PuxAI commited on
Commit
ec7b2b1
·
verified ·
1 Parent(s): 7144ffd

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -39,3 +39,5 @@ Monolingual-DE/SpanBased-DeBERTa/checkpoint-5942/tokenizer.json filter=lfs diff=
39
  Monolingual-DE/SpanBased-DeBERTa/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  Monolingual-IT/SpanBased-DeBERTa/checkpoint-5736/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
  Monolingual-IT/SpanBased-DeBERTa/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
39
  Monolingual-DE/SpanBased-DeBERTa/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  Monolingual-IT/SpanBased-DeBERTa/checkpoint-5736/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
  Monolingual-IT/SpanBased-DeBERTa/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
+ Monolingual-FR/SpanBased-DeBERTa/checkpoint-6972/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
+ Monolingual-FR/SpanBased-DeBERTa/tokenizer.json filter=lfs diff=lfs merge=lfs -text
Monolingual-FR/SpanBased-DeBERTa/checkpoint-6972/config.json ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "ACCOUNTNAME",
15
+ "2": "ACCOUNTNUMBER",
16
+ "3": "AGE",
17
+ "4": "AMOUNT",
18
+ "5": "BIC",
19
+ "6": "BITCOINADDRESS",
20
+ "7": "BUILDINGNUMBER",
21
+ "8": "CITY",
22
+ "9": "COMPANYNAME",
23
+ "10": "COUNTY",
24
+ "11": "CREDITCARDCVV",
25
+ "12": "CREDITCARDISSUER",
26
+ "13": "CREDITCARDNUMBER",
27
+ "14": "CURRENCY",
28
+ "15": "CURRENCYCODE",
29
+ "16": "CURRENCYNAME",
30
+ "17": "CURRENCYSYMBOL",
31
+ "18": "DATE",
32
+ "19": "DOB",
33
+ "20": "EMAIL",
34
+ "21": "ETHEREUMADDRESS",
35
+ "22": "EYECOLOR",
36
+ "23": "FIRSTNAME",
37
+ "24": "GENDER",
38
+ "25": "HEIGHT",
39
+ "26": "IBAN",
40
+ "27": "IP",
41
+ "28": "IPV4",
42
+ "29": "IPV6",
43
+ "30": "JOBAREA",
44
+ "31": "JOBTITLE",
45
+ "32": "JOBTYPE",
46
+ "33": "LASTNAME",
47
+ "34": "LITECOINADDRESS",
48
+ "35": "MAC",
49
+ "36": "MASKEDNUMBER",
50
+ "37": "MIDDLENAME",
51
+ "38": "NEARBYGPSCOORDINATE",
52
+ "39": "ORDINALDIRECTION",
53
+ "40": "PASSWORD",
54
+ "41": "PHONEIMEI",
55
+ "42": "PHONENUMBER",
56
+ "43": "PIN",
57
+ "44": "PREFIX",
58
+ "45": "SECONDARYADDRESS",
59
+ "46": "SEX",
60
+ "47": "SSN",
61
+ "48": "STATE",
62
+ "49": "STREET",
63
+ "50": "TIME",
64
+ "51": "URL",
65
+ "52": "USERAGENT",
66
+ "53": "USERNAME",
67
+ "54": "VEHICLEVIN",
68
+ "55": "VEHICLEVRM",
69
+ "56": "ZIPCODE"
70
+ },
71
+ "initializer_range": 0.02,
72
+ "intermediate_size": 3072,
73
+ "label2id": {
74
+ "ACCOUNTNAME": 1,
75
+ "ACCOUNTNUMBER": 2,
76
+ "AGE": 3,
77
+ "AMOUNT": 4,
78
+ "BIC": 5,
79
+ "BITCOINADDRESS": 6,
80
+ "BUILDINGNUMBER": 7,
81
+ "CITY": 8,
82
+ "COMPANYNAME": 9,
83
+ "COUNTY": 10,
84
+ "CREDITCARDCVV": 11,
85
+ "CREDITCARDISSUER": 12,
86
+ "CREDITCARDNUMBER": 13,
87
+ "CURRENCY": 14,
88
+ "CURRENCYCODE": 15,
89
+ "CURRENCYNAME": 16,
90
+ "CURRENCYSYMBOL": 17,
91
+ "DATE": 18,
92
+ "DOB": 19,
93
+ "EMAIL": 20,
94
+ "ETHEREUMADDRESS": 21,
95
+ "EYECOLOR": 22,
96
+ "FIRSTNAME": 23,
97
+ "GENDER": 24,
98
+ "HEIGHT": 25,
99
+ "IBAN": 26,
100
+ "IP": 27,
101
+ "IPV4": 28,
102
+ "IPV6": 29,
103
+ "JOBAREA": 30,
104
+ "JOBTITLE": 31,
105
+ "JOBTYPE": 32,
106
+ "LASTNAME": 33,
107
+ "LITECOINADDRESS": 34,
108
+ "MAC": 35,
109
+ "MASKEDNUMBER": 36,
110
+ "MIDDLENAME": 37,
111
+ "NEARBYGPSCOORDINATE": 38,
112
+ "O": 0,
113
+ "ORDINALDIRECTION": 39,
114
+ "PASSWORD": 40,
115
+ "PHONEIMEI": 41,
116
+ "PHONENUMBER": 42,
117
+ "PIN": 43,
118
+ "PREFIX": 44,
119
+ "SECONDARYADDRESS": 45,
120
+ "SEX": 46,
121
+ "SSN": 47,
122
+ "STATE": 48,
123
+ "STREET": 49,
124
+ "TIME": 50,
125
+ "URL": 51,
126
+ "USERAGENT": 52,
127
+ "USERNAME": 53,
128
+ "VEHICLEVIN": 54,
129
+ "VEHICLEVRM": 55,
130
+ "ZIPCODE": 56
131
+ },
132
+ "layer_norm_eps": 1e-07,
133
+ "legacy": true,
134
+ "max_position_embeddings": 512,
135
+ "max_relative_positions": -1,
136
+ "model_type": "deberta-v2",
137
+ "norm_rel_ebd": "layer_norm",
138
+ "num_attention_heads": 12,
139
+ "num_hidden_layers": 12,
140
+ "pad_token_id": 0,
141
+ "pooler_dropout": 0,
142
+ "pooler_hidden_act": "gelu",
143
+ "pooler_hidden_size": 768,
144
+ "pos_att_type": [
145
+ "p2c",
146
+ "c2p"
147
+ ],
148
+ "position_biased_input": false,
149
+ "position_buckets": 256,
150
+ "relative_attention": true,
151
+ "share_att_key": true,
152
+ "tie_word_embeddings": true,
153
+ "transformers_version": "5.3.0",
154
+ "type_vocab_size": 0,
155
+ "use_cache": false,
156
+ "vocab_size": 251000
157
+ }
Monolingual-FR/SpanBased-DeBERTa/checkpoint-6972/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78ece72b7697b0605dc88b7c1a9240a1348aacf16d02304c9787b14d3401021e
3
+ size 1119053244
Monolingual-FR/SpanBased-DeBERTa/checkpoint-6972/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84f382ceaf2d52a6ef840040485253151eb012fc5fbc7f75f2f06440e3a63b16
3
+ size 2238229899
Monolingual-FR/SpanBased-DeBERTa/checkpoint-6972/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b668923603f265fb98491b06ba81e60c16ba34213bd30525939203b8399f5658
3
+ size 14645
Monolingual-FR/SpanBased-DeBERTa/checkpoint-6972/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b0ffe1c5339266a7640f64d74cbe7720984c034c061903c7cafd92501da2b55
3
+ size 1383
Monolingual-FR/SpanBased-DeBERTa/checkpoint-6972/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2318df84d42951cae05cac0c012c9f3e976a739d62686c65c649b8d9394484e
3
+ size 1465
Monolingual-FR/SpanBased-DeBERTa/checkpoint-6972/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cbe465237b1dd548fe5cdb31bbb2468bece593dedbc71c50e491a422b706ec5
3
+ size 16033331
Monolingual-FR/SpanBased-DeBERTa/checkpoint-6972/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
+ }
Monolingual-FR/SpanBased-DeBERTa/checkpoint-6972/trainer_state.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 6972,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.1434308663224326,
14
+ "grad_norm": 0.007672377396374941,
15
+ "learning_rate": 1.8568559954102125e-05,
16
+ "loss": 0.009684596061706543,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.2868617326448652,
21
+ "grad_norm": 0.012297257781028748,
22
+ "learning_rate": 1.7134251290877798e-05,
23
+ "loss": 0.004615603446960449,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.43029259896729777,
28
+ "grad_norm": 0.011442928574979305,
29
+ "learning_rate": 1.5699942627653474e-05,
30
+ "loss": 0.002997920036315918,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.5737234652897304,
35
+ "grad_norm": 0.013272660784423351,
36
+ "learning_rate": 1.4265633964429147e-05,
37
+ "loss": 0.0017894148826599122,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.7171543316121629,
42
+ "grad_norm": 0.014016266912221909,
43
+ "learning_rate": 1.283132530120482e-05,
44
+ "loss": 0.0011281795501708984,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.8605851979345955,
49
+ "grad_norm": 0.010322137735784054,
50
+ "learning_rate": 1.1397016637980494e-05,
51
+ "loss": 0.0008115814924240112,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 1.0040160642570282,
56
+ "grad_norm": 0.01365757267922163,
57
+ "learning_rate": 9.962707974756169e-06,
58
+ "loss": 0.0006433913707733155,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 1.1474469305794608,
63
+ "grad_norm": 0.009805912151932716,
64
+ "learning_rate": 8.528399311531842e-06,
65
+ "loss": 0.000557729184627533,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 1.2908777969018934,
70
+ "grad_norm": 0.008765346370637417,
71
+ "learning_rate": 7.0940906483075165e-06,
72
+ "loss": 0.000488772600889206,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 1.4343086632243258,
77
+ "grad_norm": 0.00846004392951727,
78
+ "learning_rate": 5.65978198508319e-06,
79
+ "loss": 0.00042926350235939024,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 1.5777395295467584,
84
+ "grad_norm": 0.005864540580660105,
85
+ "learning_rate": 4.225473321858865e-06,
86
+ "loss": 0.00040997520089149477,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 1.721170395869191,
91
+ "grad_norm": 0.004622944165021181,
92
+ "learning_rate": 2.791164658634538e-06,
93
+ "loss": 0.00037252518534660337,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 1.8646012621916235,
98
+ "grad_norm": 0.01336298044770956,
99
+ "learning_rate": 1.3568559954102124e-06,
100
+ "loss": 0.0003555941879749298,
101
+ "step": 6500
102
+ }
103
+ ],
104
+ "logging_steps": 500,
105
+ "max_steps": 6972,
106
+ "num_input_tokens_seen": 0,
107
+ "num_train_epochs": 2,
108
+ "save_steps": 500,
109
+ "stateful_callbacks": {
110
+ "TrainerControl": {
111
+ "args": {
112
+ "should_epoch_stop": false,
113
+ "should_evaluate": false,
114
+ "should_log": false,
115
+ "should_save": true,
116
+ "should_training_stop": true
117
+ },
118
+ "attributes": {}
119
+ }
120
+ },
121
+ "total_flos": 6188296941634716.0,
122
+ "train_batch_size": 16,
123
+ "trial_name": null,
124
+ "trial_params": null
125
+ }
Monolingual-FR/SpanBased-DeBERTa/checkpoint-6972/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58af4ac5d37dce3a24d4efe0fcee222a03b32191d31271708f2149b94b7876f3
3
+ size 5201
Monolingual-FR/SpanBased-DeBERTa/config.json ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "ACCOUNTNAME",
15
+ "2": "ACCOUNTNUMBER",
16
+ "3": "AGE",
17
+ "4": "AMOUNT",
18
+ "5": "BIC",
19
+ "6": "BITCOINADDRESS",
20
+ "7": "BUILDINGNUMBER",
21
+ "8": "CITY",
22
+ "9": "COMPANYNAME",
23
+ "10": "COUNTY",
24
+ "11": "CREDITCARDCVV",
25
+ "12": "CREDITCARDISSUER",
26
+ "13": "CREDITCARDNUMBER",
27
+ "14": "CURRENCY",
28
+ "15": "CURRENCYCODE",
29
+ "16": "CURRENCYNAME",
30
+ "17": "CURRENCYSYMBOL",
31
+ "18": "DATE",
32
+ "19": "DOB",
33
+ "20": "EMAIL",
34
+ "21": "ETHEREUMADDRESS",
35
+ "22": "EYECOLOR",
36
+ "23": "FIRSTNAME",
37
+ "24": "GENDER",
38
+ "25": "HEIGHT",
39
+ "26": "IBAN",
40
+ "27": "IP",
41
+ "28": "IPV4",
42
+ "29": "IPV6",
43
+ "30": "JOBAREA",
44
+ "31": "JOBTITLE",
45
+ "32": "JOBTYPE",
46
+ "33": "LASTNAME",
47
+ "34": "LITECOINADDRESS",
48
+ "35": "MAC",
49
+ "36": "MASKEDNUMBER",
50
+ "37": "MIDDLENAME",
51
+ "38": "NEARBYGPSCOORDINATE",
52
+ "39": "ORDINALDIRECTION",
53
+ "40": "PASSWORD",
54
+ "41": "PHONEIMEI",
55
+ "42": "PHONENUMBER",
56
+ "43": "PIN",
57
+ "44": "PREFIX",
58
+ "45": "SECONDARYADDRESS",
59
+ "46": "SEX",
60
+ "47": "SSN",
61
+ "48": "STATE",
62
+ "49": "STREET",
63
+ "50": "TIME",
64
+ "51": "URL",
65
+ "52": "USERAGENT",
66
+ "53": "USERNAME",
67
+ "54": "VEHICLEVIN",
68
+ "55": "VEHICLEVRM",
69
+ "56": "ZIPCODE"
70
+ },
71
+ "initializer_range": 0.02,
72
+ "intermediate_size": 3072,
73
+ "label2id": {
74
+ "ACCOUNTNAME": 1,
75
+ "ACCOUNTNUMBER": 2,
76
+ "AGE": 3,
77
+ "AMOUNT": 4,
78
+ "BIC": 5,
79
+ "BITCOINADDRESS": 6,
80
+ "BUILDINGNUMBER": 7,
81
+ "CITY": 8,
82
+ "COMPANYNAME": 9,
83
+ "COUNTY": 10,
84
+ "CREDITCARDCVV": 11,
85
+ "CREDITCARDISSUER": 12,
86
+ "CREDITCARDNUMBER": 13,
87
+ "CURRENCY": 14,
88
+ "CURRENCYCODE": 15,
89
+ "CURRENCYNAME": 16,
90
+ "CURRENCYSYMBOL": 17,
91
+ "DATE": 18,
92
+ "DOB": 19,
93
+ "EMAIL": 20,
94
+ "ETHEREUMADDRESS": 21,
95
+ "EYECOLOR": 22,
96
+ "FIRSTNAME": 23,
97
+ "GENDER": 24,
98
+ "HEIGHT": 25,
99
+ "IBAN": 26,
100
+ "IP": 27,
101
+ "IPV4": 28,
102
+ "IPV6": 29,
103
+ "JOBAREA": 30,
104
+ "JOBTITLE": 31,
105
+ "JOBTYPE": 32,
106
+ "LASTNAME": 33,
107
+ "LITECOINADDRESS": 34,
108
+ "MAC": 35,
109
+ "MASKEDNUMBER": 36,
110
+ "MIDDLENAME": 37,
111
+ "NEARBYGPSCOORDINATE": 38,
112
+ "O": 0,
113
+ "ORDINALDIRECTION": 39,
114
+ "PASSWORD": 40,
115
+ "PHONEIMEI": 41,
116
+ "PHONENUMBER": 42,
117
+ "PIN": 43,
118
+ "PREFIX": 44,
119
+ "SECONDARYADDRESS": 45,
120
+ "SEX": 46,
121
+ "SSN": 47,
122
+ "STATE": 48,
123
+ "STREET": 49,
124
+ "TIME": 50,
125
+ "URL": 51,
126
+ "USERAGENT": 52,
127
+ "USERNAME": 53,
128
+ "VEHICLEVIN": 54,
129
+ "VEHICLEVRM": 55,
130
+ "ZIPCODE": 56
131
+ },
132
+ "layer_norm_eps": 1e-07,
133
+ "legacy": true,
134
+ "max_position_embeddings": 512,
135
+ "max_relative_positions": -1,
136
+ "model_type": "deberta-v2",
137
+ "norm_rel_ebd": "layer_norm",
138
+ "num_attention_heads": 12,
139
+ "num_hidden_layers": 12,
140
+ "pad_token_id": 0,
141
+ "pooler_dropout": 0,
142
+ "pooler_hidden_act": "gelu",
143
+ "pooler_hidden_size": 768,
144
+ "pos_att_type": [
145
+ "p2c",
146
+ "c2p"
147
+ ],
148
+ "position_biased_input": false,
149
+ "position_buckets": 256,
150
+ "relative_attention": true,
151
+ "share_att_key": true,
152
+ "tie_word_embeddings": true,
153
+ "transformers_version": "5.3.0",
154
+ "type_vocab_size": 0,
155
+ "use_cache": false,
156
+ "vocab_size": 251000
157
+ }
Monolingual-FR/SpanBased-DeBERTa/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3de6f5a8b15a2c64f38641070b77c25acafa189b4892ed52811709f4efa0899b
3
+ size 1119115023
Monolingual-FR/SpanBased-DeBERTa/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cbe465237b1dd548fe5cdb31bbb2468bece593dedbc71c50e491a422b706ec5
3
+ size 16033331
Monolingual-FR/SpanBased-DeBERTa/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
+ }