Hugging Face's logo

PuxAI
/
GenPII-framework

Safetensors
Model card Files
xet
 Community
PuxAI commited on
Commit
9869417
·
verified ·
1 Parent(s): 1fc24d6

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. ai4privacy_500k/SpanBased-CustomDeBERTa/checkpoint-250/config.json +85 -0
  2. ai4privacy_500k/SpanBased-CustomDeBERTa/checkpoint-250/model.safetensors +3 -0
  3. ai4privacy_500k/SpanBased-CustomDeBERTa/checkpoint-250/optimizer.pt +3 -0
  4. ai4privacy_500k/SpanBased-CustomDeBERTa/checkpoint-250/rng_state.pth +3 -0
  5. ai4privacy_500k/SpanBased-CustomDeBERTa/checkpoint-250/scheduler.pt +3 -0
  6. ai4privacy_500k/SpanBased-CustomDeBERTa/checkpoint-250/tokenizer.json +0 -0
  7. ai4privacy_500k/SpanBased-CustomDeBERTa/checkpoint-250/tokenizer_config.json +23 -0
  8. ai4privacy_500k/SpanBased-CustomDeBERTa/checkpoint-250/trainer_state.json +33 -0
  9. ai4privacy_500k/SpanBased-CustomDeBERTa/checkpoint-250/training_args.bin +3 -0
  10. ai4privacy_500k/SpanBased-CustomDeBERTa/config.json +85 -0
  11. ai4privacy_500k/SpanBased-CustomDeBERTa/pytorch_model.bin +3 -0
  12. ai4privacy_500k/SpanBased-CustomDeBERTa/tokenizer.json +0 -0
  13. ai4privacy_500k/SpanBased-CustomDeBERTa/tokenizer_config.json +23 -0
ai4privacy_500k/SpanBased-CustomDeBERTa/checkpoint-250/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaAdvancedSpanClassifier"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": null,
7
+ "dtype": "float32",
8
+ "eos_token_id": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "AGE",
15
+ "2": "BUILDINGNUM",
16
+ "3": "CITY",
17
+ "4": "CREDITCARDNUMBER",
18
+ "5": "DATE",
19
+ "6": "DRIVERLICENSENUM",
20
+ "7": "EMAIL",
21
+ "8": "GENDER",
22
+ "9": "GIVENNAME",
23
+ "10": "IDCARDNUM",
24
+ "11": "PASSPORTNUM",
25
+ "12": "SEX",
26
+ "13": "SOCIALNUM",
27
+ "14": "STREET",
28
+ "15": "SURNAME",
29
+ "16": "TAXNUM",
30
+ "17": "TELEPHONENUM",
31
+ "18": "TIME",
32
+ "19": "TITLE",
33
+ "20": "ZIPCODE"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "label2id": {
38
+ "AGE": 1,
39
+ "BUILDINGNUM": 2,
40
+ "CITY": 3,
41
+ "CREDITCARDNUMBER": 4,
42
+ "DATE": 5,
43
+ "DRIVERLICENSENUM": 6,
44
+ "EMAIL": 7,
45
+ "GENDER": 8,
46
+ "GIVENNAME": 9,
47
+ "IDCARDNUM": 10,
48
+ "O": 0,
49
+ "PASSPORTNUM": 11,
50
+ "SEX": 12,
51
+ "SOCIALNUM": 13,
52
+ "STREET": 14,
53
+ "SURNAME": 15,
54
+ "TAXNUM": 16,
55
+ "TELEPHONENUM": 17,
56
+ "TIME": 18,
57
+ "TITLE": 19,
58
+ "ZIPCODE": 20
59
+ },
60
+ "layer_norm_eps": 1e-07,
61
+ "legacy": true,
62
+ "max_position_embeddings": 512,
63
+ "max_relative_positions": -1,
64
+ "model_type": "deberta-v2",
65
+ "norm_rel_ebd": "layer_norm",
66
+ "num_attention_heads": 12,
67
+ "num_hidden_layers": 12,
68
+ "pad_token_id": 0,
69
+ "pooler_dropout": 0,
70
+ "pooler_hidden_act": "gelu",
71
+ "pooler_hidden_size": 768,
72
+ "pos_att_type": [
73
+ "p2c",
74
+ "c2p"
75
+ ],
76
+ "position_biased_input": false,
77
+ "position_buckets": 256,
78
+ "relative_attention": true,
79
+ "share_att_key": true,
80
+ "tie_word_embeddings": true,
81
+ "transformers_version": "5.3.0",
82
+ "type_vocab_size": 0,
83
+ "use_cache": false,
84
+ "vocab_size": 128100
85
+ }
ai4privacy_500k/SpanBased-CustomDeBERTa/checkpoint-250/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3938e325c2203e63d1eb961447f91f5eaeb357f38ffd33528448c2d82e8af6b4
3
+ size 741393580
ai4privacy_500k/SpanBased-CustomDeBERTa/checkpoint-250/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f9160f87b91629da31a8ac2f8d3be25b0792f491874419f30107f9b9dda1c3
3
+ size 1482910859
ai4privacy_500k/SpanBased-CustomDeBERTa/checkpoint-250/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e6c21e85ac3a4d31edfe2010af7ed4a9b8d67e5d21e38630933011fa80f7375
3
+ size 14645
ai4privacy_500k/SpanBased-CustomDeBERTa/checkpoint-250/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b04611bea80597dee677a377375d057cf3fa3437fb4ed8809d4662285b8811b
3
+ size 1465
ai4privacy_500k/SpanBased-CustomDeBERTa/checkpoint-250/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
ai4privacy_500k/SpanBased-CustomDeBERTa/checkpoint-250/tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ],
13
+ "is_local": false,
14
+ "mask_token": "[MASK]",
15
+ "model_max_length": 1000000000000000019884624838656,
16
+ "pad_token": "[PAD]",
17
+ "sep_token": "[SEP]",
18
+ "split_by_punct": false,
19
+ "tokenizer_class": "DebertaV2Tokenizer",
20
+ "unk_id": 3,
21
+ "unk_token": "[UNK]",
22
+ "vocab_type": "spm"
23
+ }
ai4privacy_500k/SpanBased-CustomDeBERTa/checkpoint-250/trainer_state.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 250,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [],
12
+ "logging_steps": 500,
13
+ "max_steps": 250,
14
+ "num_input_tokens_seen": 0,
15
+ "num_train_epochs": 1,
16
+ "save_steps": 500,
17
+ "stateful_callbacks": {
18
+ "TrainerControl": {
19
+ "args": {
20
+ "should_epoch_stop": false,
21
+ "should_evaluate": false,
22
+ "should_log": false,
23
+ "should_save": true,
24
+ "should_training_stop": true
25
+ },
26
+ "attributes": {}
27
+ }
28
+ },
29
+ "total_flos": 9621480677184.0,
30
+ "train_batch_size": 2,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
ai4privacy_500k/SpanBased-CustomDeBERTa/checkpoint-250/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f5172629b8600d11f727b092327fd79439463dfef84c63919927062d70ebaac
3
+ size 5201
ai4privacy_500k/SpanBased-CustomDeBERTa/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaAdvancedSpanClassifier"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": null,
7
+ "dtype": "float32",
8
+ "eos_token_id": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "AGE",
15
+ "2": "BUILDINGNUM",
16
+ "3": "CITY",
17
+ "4": "CREDITCARDNUMBER",
18
+ "5": "DATE",
19
+ "6": "DRIVERLICENSENUM",
20
+ "7": "EMAIL",
21
+ "8": "GENDER",
22
+ "9": "GIVENNAME",
23
+ "10": "IDCARDNUM",
24
+ "11": "PASSPORTNUM",
25
+ "12": "SEX",
26
+ "13": "SOCIALNUM",
27
+ "14": "STREET",
28
+ "15": "SURNAME",
29
+ "16": "TAXNUM",
30
+ "17": "TELEPHONENUM",
31
+ "18": "TIME",
32
+ "19": "TITLE",
33
+ "20": "ZIPCODE"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "label2id": {
38
+ "AGE": 1,
39
+ "BUILDINGNUM": 2,
40
+ "CITY": 3,
41
+ "CREDITCARDNUMBER": 4,
42
+ "DATE": 5,
43
+ "DRIVERLICENSENUM": 6,
44
+ "EMAIL": 7,
45
+ "GENDER": 8,
46
+ "GIVENNAME": 9,
47
+ "IDCARDNUM": 10,
48
+ "O": 0,
49
+ "PASSPORTNUM": 11,
50
+ "SEX": 12,
51
+ "SOCIALNUM": 13,
52
+ "STREET": 14,
53
+ "SURNAME": 15,
54
+ "TAXNUM": 16,
55
+ "TELEPHONENUM": 17,
56
+ "TIME": 18,
57
+ "TITLE": 19,
58
+ "ZIPCODE": 20
59
+ },
60
+ "layer_norm_eps": 1e-07,
61
+ "legacy": true,
62
+ "max_position_embeddings": 512,
63
+ "max_relative_positions": -1,
64
+ "model_type": "deberta-v2",
65
+ "norm_rel_ebd": "layer_norm",
66
+ "num_attention_heads": 12,
67
+ "num_hidden_layers": 12,
68
+ "pad_token_id": 0,
69
+ "pooler_dropout": 0,
70
+ "pooler_hidden_act": "gelu",
71
+ "pooler_hidden_size": 768,
72
+ "pos_att_type": [
73
+ "p2c",
74
+ "c2p"
75
+ ],
76
+ "position_biased_input": false,
77
+ "position_buckets": 256,
78
+ "relative_attention": true,
79
+ "share_att_key": true,
80
+ "tie_word_embeddings": true,
81
+ "transformers_version": "5.3.0",
82
+ "type_vocab_size": 0,
83
+ "use_cache": false,
84
+ "vocab_size": 128100
85
+ }
ai4privacy_500k/SpanBased-CustomDeBERTa/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2dad1ed10484318360143e6aae80209c86d61758f7d7c86242a4388823ef37a
3
+ size 741455503
ai4privacy_500k/SpanBased-CustomDeBERTa/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
ai4privacy_500k/SpanBased-CustomDeBERTa/tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ],
13
+ "is_local": false,
14
+ "mask_token": "[MASK]",
15
+ "model_max_length": 1000000000000000019884624838656,
16
+ "pad_token": "[PAD]",
17
+ "sep_token": "[SEP]",
18
+ "split_by_punct": false,
19
+ "tokenizer_class": "DebertaV2Tokenizer",
20
+ "unk_id": 3,
21
+ "unk_token": "[UNK]",
22
+ "vocab_type": "spm"
23
+ }