Hugging Face's logo

hiteshwadhwani
/
pii-model-indicv2

Token Classification
Safetensors
English
Hindi
bert
ner
pii
indian-languages
hindi
devanagari
hinglish
privacy
Eval Results (legacy)
Model card Files
xet
 Community
hiteshwadhwani commited on
Commit
532f888
·
verified ·
1 Parent(s): ee16bc7

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. config.json +155 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +37 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +245 -0
  6. training_info.json +17 -0
config.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "embedding_size": 768,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-ACCOUNTNUMBER",
15
+ "2": "I-ACCOUNTNUMBER",
16
+ "3": "B-FIRSTNAME",
17
+ "4": "I-FIRSTNAME",
18
+ "5": "B-ACCOUNTNAME",
19
+ "6": "I-ACCOUNTNAME",
20
+ "7": "B-PHONENUMBER",
21
+ "8": "I-PHONENUMBER",
22
+ "9": "B-CREDITCARDCVV",
23
+ "10": "I-CREDITCARDCVV",
24
+ "11": "B-CREDITCARDISSUER",
25
+ "12": "I-CREDITCARDISSUER",
26
+ "13": "B-PREFIX",
27
+ "14": "I-PREFIX",
28
+ "15": "B-LASTNAME",
29
+ "16": "I-LASTNAME",
30
+ "17": "B-AMOUNT",
31
+ "18": "I-AMOUNT",
32
+ "19": "B-DATE",
33
+ "20": "I-DATE",
34
+ "21": "B-DOB",
35
+ "22": "I-DOB",
36
+ "23": "B-COMPANYNAME",
37
+ "24": "I-COMPANYNAME",
38
+ "25": "B-BUILDINGNUMBER",
39
+ "26": "I-BUILDINGNUMBER",
40
+ "27": "B-STREET",
41
+ "28": "I-STREET",
42
+ "29": "B-SECONDARYADDRESS",
43
+ "30": "I-SECONDARYADDRESS",
44
+ "31": "B-STATE",
45
+ "32": "I-STATE",
46
+ "33": "B-EMAIL",
47
+ "34": "I-EMAIL",
48
+ "35": "B-CITY",
49
+ "36": "I-CITY",
50
+ "37": "B-CREDITCARDNUMBER",
51
+ "38": "I-CREDITCARDNUMBER",
52
+ "39": "B-SSN",
53
+ "40": "I-SSN",
54
+ "41": "B-URL",
55
+ "42": "I-URL",
56
+ "43": "B-USERNAME",
57
+ "44": "I-USERNAME",
58
+ "45": "B-PASSWORD",
59
+ "46": "I-PASSWORD",
60
+ "47": "B-COUNTY",
61
+ "48": "I-COUNTY",
62
+ "49": "B-PIN",
63
+ "50": "I-PIN",
64
+ "51": "B-MIDDLENAME",
65
+ "52": "I-MIDDLENAME",
66
+ "53": "B-IBAN",
67
+ "54": "I-IBAN",
68
+ "55": "B-GENDER",
69
+ "56": "I-GENDER",
70
+ "57": "B-AGE",
71
+ "58": "I-AGE",
72
+ "59": "B-ZIPCODE",
73
+ "60": "I-ZIPCODE",
74
+ "61": "B-SEX",
75
+ "62": "I-SEX"
76
+ },
77
+ "initializer_range": 0.02,
78
+ "intermediate_size": 3072,
79
+ "label2id": {
80
+ "B-ACCOUNTNAME": 5,
81
+ "B-ACCOUNTNUMBER": 1,
82
+ "B-AGE": 57,
83
+ "B-AMOUNT": 17,
84
+ "B-BUILDINGNUMBER": 25,
85
+ "B-CITY": 35,
86
+ "B-COMPANYNAME": 23,
87
+ "B-COUNTY": 47,
88
+ "B-CREDITCARDCVV": 9,
89
+ "B-CREDITCARDISSUER": 11,
90
+ "B-CREDITCARDNUMBER": 37,
91
+ "B-DATE": 19,
92
+ "B-DOB": 21,
93
+ "B-EMAIL": 33,
94
+ "B-FIRSTNAME": 3,
95
+ "B-GENDER": 55,
96
+ "B-IBAN": 53,
97
+ "B-LASTNAME": 15,
98
+ "B-MIDDLENAME": 51,
99
+ "B-PASSWORD": 45,
100
+ "B-PHONENUMBER": 7,
101
+ "B-PIN": 49,
102
+ "B-PREFIX": 13,
103
+ "B-SECONDARYADDRESS": 29,
104
+ "B-SEX": 61,
105
+ "B-SSN": 39,
106
+ "B-STATE": 31,
107
+ "B-STREET": 27,
108
+ "B-URL": 41,
109
+ "B-USERNAME": 43,
110
+ "B-ZIPCODE": 59,
111
+ "I-ACCOUNTNAME": 6,
112
+ "I-ACCOUNTNUMBER": 2,
113
+ "I-AGE": 58,
114
+ "I-AMOUNT": 18,
115
+ "I-BUILDINGNUMBER": 26,
116
+ "I-CITY": 36,
117
+ "I-COMPANYNAME": 24,
118
+ "I-COUNTY": 48,
119
+ "I-CREDITCARDCVV": 10,
120
+ "I-CREDITCARDISSUER": 12,
121
+ "I-CREDITCARDNUMBER": 38,
122
+ "I-DATE": 20,
123
+ "I-DOB": 22,
124
+ "I-EMAIL": 34,
125
+ "I-FIRSTNAME": 4,
126
+ "I-GENDER": 56,
127
+ "I-IBAN": 54,
128
+ "I-LASTNAME": 16,
129
+ "I-MIDDLENAME": 52,
130
+ "I-PASSWORD": 46,
131
+ "I-PHONENUMBER": 8,
132
+ "I-PIN": 50,
133
+ "I-PREFIX": 14,
134
+ "I-SECONDARYADDRESS": 30,
135
+ "I-SEX": 62,
136
+ "I-SSN": 40,
137
+ "I-STATE": 32,
138
+ "I-STREET": 28,
139
+ "I-URL": 42,
140
+ "I-USERNAME": 44,
141
+ "I-ZIPCODE": 60,
142
+ "O": 0
143
+ },
144
+ "layer_norm_eps": 1e-12,
145
+ "max_position_embeddings": 512,
146
+ "model_type": "bert",
147
+ "num_attention_heads": 12,
148
+ "num_hidden_layers": 12,
149
+ "pad_token_id": 3,
150
+ "position_embedding_type": "absolute",
151
+ "transformers_version": "4.57.6",
152
+ "type_vocab_size": 2,
153
+ "use_cache": true,
154
+ "vocab_size": 250000
155
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9891d278072689274b2a4576c68bf6f9da904a6a8e41a2787ce4eb599f7a407d
3
+ size 1110020276
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[PAD]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<as>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<bd>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<bn>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "<dg>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "9": {
76
+ "content": "<en>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "10": {
84
+ "content": "<gom>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "11": {
92
+ "content": "<gu>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "12": {
100
+ "content": "<hi>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "13": {
108
+ "content": "<kha>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "14": {
116
+ "content": "<kn>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "15": {
124
+ "content": "<ks>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "16": {
132
+ "content": "<mai>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "17": {
140
+ "content": "<ml>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "18": {
148
+ "content": "<mni>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "19": {
156
+ "content": "<mr>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "20": {
164
+ "content": "<ne>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "21": {
172
+ "content": "<or>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "22": {
180
+ "content": "<pa>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "23": {
188
+ "content": "<sa>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "24": {
196
+ "content": "<sd>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "25": {
204
+ "content": "<sat>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "26": {
212
+ "content": "<ta>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "27": {
220
+ "content": "<te>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "28": {
228
+ "content": "<ur>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ }
235
+ },
236
+ "clean_up_tokenization_spaces": false,
237
+ "cls_token": "[CLS]",
238
+ "extra_special_tokens": {},
239
+ "mask_token": "[MASK]",
240
+ "model_max_length": 1000000000000000019884624838656,
241
+ "pad_token": "[PAD]",
242
+ "sep_token": "[SEP]",
243
+ "tokenizer_class": "PreTrainedTokenizerFast",
244
+ "unk_token": "[UNK]"
245
+ }
training_info.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name": "ai4bharat/IndicBERTv2-MLM-only",
3
+ "output_dir": "./pii_model_indicv2",
4
+ "num_labels": 63,
5
+ "training_loss": 0.32986291919814215,
6
+ "val_precision": 0.9559953881629516,
7
+ "val_recall": 0.9563629373317954,
8
+ "val_f1": 0.9561791274264847,
9
+ "test_precision": 0.9462447579107892,
10
+ "test_recall": 0.9529660203493953,
11
+ "test_f1": 0.9495934959349593,
12
+ "train_samples": 15328,
13
+ "val_samples": 1916,
14
+ "test_samples": 1917,
15
+ "epochs": 10,
16
+ "learning_rate": 2e-05
17
+ }