Upload fine-tuned model
Browse files- config.json +268 -0
- merges.txt +0 -0
- special_tokens_map.json +51 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +60 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,268 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "lakshyakh93/deberta_finetuned_pii",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"id2label": {
|
11 |
+
"0": "B-PREFIX",
|
12 |
+
"1": "I-PREFIX",
|
13 |
+
"2": "B-FIRSTNAME",
|
14 |
+
"3": "I-FIRSTNAME",
|
15 |
+
"4": "B-MIDDLENAME",
|
16 |
+
"5": "B-LASTNAME",
|
17 |
+
"6": "I-LASTNAME",
|
18 |
+
"7": "O",
|
19 |
+
"8": "B-JOBDESCRIPTOR",
|
20 |
+
"9": "B-JOBTITLE",
|
21 |
+
"10": "I-JOBTITLE",
|
22 |
+
"11": "B-COMPANY_NAME",
|
23 |
+
"12": "I-COMPANY_NAME",
|
24 |
+
"13": "B-JOBAREA",
|
25 |
+
"14": "B-EMAIL",
|
26 |
+
"15": "I-EMAIL",
|
27 |
+
"16": "B-TIME",
|
28 |
+
"17": "I-TIME",
|
29 |
+
"18": "B-DATE",
|
30 |
+
"19": "I-DATE",
|
31 |
+
"20": "B-URL",
|
32 |
+
"21": "I-URL",
|
33 |
+
"22": "B-BITCOINADDRESS",
|
34 |
+
"23": "I-BITCOINADDRESS",
|
35 |
+
"24": "B-ETHEREUMADDRESS",
|
36 |
+
"25": "I-ETHEREUMADDRESS",
|
37 |
+
"26": "B-ACCOUNTNAME",
|
38 |
+
"27": "I-ACCOUNTNAME",
|
39 |
+
"28": "B-IBAN",
|
40 |
+
"29": "I-IBAN",
|
41 |
+
"30": "B-ACCOUNTNUMBER",
|
42 |
+
"31": "I-ACCOUNTNUMBER",
|
43 |
+
"32": "B-BIC",
|
44 |
+
"33": "I-BIC",
|
45 |
+
"34": "B-IPV4",
|
46 |
+
"35": "I-IPV4",
|
47 |
+
"36": "B-STREETADDRESS",
|
48 |
+
"37": "I-STREETADDRESS",
|
49 |
+
"38": "B-CITY",
|
50 |
+
"39": "I-CITY",
|
51 |
+
"40": "B-ZIPCODE",
|
52 |
+
"41": "I-ZIPCODE",
|
53 |
+
"42": "B-USERNAME",
|
54 |
+
"43": "I-USERNAME",
|
55 |
+
"44": "B-IPV6",
|
56 |
+
"45": "I-IPV6",
|
57 |
+
"46": "B-CREDITCARDNUMBER",
|
58 |
+
"47": "I-CREDITCARDNUMBER",
|
59 |
+
"48": "B-VEHICLEVIN",
|
60 |
+
"49": "I-VEHICLEVIN",
|
61 |
+
"50": "B-SUFFIX",
|
62 |
+
"51": "I-SUFFIX",
|
63 |
+
"52": "B-AMOUNT",
|
64 |
+
"53": "I-AMOUNT",
|
65 |
+
"54": "B-CURRENCY",
|
66 |
+
"55": "I-CURRENCY",
|
67 |
+
"56": "B-PASSWORD",
|
68 |
+
"57": "I-PASSWORD",
|
69 |
+
"58": "B-JOBTYPE",
|
70 |
+
"59": "B-STATE",
|
71 |
+
"60": "B-BUILDINGNUMBER",
|
72 |
+
"61": "I-BUILDINGNUMBER",
|
73 |
+
"62": "B-VEHICLEVRM",
|
74 |
+
"63": "I-VEHICLEVRM",
|
75 |
+
"64": "B-PHONEIMEI",
|
76 |
+
"65": "I-PHONEIMEI",
|
77 |
+
"66": "I-JOBAREA",
|
78 |
+
"67": "I-STATE",
|
79 |
+
"68": "B-COUNTY",
|
80 |
+
"69": "B-CURRENCYNAME",
|
81 |
+
"70": "I-CURRENCYNAME",
|
82 |
+
"71": "B-CURRENCYSYMBOL",
|
83 |
+
"72": "B-MASKEDNUMBER",
|
84 |
+
"73": "I-MASKEDNUMBER",
|
85 |
+
"74": "B-PHONE_NUMBER",
|
86 |
+
"75": "I-PHONE_NUMBER",
|
87 |
+
"76": "B-SECONDARYADDRESS",
|
88 |
+
"77": "I-SECONDARYADDRESS",
|
89 |
+
"78": "B-SSN",
|
90 |
+
"79": "I-SSN",
|
91 |
+
"80": "B-CURRENCYCODE",
|
92 |
+
"81": "B-LITECOINADDRESS",
|
93 |
+
"82": "I-LITECOINADDRESS",
|
94 |
+
"83": "B-MAC",
|
95 |
+
"84": "I-MAC",
|
96 |
+
"85": "B-CREDITCARDISSUER",
|
97 |
+
"86": "I-CREDITCARDISSUER",
|
98 |
+
"87": "B-CREDITCARDCVV",
|
99 |
+
"88": "I-CREDITCARDCVV",
|
100 |
+
"89": "B-USERAGENT",
|
101 |
+
"90": "I-USERAGENT",
|
102 |
+
"91": "B-IP",
|
103 |
+
"92": "I-IP",
|
104 |
+
"93": "B-SEX",
|
105 |
+
"94": "B-STREET",
|
106 |
+
"95": "I-STREET",
|
107 |
+
"96": "B-PIN",
|
108 |
+
"97": "I-PIN",
|
109 |
+
"98": "I-JOBTYPE",
|
110 |
+
"99": "I-MIDDLENAME",
|
111 |
+
"100": "I-CURRENCYCODE",
|
112 |
+
"101": "I-CURRENCYSYMBOL",
|
113 |
+
"102": "B-FULLNAME",
|
114 |
+
"103": "I-FULLNAME",
|
115 |
+
"104": "B-NAME",
|
116 |
+
"105": "I-NAME",
|
117 |
+
"106": "B-GENDER",
|
118 |
+
"107": "B-NUMBER",
|
119 |
+
"108": "I-NUMBER",
|
120 |
+
"109": "I-GENDER",
|
121 |
+
"110": "B-NEARBYGPSCOORDINATE",
|
122 |
+
"111": "I-NEARBYGPSCOORDINATE",
|
123 |
+
"112": "B-DISPLAYNAME",
|
124 |
+
"113": "I-DISPLAYNAME",
|
125 |
+
"114": "B-SEXTYPE",
|
126 |
+
"115": "B-ORDINALDIRECTION"
|
127 |
+
},
|
128 |
+
"initializer_range": 0.02,
|
129 |
+
"intermediate_size": 3072,
|
130 |
+
"label2id": {
|
131 |
+
"B-ACCOUNTNAME": 26,
|
132 |
+
"B-ACCOUNTNUMBER": 30,
|
133 |
+
"B-AMOUNT": 52,
|
134 |
+
"B-BIC": 32,
|
135 |
+
"B-BITCOINADDRESS": 22,
|
136 |
+
"B-BUILDINGNUMBER": 60,
|
137 |
+
"B-CITY": 38,
|
138 |
+
"B-COMPANY_NAME": 11,
|
139 |
+
"B-COUNTY": 68,
|
140 |
+
"B-CREDITCARDCVV": 87,
|
141 |
+
"B-CREDITCARDISSUER": 85,
|
142 |
+
"B-CREDITCARDNUMBER": 46,
|
143 |
+
"B-CURRENCY": 54,
|
144 |
+
"B-CURRENCYCODE": 80,
|
145 |
+
"B-CURRENCYNAME": 69,
|
146 |
+
"B-CURRENCYSYMBOL": 71,
|
147 |
+
"B-DATE": 18,
|
148 |
+
"B-DISPLAYNAME": 112,
|
149 |
+
"B-EMAIL": 14,
|
150 |
+
"B-ETHEREUMADDRESS": 24,
|
151 |
+
"B-FIRSTNAME": 2,
|
152 |
+
"B-FULLNAME": 102,
|
153 |
+
"B-GENDER": 106,
|
154 |
+
"B-IBAN": 28,
|
155 |
+
"B-IP": 91,
|
156 |
+
"B-IPV4": 34,
|
157 |
+
"B-IPV6": 44,
|
158 |
+
"B-JOBAREA": 13,
|
159 |
+
"B-JOBDESCRIPTOR": 8,
|
160 |
+
"B-JOBTITLE": 9,
|
161 |
+
"B-JOBTYPE": 58,
|
162 |
+
"B-LASTNAME": 5,
|
163 |
+
"B-LITECOINADDRESS": 81,
|
164 |
+
"B-MAC": 83,
|
165 |
+
"B-MASKEDNUMBER": 72,
|
166 |
+
"B-MIDDLENAME": 4,
|
167 |
+
"B-NAME": 104,
|
168 |
+
"B-NEARBYGPSCOORDINATE": 110,
|
169 |
+
"B-NUMBER": 107,
|
170 |
+
"B-ORDINALDIRECTION": 115,
|
171 |
+
"B-PASSWORD": 56,
|
172 |
+
"B-PHONEIMEI": 64,
|
173 |
+
"B-PHONE_NUMBER": 74,
|
174 |
+
"B-PIN": 96,
|
175 |
+
"B-PREFIX": 0,
|
176 |
+
"B-SECONDARYADDRESS": 76,
|
177 |
+
"B-SEX": 93,
|
178 |
+
"B-SEXTYPE": 114,
|
179 |
+
"B-SSN": 78,
|
180 |
+
"B-STATE": 59,
|
181 |
+
"B-STREET": 94,
|
182 |
+
"B-STREETADDRESS": 36,
|
183 |
+
"B-SUFFIX": 50,
|
184 |
+
"B-TIME": 16,
|
185 |
+
"B-URL": 20,
|
186 |
+
"B-USERAGENT": 89,
|
187 |
+
"B-USERNAME": 42,
|
188 |
+
"B-VEHICLEVIN": 48,
|
189 |
+
"B-VEHICLEVRM": 62,
|
190 |
+
"B-ZIPCODE": 40,
|
191 |
+
"I-ACCOUNTNAME": 27,
|
192 |
+
"I-ACCOUNTNUMBER": 31,
|
193 |
+
"I-AMOUNT": 53,
|
194 |
+
"I-BIC": 33,
|
195 |
+
"I-BITCOINADDRESS": 23,
|
196 |
+
"I-BUILDINGNUMBER": 61,
|
197 |
+
"I-CITY": 39,
|
198 |
+
"I-COMPANY_NAME": 12,
|
199 |
+
"I-CREDITCARDCVV": 88,
|
200 |
+
"I-CREDITCARDISSUER": 86,
|
201 |
+
"I-CREDITCARDNUMBER": 47,
|
202 |
+
"I-CURRENCY": 55,
|
203 |
+
"I-CURRENCYCODE": 100,
|
204 |
+
"I-CURRENCYNAME": 70,
|
205 |
+
"I-CURRENCYSYMBOL": 101,
|
206 |
+
"I-DATE": 19,
|
207 |
+
"I-DISPLAYNAME": 113,
|
208 |
+
"I-EMAIL": 15,
|
209 |
+
"I-ETHEREUMADDRESS": 25,
|
210 |
+
"I-FIRSTNAME": 3,
|
211 |
+
"I-FULLNAME": 103,
|
212 |
+
"I-GENDER": 109,
|
213 |
+
"I-IBAN": 29,
|
214 |
+
"I-IP": 92,
|
215 |
+
"I-IPV4": 35,
|
216 |
+
"I-IPV6": 45,
|
217 |
+
"I-JOBAREA": 66,
|
218 |
+
"I-JOBTITLE": 10,
|
219 |
+
"I-JOBTYPE": 98,
|
220 |
+
"I-LASTNAME": 6,
|
221 |
+
"I-LITECOINADDRESS": 82,
|
222 |
+
"I-MAC": 84,
|
223 |
+
"I-MASKEDNUMBER": 73,
|
224 |
+
"I-MIDDLENAME": 99,
|
225 |
+
"I-NAME": 105,
|
226 |
+
"I-NEARBYGPSCOORDINATE": 111,
|
227 |
+
"I-NUMBER": 108,
|
228 |
+
"I-PASSWORD": 57,
|
229 |
+
"I-PHONEIMEI": 65,
|
230 |
+
"I-PHONE_NUMBER": 75,
|
231 |
+
"I-PIN": 97,
|
232 |
+
"I-PREFIX": 1,
|
233 |
+
"I-SECONDARYADDRESS": 77,
|
234 |
+
"I-SSN": 79,
|
235 |
+
"I-STATE": 67,
|
236 |
+
"I-STREET": 95,
|
237 |
+
"I-STREETADDRESS": 37,
|
238 |
+
"I-SUFFIX": 51,
|
239 |
+
"I-TIME": 17,
|
240 |
+
"I-URL": 21,
|
241 |
+
"I-USERAGENT": 90,
|
242 |
+
"I-USERNAME": 43,
|
243 |
+
"I-VEHICLEVIN": 49,
|
244 |
+
"I-VEHICLEVRM": 63,
|
245 |
+
"I-ZIPCODE": 41,
|
246 |
+
"O": 7
|
247 |
+
},
|
248 |
+
"layer_norm_eps": 1e-07,
|
249 |
+
"max_position_embeddings": 512,
|
250 |
+
"max_relative_positions": -1,
|
251 |
+
"model_type": "deberta",
|
252 |
+
"num_attention_heads": 12,
|
253 |
+
"num_hidden_layers": 12,
|
254 |
+
"pad_token_id": 0,
|
255 |
+
"pooler_dropout": 0,
|
256 |
+
"pooler_hidden_act": "gelu",
|
257 |
+
"pooler_hidden_size": 768,
|
258 |
+
"pos_att_type": [
|
259 |
+
"c2p",
|
260 |
+
"p2c"
|
261 |
+
],
|
262 |
+
"position_biased_input": false,
|
263 |
+
"relative_attention": true,
|
264 |
+
"torch_dtype": "float32",
|
265 |
+
"transformers_version": "4.44.2",
|
266 |
+
"type_vocab_size": 0,
|
267 |
+
"vocab_size": 50265
|
268 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "[CLS]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "[SEP]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "[MASK]",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "[PAD]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "[SEP]",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "[UNK]",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87e4dee2313b2137aca7d9a59cd4166d3644682b78c818e4104e0c6859bb41bc
|
3 |
+
size 555049352
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": true,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "[PAD]",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "[CLS]",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "[SEP]",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "[UNK]",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"50264": {
|
38 |
+
"content": "[MASK]",
|
39 |
+
"lstrip": true,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
}
|
45 |
+
},
|
46 |
+
"additional_special_tokens": [],
|
47 |
+
"bos_token": "[CLS]",
|
48 |
+
"clean_up_tokenization_spaces": true,
|
49 |
+
"cls_token": "[CLS]",
|
50 |
+
"do_lower_case": false,
|
51 |
+
"eos_token": "[SEP]",
|
52 |
+
"errors": "replace",
|
53 |
+
"mask_token": "[MASK]",
|
54 |
+
"model_max_length": 512,
|
55 |
+
"pad_token": "[PAD]",
|
56 |
+
"sep_token": "[SEP]",
|
57 |
+
"tokenizer_class": "DebertaTokenizer",
|
58 |
+
"unk_token": "[UNK]",
|
59 |
+
"vocab_type": "gpt2"
|
60 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|