pweidel commited on
Commit
30949b8
·
verified ·
1 Parent(s): bd26320

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers.js
3
+ base_model:
4
+ - pweidel/pii-bert-redactor
5
+ ---
6
+
7
+ # pii-bert-redactor (ONNX)
8
+
9
+ This is an ONNX version of [pweidel/pii-bert-redactor](https://huggingface.co/pweidel/pii-bert-redactor). It was automatically converted and uploaded using [this space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
config.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "pweidel/pii-bert-redactor",
4
+ "architectures": [
5
+ "BertForTokenClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "directionality": "bidi",
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "B-ACCOUNTNAME",
15
+ "1": "B-ACCOUNTNUMBER",
16
+ "2": "B-AGE",
17
+ "3": "B-AMOUNT",
18
+ "4": "B-BIC",
19
+ "5": "B-BITCOINADDRESS",
20
+ "6": "B-BUILDINGNUMBER",
21
+ "7": "B-CITY",
22
+ "8": "B-COMPANYNAME",
23
+ "9": "B-COUNTY",
24
+ "10": "B-CREDITCARDCVV",
25
+ "11": "B-CREDITCARDISSUER",
26
+ "12": "B-CREDITCARDNUMBER",
27
+ "13": "B-CURRENCY",
28
+ "14": "B-CURRENCYCODE",
29
+ "15": "B-CURRENCYNAME",
30
+ "16": "B-CURRENCYSYMBOL",
31
+ "17": "B-DATE",
32
+ "18": "B-DOB",
33
+ "19": "B-EMAIL",
34
+ "20": "B-ETHEREUMADDRESS",
35
+ "21": "B-EYECOLOR",
36
+ "22": "B-FIRSTNAME",
37
+ "23": "B-GENDER",
38
+ "24": "B-HEIGHT",
39
+ "25": "B-IBAN",
40
+ "26": "B-IP",
41
+ "27": "B-IPV4",
42
+ "28": "B-IPV6",
43
+ "29": "B-JOBAREA",
44
+ "30": "B-JOBTITLE",
45
+ "31": "B-JOBTYPE",
46
+ "32": "B-LASTNAME",
47
+ "33": "B-LITECOINADDRESS",
48
+ "34": "B-MAC",
49
+ "35": "B-MASKEDNUMBER",
50
+ "36": "B-MIDDLENAME",
51
+ "37": "B-NEARBYGPSCOORDINATE",
52
+ "38": "B-ORDINALDIRECTION",
53
+ "39": "B-PASSWORD",
54
+ "40": "B-PHONEIMEI",
55
+ "41": "B-PHONENUMBER",
56
+ "42": "B-PIN",
57
+ "43": "B-PREFIX",
58
+ "44": "B-SECONDARYADDRESS",
59
+ "45": "B-SEX",
60
+ "46": "B-SSN",
61
+ "47": "B-STATE",
62
+ "48": "B-STREET",
63
+ "49": "B-TIME",
64
+ "50": "B-URL",
65
+ "51": "B-USERAGENT",
66
+ "52": "B-USERNAME",
67
+ "53": "B-VEHICLEVIN",
68
+ "54": "B-VEHICLEVRM",
69
+ "55": "B-ZIPCODE",
70
+ "56": "I-ACCOUNTNAME",
71
+ "57": "I-ACCOUNTNUMBER",
72
+ "58": "I-AGE",
73
+ "59": "I-AMOUNT",
74
+ "60": "I-BIC",
75
+ "61": "I-BITCOINADDRESS",
76
+ "62": "I-BUILDINGNUMBER",
77
+ "63": "I-CITY",
78
+ "64": "I-COMPANYNAME",
79
+ "65": "I-COUNTY",
80
+ "66": "I-CREDITCARDCVV",
81
+ "67": "I-CREDITCARDISSUER",
82
+ "68": "I-CREDITCARDNUMBER",
83
+ "69": "I-CURRENCY",
84
+ "70": "I-CURRENCYCODE",
85
+ "71": "I-CURRENCYNAME",
86
+ "72": "I-CURRENCYSYMBOL",
87
+ "73": "I-DATE",
88
+ "74": "I-DOB",
89
+ "75": "I-EMAIL",
90
+ "76": "I-ETHEREUMADDRESS",
91
+ "77": "I-EYECOLOR",
92
+ "78": "I-FIRSTNAME",
93
+ "79": "I-GENDER",
94
+ "80": "I-HEIGHT",
95
+ "81": "I-IBAN",
96
+ "82": "I-IP",
97
+ "83": "I-IPV4",
98
+ "84": "I-IPV6",
99
+ "85": "I-JOBAREA",
100
+ "86": "I-JOBTITLE",
101
+ "87": "I-JOBTYPE",
102
+ "88": "I-LASTNAME",
103
+ "89": "I-LITECOINADDRESS",
104
+ "90": "I-MAC",
105
+ "91": "I-MASKEDNUMBER",
106
+ "92": "I-MIDDLENAME",
107
+ "93": "I-NEARBYGPSCOORDINATE",
108
+ "94": "I-ORDINALDIRECTION",
109
+ "95": "I-PASSWORD",
110
+ "96": "I-PHONEIMEI",
111
+ "97": "I-PHONENUMBER",
112
+ "98": "I-PIN",
113
+ "99": "I-PREFIX",
114
+ "100": "I-SECONDARYADDRESS",
115
+ "101": "I-SEX",
116
+ "102": "I-SSN",
117
+ "103": "I-STATE",
118
+ "104": "I-STREET",
119
+ "105": "I-TIME",
120
+ "106": "I-URL",
121
+ "107": "I-USERAGENT",
122
+ "108": "I-USERNAME",
123
+ "109": "I-VEHICLEVIN",
124
+ "110": "I-VEHICLEVRM",
125
+ "111": "I-ZIPCODE",
126
+ "112": "O"
127
+ },
128
+ "initializer_range": 0.02,
129
+ "intermediate_size": 3072,
130
+ "label2id": {
131
+ "B-ACCOUNTNAME": 0,
132
+ "B-ACCOUNTNUMBER": 1,
133
+ "B-AGE": 2,
134
+ "B-AMOUNT": 3,
135
+ "B-BIC": 4,
136
+ "B-BITCOINADDRESS": 5,
137
+ "B-BUILDINGNUMBER": 6,
138
+ "B-CITY": 7,
139
+ "B-COMPANYNAME": 8,
140
+ "B-COUNTY": 9,
141
+ "B-CREDITCARDCVV": 10,
142
+ "B-CREDITCARDISSUER": 11,
143
+ "B-CREDITCARDNUMBER": 12,
144
+ "B-CURRENCY": 13,
145
+ "B-CURRENCYCODE": 14,
146
+ "B-CURRENCYNAME": 15,
147
+ "B-CURRENCYSYMBOL": 16,
148
+ "B-DATE": 17,
149
+ "B-DOB": 18,
150
+ "B-EMAIL": 19,
151
+ "B-ETHEREUMADDRESS": 20,
152
+ "B-EYECOLOR": 21,
153
+ "B-FIRSTNAME": 22,
154
+ "B-GENDER": 23,
155
+ "B-HEIGHT": 24,
156
+ "B-IBAN": 25,
157
+ "B-IP": 26,
158
+ "B-IPV4": 27,
159
+ "B-IPV6": 28,
160
+ "B-JOBAREA": 29,
161
+ "B-JOBTITLE": 30,
162
+ "B-JOBTYPE": 31,
163
+ "B-LASTNAME": 32,
164
+ "B-LITECOINADDRESS": 33,
165
+ "B-MAC": 34,
166
+ "B-MASKEDNUMBER": 35,
167
+ "B-MIDDLENAME": 36,
168
+ "B-NEARBYGPSCOORDINATE": 37,
169
+ "B-ORDINALDIRECTION": 38,
170
+ "B-PASSWORD": 39,
171
+ "B-PHONEIMEI": 40,
172
+ "B-PHONENUMBER": 41,
173
+ "B-PIN": 42,
174
+ "B-PREFIX": 43,
175
+ "B-SECONDARYADDRESS": 44,
176
+ "B-SEX": 45,
177
+ "B-SSN": 46,
178
+ "B-STATE": 47,
179
+ "B-STREET": 48,
180
+ "B-TIME": 49,
181
+ "B-URL": 50,
182
+ "B-USERAGENT": 51,
183
+ "B-USERNAME": 52,
184
+ "B-VEHICLEVIN": 53,
185
+ "B-VEHICLEVRM": 54,
186
+ "B-ZIPCODE": 55,
187
+ "I-ACCOUNTNAME": 56,
188
+ "I-ACCOUNTNUMBER": 57,
189
+ "I-AGE": 58,
190
+ "I-AMOUNT": 59,
191
+ "I-BIC": 60,
192
+ "I-BITCOINADDRESS": 61,
193
+ "I-BUILDINGNUMBER": 62,
194
+ "I-CITY": 63,
195
+ "I-COMPANYNAME": 64,
196
+ "I-COUNTY": 65,
197
+ "I-CREDITCARDCVV": 66,
198
+ "I-CREDITCARDISSUER": 67,
199
+ "I-CREDITCARDNUMBER": 68,
200
+ "I-CURRENCY": 69,
201
+ "I-CURRENCYCODE": 70,
202
+ "I-CURRENCYNAME": 71,
203
+ "I-CURRENCYSYMBOL": 72,
204
+ "I-DATE": 73,
205
+ "I-DOB": 74,
206
+ "I-EMAIL": 75,
207
+ "I-ETHEREUMADDRESS": 76,
208
+ "I-EYECOLOR": 77,
209
+ "I-FIRSTNAME": 78,
210
+ "I-GENDER": 79,
211
+ "I-HEIGHT": 80,
212
+ "I-IBAN": 81,
213
+ "I-IP": 82,
214
+ "I-IPV4": 83,
215
+ "I-IPV6": 84,
216
+ "I-JOBAREA": 85,
217
+ "I-JOBTITLE": 86,
218
+ "I-JOBTYPE": 87,
219
+ "I-LASTNAME": 88,
220
+ "I-LITECOINADDRESS": 89,
221
+ "I-MAC": 90,
222
+ "I-MASKEDNUMBER": 91,
223
+ "I-MIDDLENAME": 92,
224
+ "I-NEARBYGPSCOORDINATE": 93,
225
+ "I-ORDINALDIRECTION": 94,
226
+ "I-PASSWORD": 95,
227
+ "I-PHONEIMEI": 96,
228
+ "I-PHONENUMBER": 97,
229
+ "I-PIN": 98,
230
+ "I-PREFIX": 99,
231
+ "I-SECONDARYADDRESS": 100,
232
+ "I-SEX": 101,
233
+ "I-SSN": 102,
234
+ "I-STATE": 103,
235
+ "I-STREET": 104,
236
+ "I-TIME": 105,
237
+ "I-URL": 106,
238
+ "I-USERAGENT": 107,
239
+ "I-USERNAME": 108,
240
+ "I-VEHICLEVIN": 109,
241
+ "I-VEHICLEVRM": 110,
242
+ "I-ZIPCODE": 111,
243
+ "O": 112
244
+ },
245
+ "layer_norm_eps": 1e-12,
246
+ "max_position_embeddings": 512,
247
+ "model_type": "bert",
248
+ "num_attention_heads": 12,
249
+ "num_hidden_layers": 12,
250
+ "pad_token_id": 0,
251
+ "pooler_fc_size": 768,
252
+ "pooler_num_attention_heads": 12,
253
+ "pooler_num_fc_layers": 3,
254
+ "pooler_size_per_head": 128,
255
+ "pooler_type": "first_token_transform",
256
+ "position_embedding_type": "absolute",
257
+ "torch_dtype": "float32",
258
+ "transformers_version": "4.49.0",
259
+ "type_vocab_size": 2,
260
+ "use_cache": true,
261
+ "vocab_size": 119547
262
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c398a7fc4b45d197ae7c6a869700f8684942bf004eb49aedb20d43ecab734e44
3
+ size 709706778
onnx/model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d8269f765202e10c142adc605e3b309b1d2ed20b1e20ad1084f3539a795b747
3
+ size 417456936
onnx/model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06025d0d3fc60b43dd0744f1d6ad91cfd66945dacfd3d02141fd0abdbf0c1b9e
3
+ size 355007569
onnx/model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5b6ac478c15b5f2b190909e1298b624ae4ca9c95433243b24b51ec3f423f0a4
3
+ size 178532090
onnx/model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0924e2526911dfdc74f741ad794eb143615ce7bb82e15e0c40116c4826dc97e4
3
+ size 422770239
onnx/model_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7beddca57273bd61a87f658ad792f55d020e28b0653ba141afd30cc55c24d6d1
3
+ size 232800165
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5b6ac478c15b5f2b190909e1298b624ae4ca9c95433243b24b51ec3f423f0a4
3
+ size 178532090
onnx/model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95cbbda24efe30f3dfb715e0ec93d823cdfef6241925cb27cd7d505d2f7ed2a8
3
+ size 178532090
quantize_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "modes": [
3
+ "fp16",
4
+ "q8",
5
+ "int8",
6
+ "uint8",
7
+ "q4",
8
+ "q4f16",
9
+ "bnb4"
10
+ ],
11
+ "per_channel": true,
12
+ "reduce_range": true,
13
+ "block_size": null,
14
+ "is_symmetric": true,
15
+ "accuracy_level": null,
16
+ "quant_type": 1,
17
+ "op_block_list": null
18
+ }
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 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "max_length": 128,
50
+ "model_max_length": 512,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "[PAD]",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "[SEP]",
56
+ "stride": 0,
57
+ "strip_accents": null,
58
+ "tokenize_chinese_chars": true,
59
+ "tokenizer_class": "BertTokenizer",
60
+ "truncation_side": "right",
61
+ "truncation_strategy": "longest_first",
62
+ "unk_token": "[UNK]"
63
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff