Hugging Face's logo

DeepMount00
/
Italian_NER_XXL_v2

Token Classification
Safetensors
Italian
English
bert
legal
finance
medical
privacy
named-entity-recognition
Model card Files Community
DeepMount00 commited on
Commit
5e2024f
·
verified ·
1 Parent(s): 3f81c3a

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +262 -0
  2. id2tag.json +119 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +7 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +59 -0
  7. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "O",
12
+ "1": "B-AVV_NOTAIO",
13
+ "2": "B-BANCA",
14
+ "3": "B-BIC",
15
+ "4": "B-BRAND",
16
+ "5": "B-CARTELLA_CLINICA",
17
+ "6": "B-CODICE_FISCALE",
18
+ "7": "B-CODICE_POSTALE",
19
+ "8": "B-COGNOME",
20
+ "9": "B-CVV",
21
+ "10": "B-DATA",
22
+ "11": "B-DATA_MORTE",
23
+ "12": "B-DATA_NASCITA",
24
+ "13": "B-DOSAGGIO",
25
+ "14": "B-DURATION",
26
+ "15": "B-EMAIL",
27
+ "16": "B-ETA",
28
+ "17": "B-FOGLIO",
29
+ "18": "B-FORM",
30
+ "19": "B-FREQUENZA",
31
+ "20": "B-IBAN",
32
+ "21": "B-IMEI",
33
+ "22": "B-IMPORTO",
34
+ "23": "B-INDIRIZZO",
35
+ "24": "B-IP",
36
+ "25": "B-IPV6_1",
37
+ "26": "B-LEGGE",
38
+ "27": "B-LUOGO",
39
+ "28": "B-MAC",
40
+ "29": "B-MALATTIA",
41
+ "30": "B-MAPPALE",
42
+ "31": "B-MEDICINA",
43
+ "32": "B-NOME",
44
+ "33": "B-NUMERO_CARTA",
45
+ "34": "B-NUMERO_CONTO",
46
+ "35": "B-NUMERO_DOCUMENTO",
47
+ "36": "B-NUMERO_TELEFONO",
48
+ "37": "B-NUM_ASSEGNO_BANCARIO",
49
+ "38": "B-N_LICENZA",
50
+ "39": "B-N_SENTENZA",
51
+ "40": "B-ORARIO",
52
+ "41": "B-PARTICELLA",
53
+ "42": "B-PASSWORD",
54
+ "43": "B-PIN",
55
+ "44": "B-PROFESSIONE",
56
+ "45": "B-P_IVA",
57
+ "46": "B-RAGIONE_SOCIALE",
58
+ "47": "B-REGIME_PATRIMONIALE",
59
+ "48": "B-STATO",
60
+ "49": "B-STATO_CIVILE",
61
+ "50": "B-STORIA_CLINICA",
62
+ "51": "B-STRENGTH",
63
+ "52": "B-SUBALTERNO",
64
+ "53": "B-TARGA_VEICOLO",
65
+ "54": "B-TASSO_MUTUO",
66
+ "55": "B-TRIBUNALE",
67
+ "56": "B-URL",
68
+ "57": "B-USER_AGENT",
69
+ "58": "B-VALUTA",
70
+ "59": "I-AVV_NOTAIO",
71
+ "60": "I-BANCA",
72
+ "61": "I-BIC",
73
+ "62": "I-BRAND",
74
+ "63": "I-CARTELLA_CLINICA",
75
+ "64": "I-CODICE_FISCALE",
76
+ "65": "I-CODICE_POSTALE",
77
+ "66": "I-COGNOME",
78
+ "67": "I-CVV",
79
+ "68": "I-DATA",
80
+ "69": "I-DATA_MORTE",
81
+ "70": "I-DATA_NASCITA",
82
+ "71": "I-DOSAGGIO",
83
+ "72": "I-DURATION",
84
+ "73": "I-EMAIL",
85
+ "74": "I-ETA",
86
+ "75": "I-FOGLIO",
87
+ "76": "I-FORM",
88
+ "77": "I-FREQUENZA",
89
+ "78": "I-IBAN",
90
+ "79": "I-IMEI",
91
+ "80": "I-IMPORTO",
92
+ "81": "I-INDIRIZZO",
93
+ "82": "I-IP",
94
+ "83": "I-IPV6_1",
95
+ "84": "I-LEGGE",
96
+ "85": "I-LUOGO",
97
+ "86": "I-MAC",
98
+ "87": "I-MALATTIA",
99
+ "88": "I-MAPPALE",
100
+ "89": "I-MEDICINA",
101
+ "90": "I-NOME",
102
+ "91": "I-NUMERO_CARTA",
103
+ "92": "I-NUMERO_CONTO",
104
+ "93": "I-NUMERO_DOCUMENTO",
105
+ "94": "I-NUMERO_TELEFONO",
106
+ "95": "I-NUM_ASSEGNO_BANCARIO",
107
+ "96": "I-N_LICENZA",
108
+ "97": "I-N_SENTENZA",
109
+ "98": "I-ORARIO",
110
+ "99": "I-PARTICELLA",
111
+ "100": "I-PASSWORD",
112
+ "101": "I-PIN",
113
+ "102": "I-PROFESSIONE",
114
+ "103": "I-P_IVA",
115
+ "104": "I-RAGIONE_SOCIALE",
116
+ "105": "I-REGIME_PATRIMONIALE",
117
+ "106": "I-STATO",
118
+ "107": "I-STATO_CIVILE",
119
+ "108": "I-STORIA_CLINICA",
120
+ "109": "I-STRENGTH",
121
+ "110": "I-SUBALTERNO",
122
+ "111": "I-TARGA_VEICOLO",
123
+ "112": "I-TASSO_MUTUO",
124
+ "113": "I-TRIBUNALE",
125
+ "114": "I-URL",
126
+ "115": "I-USER_AGENT",
127
+ "116": "I-VALUTA"
128
+ },
129
+ "initializer_range": 0.02,
130
+ "intermediate_size": 3072,
131
+ "label2id": {
132
+ "B-AVV_NOTAIO": 1,
133
+ "B-BANCA": 2,
134
+ "B-BIC": 3,
135
+ "B-BRAND": 4,
136
+ "B-CARTELLA_CLINICA": 5,
137
+ "B-CODICE_FISCALE": 6,
138
+ "B-CODICE_POSTALE": 7,
139
+ "B-COGNOME": 8,
140
+ "B-CVV": 9,
141
+ "B-DATA": 10,
142
+ "B-DATA_MORTE": 11,
143
+ "B-DATA_NASCITA": 12,
144
+ "B-DOSAGGIO": 13,
145
+ "B-DURATION": 14,
146
+ "B-EMAIL": 15,
147
+ "B-ETA": 16,
148
+ "B-FOGLIO": 17,
149
+ "B-FORM": 18,
150
+ "B-FREQUENZA": 19,
151
+ "B-IBAN": 20,
152
+ "B-IMEI": 21,
153
+ "B-IMPORTO": 22,
154
+ "B-INDIRIZZO": 23,
155
+ "B-IP": 24,
156
+ "B-IPV6_1": 25,
157
+ "B-LEGGE": 26,
158
+ "B-LUOGO": 27,
159
+ "B-MAC": 28,
160
+ "B-MALATTIA": 29,
161
+ "B-MAPPALE": 30,
162
+ "B-MEDICINA": 31,
163
+ "B-NOME": 32,
164
+ "B-NUMERO_CARTA": 33,
165
+ "B-NUMERO_CONTO": 34,
166
+ "B-NUMERO_DOCUMENTO": 35,
167
+ "B-NUMERO_TELEFONO": 36,
168
+ "B-NUM_ASSEGNO_BANCARIO": 37,
169
+ "B-N_LICENZA": 38,
170
+ "B-N_SENTENZA": 39,
171
+ "B-ORARIO": 40,
172
+ "B-PARTICELLA": 41,
173
+ "B-PASSWORD": 42,
174
+ "B-PIN": 43,
175
+ "B-PROFESSIONE": 44,
176
+ "B-P_IVA": 45,
177
+ "B-RAGIONE_SOCIALE": 46,
178
+ "B-REGIME_PATRIMONIALE": 47,
179
+ "B-STATO": 48,
180
+ "B-STATO_CIVILE": 49,
181
+ "B-STORIA_CLINICA": 50,
182
+ "B-STRENGTH": 51,
183
+ "B-SUBALTERNO": 52,
184
+ "B-TARGA_VEICOLO": 53,
185
+ "B-TASSO_MUTUO": 54,
186
+ "B-TRIBUNALE": 55,
187
+ "B-URL": 56,
188
+ "B-USER_AGENT": 57,
189
+ "B-VALUTA": 58,
190
+ "I-AVV_NOTAIO": 59,
191
+ "I-BANCA": 60,
192
+ "I-BIC": 61,
193
+ "I-BRAND": 62,
194
+ "I-CARTELLA_CLINICA": 63,
195
+ "I-CODICE_FISCALE": 64,
196
+ "I-CODICE_POSTALE": 65,
197
+ "I-COGNOME": 66,
198
+ "I-CVV": 67,
199
+ "I-DATA": 68,
200
+ "I-DATA_MORTE": 69,
201
+ "I-DATA_NASCITA": 70,
202
+ "I-DOSAGGIO": 71,
203
+ "I-DURATION": 72,
204
+ "I-EMAIL": 73,
205
+ "I-ETA": 74,
206
+ "I-FOGLIO": 75,
207
+ "I-FORM": 76,
208
+ "I-FREQUENZA": 77,
209
+ "I-IBAN": 78,
210
+ "I-IMEI": 79,
211
+ "I-IMPORTO": 80,
212
+ "I-INDIRIZZO": 81,
213
+ "I-IP": 82,
214
+ "I-IPV6_1": 83,
215
+ "I-LEGGE": 84,
216
+ "I-LUOGO": 85,
217
+ "I-MAC": 86,
218
+ "I-MALATTIA": 87,
219
+ "I-MAPPALE": 88,
220
+ "I-MEDICINA": 89,
221
+ "I-NOME": 90,
222
+ "I-NUMERO_CARTA": 91,
223
+ "I-NUMERO_CONTO": 92,
224
+ "I-NUMERO_DOCUMENTO": 93,
225
+ "I-NUMERO_TELEFONO": 94,
226
+ "I-NUM_ASSEGNO_BANCARIO": 95,
227
+ "I-N_LICENZA": 96,
228
+ "I-N_SENTENZA": 97,
229
+ "I-ORARIO": 98,
230
+ "I-PARTICELLA": 99,
231
+ "I-PASSWORD": 100,
232
+ "I-PIN": 101,
233
+ "I-PROFESSIONE": 102,
234
+ "I-P_IVA": 103,
235
+ "I-RAGIONE_SOCIALE": 104,
236
+ "I-REGIME_PATRIMONIALE": 105,
237
+ "I-STATO": 106,
238
+ "I-STATO_CIVILE": 107,
239
+ "I-STORIA_CLINICA": 108,
240
+ "I-STRENGTH": 109,
241
+ "I-SUBALTERNO": 110,
242
+ "I-TARGA_VEICOLO": 111,
243
+ "I-TASSO_MUTUO": 112,
244
+ "I-TRIBUNALE": 113,
245
+ "I-URL": 114,
246
+ "I-USER_AGENT": 115,
247
+ "I-VALUTA": 116,
248
+ "O": 0
249
+ },
250
+ "layer_norm_eps": 1e-12,
251
+ "max_position_embeddings": 512,
252
+ "model_type": "bert",
253
+ "num_attention_heads": 12,
254
+ "num_hidden_layers": 12,
255
+ "pad_token_id": 0,
256
+ "position_embedding_type": "absolute",
257
+ "torch_dtype": "float32",
258
+ "transformers_version": "4.51.3",
259
+ "type_vocab_size": 2,
260
+ "use_cache": true,
261
+ "vocab_size": 32102
262
+ }
id2tag.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "0": "O",
3
+ "1": "B-AVV_NOTAIO",
4
+ "2": "B-BANCA",
5
+ "3": "B-BIC",
6
+ "4": "B-BRAND",
7
+ "5": "B-CARTELLA_CLINICA",
8
+ "6": "B-CODICE_FISCALE",
9
+ "7": "B-CODICE_POSTALE",
10
+ "8": "B-COGNOME",
11
+ "9": "B-CVV",
12
+ "10": "B-DATA",
13
+ "11": "B-DATA_MORTE",
14
+ "12": "B-DATA_NASCITA",
15
+ "13": "B-DOSAGGIO",
16
+ "14": "B-DURATION",
17
+ "15": "B-EMAIL",
18
+ "16": "B-ETA",
19
+ "17": "B-FOGLIO",
20
+ "18": "B-FORM",
21
+ "19": "B-FREQUENZA",
22
+ "20": "B-IBAN",
23
+ "21": "B-IMEI",
24
+ "22": "B-IMPORTO",
25
+ "23": "B-INDIRIZZO",
26
+ "24": "B-IP",
27
+ "25": "B-IPV6_1",
28
+ "26": "B-LEGGE",
29
+ "27": "B-LUOGO",
30
+ "28": "B-MAC",
31
+ "29": "B-MALATTIA",
32
+ "30": "B-MAPPALE",
33
+ "31": "B-MEDICINA",
34
+ "32": "B-NOME",
35
+ "33": "B-NUMERO_CARTA",
36
+ "34": "B-NUMERO_CONTO",
37
+ "35": "B-NUMERO_DOCUMENTO",
38
+ "36": "B-NUMERO_TELEFONO",
39
+ "37": "B-NUM_ASSEGNO_BANCARIO",
40
+ "38": "B-N_LICENZA",
41
+ "39": "B-N_SENTENZA",
42
+ "40": "B-ORARIO",
43
+ "41": "B-PARTICELLA",
44
+ "42": "B-PASSWORD",
45
+ "43": "B-PIN",
46
+ "44": "B-PROFESSIONE",
47
+ "45": "B-P_IVA",
48
+ "46": "B-RAGIONE_SOCIALE",
49
+ "47": "B-REGIME_PATRIMONIALE",
50
+ "48": "B-STATO",
51
+ "49": "B-STATO_CIVILE",
52
+ "50": "B-STORIA_CLINICA",
53
+ "51": "B-STRENGTH",
54
+ "52": "B-SUBALTERNO",
55
+ "53": "B-TARGA_VEICOLO",
56
+ "54": "B-TASSO_MUTUO",
57
+ "55": "B-TRIBUNALE",
58
+ "56": "B-URL",
59
+ "57": "B-USER_AGENT",
60
+ "58": "B-VALUTA",
61
+ "59": "I-AVV_NOTAIO",
62
+ "60": "I-BANCA",
63
+ "61": "I-BIC",
64
+ "62": "I-BRAND",
65
+ "63": "I-CARTELLA_CLINICA",
66
+ "64": "I-CODICE_FISCALE",
67
+ "65": "I-CODICE_POSTALE",
68
+ "66": "I-COGNOME",
69
+ "67": "I-CVV",
70
+ "68": "I-DATA",
71
+ "69": "I-DATA_MORTE",
72
+ "70": "I-DATA_NASCITA",
73
+ "71": "I-DOSAGGIO",
74
+ "72": "I-DURATION",
75
+ "73": "I-EMAIL",
76
+ "74": "I-ETA",
77
+ "75": "I-FOGLIO",
78
+ "76": "I-FORM",
79
+ "77": "I-FREQUENZA",
80
+ "78": "I-IBAN",
81
+ "79": "I-IMEI",
82
+ "80": "I-IMPORTO",
83
+ "81": "I-INDIRIZZO",
84
+ "82": "I-IP",
85
+ "83": "I-IPV6_1",
86
+ "84": "I-LEGGE",
87
+ "85": "I-LUOGO",
88
+ "86": "I-MAC",
89
+ "87": "I-MALATTIA",
90
+ "88": "I-MAPPALE",
91
+ "89": "I-MEDICINA",
92
+ "90": "I-NOME",
93
+ "91": "I-NUMERO_CARTA",
94
+ "92": "I-NUMERO_CONTO",
95
+ "93": "I-NUMERO_DOCUMENTO",
96
+ "94": "I-NUMERO_TELEFONO",
97
+ "95": "I-NUM_ASSEGNO_BANCARIO",
98
+ "96": "I-N_LICENZA",
99
+ "97": "I-N_SENTENZA",
100
+ "98": "I-ORARIO",
101
+ "99": "I-PARTICELLA",
102
+ "100": "I-PASSWORD",
103
+ "101": "I-PIN",
104
+ "102": "I-PROFESSIONE",
105
+ "103": "I-P_IVA",
106
+ "104": "I-RAGIONE_SOCIALE",
107
+ "105": "I-REGIME_PATRIMONIALE",
108
+ "106": "I-STATO",
109
+ "107": "I-STATO_CIVILE",
110
+ "108": "I-STORIA_CLINICA",
111
+ "109": "I-STRENGTH",
112
+ "110": "I-SUBALTERNO",
113
+ "111": "I-TARGA_VEICOLO",
114
+ "112": "I-TASSO_MUTUO",
115
+ "113": "I-TRIBUNALE",
116
+ "114": "I-URL",
117
+ "115": "I-USER_AGENT",
118
+ "116": "I-VALUTA"
119
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c60cf8b8814bd71c31816a09996872417abc13a696dd52aa806b41693eaa40b
3
+ size 440803604
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "101": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "102": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "103": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "104": {
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": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_len": 512,
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff