a73fd9f05aaaf6e8eff1
3
+ size 16034824
open-pii-masking-500k-ai4privacy/gliner-gliner_multi_pii-v1/tokenizer_config.json ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": false,
7
+ "eos_token": "[SEP]",
8
+ "extra_special_tokens": [
9
+ "[PAD]",
10
+ "[CLS]",
11
+ "[SEP]",
12
+ "▁<extra_id_99>",
13
+ "▁<extra_id_98>",
14
+ "▁<extra_id_97>",
15
+ "▁<extra_id_96>",
16
+ "▁<extra_id_95>",
17
+ "▁<extra_id_94>",
18
+ "▁<extra_id_93>",
19
+ "▁<extra_id_92>",
20
+ "▁<extra_id_91>",
21
+ "▁<extra_id_90>",
22
+ "▁<extra_id_89>",
23
+ "▁<extra_id_88>",
24
+ "▁<extra_id_87>",
25
+ "▁<extra_id_86>",
26
+ "▁<extra_id_85>",
27
+ "▁<extra_id_84>",
28
+ "▁<extra_id_83>",
29
+ "▁<extra_id_82>",
30
+ "▁<extra_id_81>",
31
+ "▁<extra_id_80>",
32
+ "▁<extra_id_79>",
33
+ "▁<extra_id_78>",
34
+ "▁<extra_id_77>",
35
+ "▁<extra_id_76>",
36
+ "▁<extra_id_75>",
37
+ "▁<extra_id_74>",
38
+ "▁<extra_id_73>",
39
+ "▁<extra_id_72>",
40
+ "▁<extra_id_71>",
41
+ "▁<extra_id_70>",
42
+ "▁<extra_id_69>",
43
+ "▁<extra_id_68>",
44
+ "▁<extra_id_67>",
45
+ "▁<extra_id_66>",
46
+ "▁<extra_id_65>",
47
+ "▁<extra_id_64>",
48
+ "▁<extra_id_63>",
49
+ "▁<extra_id_62>",
50
+ "▁<extra_id_61>",
51
+ "▁<extra_id_60>",
52
+ "▁<extra_id_59>",
53
+ "▁<extra_id_58>",
54
+ "▁<extra_id_57>",
55
+ "▁<extra_id_56>",
56
+ "▁<extra_id_55>",
57
+ "▁<extra_id_54>",
58
+ "▁<extra_id_53>",
59
+ "▁<extra_id_52>",
60
+ "▁<extra_id_51>",
61
+ "▁<extra_id_50>",
62
+ "▁<extra_id_49>",
63
+ "▁<extra_id_48>",
64
+ "▁<extra_id_47>",
65
+ "▁<extra_id_46>",
66
+ "▁<extra_id_45>",
67
+ "▁<extra_id_44>",
68
+ "▁<extra_id_43>",
69
+ "▁<extra_id_42>",
70
+ "▁<extra_id_41>",
71
+ "▁<extra_id_40>",
72
+ "▁<extra_id_39>",
73
+ "▁<extra_id_38>",
74
+ "▁<extra_id_37>",
75
+ "▁<extra_id_36>",
76
+ "▁<extra_id_35>",
77
+ "▁<extra_id_34>",
78
+ "▁<extra_id_33>",
79
+ "▁<extra_id_32>",
80
+ "▁<extra_id_31>",
81
+ "▁<extra_id_30>",
82
+ "▁<extra_id_29>",
83
+ "▁<extra_id_28>",
84
+ "▁<extra_id_27>",
85
+ "▁<extra_id_26>",
86
+ "▁<extra_id_25>",
87
+ "▁<extra_id_24>",
88
+ "▁<extra_id_23>",
89
+ "▁<extra_id_22>",
90
+ "▁<extra_id_21>",
91
+ "▁<extra_id_20>",
92
+ "▁<extra_id_19>",
93
+ "▁<extra_id_18>",
94
+ "▁<extra_id_17>",
95
+ "▁<extra_id_16>",
96
+ "▁<extra_id_15>",
97
+ "▁<extra_id_14>",
98
+ "▁<extra_id_13>",
99
+ "▁<extra_id_12>",
100
+ "▁<extra_id_11>",
101
+ "▁<extra_id_10>",
102
+ "▁<extra_id_9>",
103
+ "▁<extra_id_8>",
104
+ "▁<extra_id_7>",
105
+ "▁<extra_id_6>",
106
+ "▁<extra_id_5>",
107
+ "▁<extra_id_4>",
108
+ "▁<extra_id_3>",
109
+ "▁<extra_id_2>",
110
+ "▁<extra_id_1>",
111
+ "▁<extra_id_0>"
112
+ ],
113
+ "is_local": false,
114
+ "mask_token": "[MASK]",
115
+ "model_max_length": 1000000000000000019884624838656,
116
+ "pad_token": "[PAD]",
117
+ "sep_token": "[SEP]",
118
+ "split_by_punct": false,
119
+ "tokenizer_class": "DebertaV2Tokenizer",
120
+ "unk_id": 3,
121
+ "unk_token": "[UNK]",
122
+ "vocab_type": "spm"
123
+ }
open-pii-masking-500k-ai4privacy/gliner-gliner_multi_pii-v1/training_meta.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "gliner",
3
+ "base_model": "urchade/gliner_multi_pii-v1",
4
+ "dataset": "open-pii-masking-500k-ai4privacy",
5
+ "label_map": {
6
+ "AGE": "age",
7
+ "BUILDINGNUM": "buildingnum",
8
+ "CITY": "city",
9
+ "CREDITCARDNUMBER": "creditcardnumber",
10
+ "DATE": "date",
11
+ "DRIVERLICENSENUM": "driverlicensenum",
12
+ "EMAIL": "email",
13
+ "GENDER": "gender",
14
+ "GIVENNAME": "givenname",
15
+ "IDCARDNUM": "idcardnum",
16
+ "PASSPORTNUM": "passportnum",
17
+ "SEX": "sex",
18
+ "SOCIALNUM": "socialnum",
19
+ "STREET": "street",
20
+ "SURNAME": "surname",
21
+ "TAXNUM": "taxnum",
22
+ "TELEPHONENUM": "telephonenum",
23
+ "TIME": "time",
24
+ "TITLE": "title",
25
+ "ZIPCODE": "zipcode"
26
+ },
27
+ "timestamp": "2026-06-14T09:39:43.006446"
28
+ }