Training done
Browse files- added_tokens.json +19 -11
- tokenizer.json +82 -10
- tokenizer_config.json +74 -10
added_tokens.json
CHANGED
|
@@ -1,20 +1,28 @@
|
|
| 1 |
{
|
| 2 |
-
"</s_Date Naissance>":
|
| 3 |
-
"</
|
| 4 |
-
"</s_Nationalite>": 57534,
|
| 5 |
"</s_Nom>": 57526,
|
| 6 |
-
"</s_Numero Carte>":
|
| 7 |
"</s_Prenoms>": 57528,
|
| 8 |
-
"</s_Sexe>":
|
| 9 |
-
"<
|
| 10 |
-
"<
|
| 11 |
-
"<
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
"<s_Nom>": 57525,
|
| 13 |
-
"<s_Numero Carte>":
|
| 14 |
"<s_Prenoms>": 57527,
|
| 15 |
-
"<s_Sexe>":
|
| 16 |
-
"<
|
|
|
|
| 17 |
"<s_iitcdip>": 57523,
|
|
|
|
|
|
|
| 18 |
"<s_synthdog>": 57524,
|
|
|
|
|
|
|
| 19 |
"<sep/>": 57522
|
| 20 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"</s_Date Naissance>": 57530,
|
| 3 |
+
"</s_Nationalite>": 57532,
|
|
|
|
| 4 |
"</s_Nom>": 57526,
|
| 5 |
+
"</s_Numero Carte>": 57534,
|
| 6 |
"</s_Prenoms>": 57528,
|
| 7 |
+
"</s_Sexe>": 57536,
|
| 8 |
+
"</s_address>": 57540,
|
| 9 |
+
"</s_issued_by>": 57546,
|
| 10 |
+
"</s_issued_on>": 57544,
|
| 11 |
+
"</s_type>": 57538,
|
| 12 |
+
"</s_valid_until>": 57542,
|
| 13 |
+
"<s_Date Naissance>": 57529,
|
| 14 |
+
"<s_Nationalite>": 57531,
|
| 15 |
"<s_Nom>": 57525,
|
| 16 |
+
"<s_Numero Carte>": 57533,
|
| 17 |
"<s_Prenoms>": 57527,
|
| 18 |
+
"<s_Sexe>": 57535,
|
| 19 |
+
"<s_address>": 57539,
|
| 20 |
+
"<s_id_card>": 57547,
|
| 21 |
"<s_iitcdip>": 57523,
|
| 22 |
+
"<s_issued_by>": 57545,
|
| 23 |
+
"<s_issued_on>": 57543,
|
| 24 |
"<s_synthdog>": 57524,
|
| 25 |
+
"<s_type>": 57537,
|
| 26 |
+
"<s_valid_until>": 57541,
|
| 27 |
"<sep/>": 57522
|
| 28 |
}
|
tokenizer.json
CHANGED
|
@@ -127,7 +127,7 @@
|
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"id": 57529,
|
| 130 |
-
"content": "<
|
| 131 |
"single_word": false,
|
| 132 |
"lstrip": false,
|
| 133 |
"rstrip": false,
|
|
@@ -136,7 +136,7 @@
|
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"id": 57530,
|
| 139 |
-
"content": "</
|
| 140 |
"single_word": false,
|
| 141 |
"lstrip": false,
|
| 142 |
"rstrip": false,
|
|
@@ -145,7 +145,7 @@
|
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"id": 57531,
|
| 148 |
-
"content": "<
|
| 149 |
"single_word": false,
|
| 150 |
"lstrip": false,
|
| 151 |
"rstrip": false,
|
|
@@ -154,7 +154,7 @@
|
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"id": 57532,
|
| 157 |
-
"content": "</
|
| 158 |
"single_word": false,
|
| 159 |
"lstrip": false,
|
| 160 |
"rstrip": false,
|
|
@@ -163,7 +163,7 @@
|
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"id": 57533,
|
| 166 |
-
"content": "<
|
| 167 |
"single_word": false,
|
| 168 |
"lstrip": false,
|
| 169 |
"rstrip": false,
|
|
@@ -172,7 +172,7 @@
|
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"id": 57534,
|
| 175 |
-
"content": "</
|
| 176 |
"single_word": false,
|
| 177 |
"lstrip": false,
|
| 178 |
"rstrip": false,
|
|
@@ -181,7 +181,7 @@
|
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"id": 57535,
|
| 184 |
-
"content": "<
|
| 185 |
"single_word": false,
|
| 186 |
"lstrip": false,
|
| 187 |
"rstrip": false,
|
|
@@ -190,7 +190,7 @@
|
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"id": 57536,
|
| 193 |
-
"content": "</
|
| 194 |
"single_word": false,
|
| 195 |
"lstrip": false,
|
| 196 |
"rstrip": false,
|
|
@@ -199,7 +199,7 @@
|
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"id": 57537,
|
| 202 |
-
"content": "<
|
| 203 |
"single_word": false,
|
| 204 |
"lstrip": false,
|
| 205 |
"rstrip": false,
|
|
@@ -208,7 +208,7 @@
|
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"id": 57538,
|
| 211 |
-
"content": "</
|
| 212 |
"single_word": false,
|
| 213 |
"lstrip": false,
|
| 214 |
"rstrip": false,
|
|
@@ -217,6 +217,78 @@
|
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"id": 57539,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 220 |
"content": "<s_id_card>",
|
| 221 |
"single_word": false,
|
| 222 |
"lstrip": false,
|
|
|
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"id": 57529,
|
| 130 |
+
"content": "<s_Date Naissance>",
|
| 131 |
"single_word": false,
|
| 132 |
"lstrip": false,
|
| 133 |
"rstrip": false,
|
|
|
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"id": 57530,
|
| 139 |
+
"content": "</s_Date Naissance>",
|
| 140 |
"single_word": false,
|
| 141 |
"lstrip": false,
|
| 142 |
"rstrip": false,
|
|
|
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"id": 57531,
|
| 148 |
+
"content": "<s_Nationalite>",
|
| 149 |
"single_word": false,
|
| 150 |
"lstrip": false,
|
| 151 |
"rstrip": false,
|
|
|
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"id": 57532,
|
| 157 |
+
"content": "</s_Nationalite>",
|
| 158 |
"single_word": false,
|
| 159 |
"lstrip": false,
|
| 160 |
"rstrip": false,
|
|
|
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"id": 57533,
|
| 166 |
+
"content": "<s_Numero Carte>",
|
| 167 |
"single_word": false,
|
| 168 |
"lstrip": false,
|
| 169 |
"rstrip": false,
|
|
|
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"id": 57534,
|
| 175 |
+
"content": "</s_Numero Carte>",
|
| 176 |
"single_word": false,
|
| 177 |
"lstrip": false,
|
| 178 |
"rstrip": false,
|
|
|
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"id": 57535,
|
| 184 |
+
"content": "<s_Sexe>",
|
| 185 |
"single_word": false,
|
| 186 |
"lstrip": false,
|
| 187 |
"rstrip": false,
|
|
|
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"id": 57536,
|
| 193 |
+
"content": "</s_Sexe>",
|
| 194 |
"single_word": false,
|
| 195 |
"lstrip": false,
|
| 196 |
"rstrip": false,
|
|
|
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"id": 57537,
|
| 202 |
+
"content": "<s_type>",
|
| 203 |
"single_word": false,
|
| 204 |
"lstrip": false,
|
| 205 |
"rstrip": false,
|
|
|
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"id": 57538,
|
| 211 |
+
"content": "</s_type>",
|
| 212 |
"single_word": false,
|
| 213 |
"lstrip": false,
|
| 214 |
"rstrip": false,
|
|
|
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"id": 57539,
|
| 220 |
+
"content": "<s_address>",
|
| 221 |
+
"single_word": false,
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"normalized": true,
|
| 225 |
+
"special": false
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"id": 57540,
|
| 229 |
+
"content": "</s_address>",
|
| 230 |
+
"single_word": false,
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"normalized": true,
|
| 234 |
+
"special": false
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"id": 57541,
|
| 238 |
+
"content": "<s_valid_until>",
|
| 239 |
+
"single_word": false,
|
| 240 |
+
"lstrip": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"normalized": true,
|
| 243 |
+
"special": false
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"id": 57542,
|
| 247 |
+
"content": "</s_valid_until>",
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"lstrip": false,
|
| 250 |
+
"rstrip": false,
|
| 251 |
+
"normalized": true,
|
| 252 |
+
"special": false
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"id": 57543,
|
| 256 |
+
"content": "<s_issued_on>",
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"lstrip": false,
|
| 259 |
+
"rstrip": false,
|
| 260 |
+
"normalized": true,
|
| 261 |
+
"special": false
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"id": 57544,
|
| 265 |
+
"content": "</s_issued_on>",
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"lstrip": false,
|
| 268 |
+
"rstrip": false,
|
| 269 |
+
"normalized": true,
|
| 270 |
+
"special": false
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"id": 57545,
|
| 274 |
+
"content": "<s_issued_by>",
|
| 275 |
+
"single_word": false,
|
| 276 |
+
"lstrip": false,
|
| 277 |
+
"rstrip": false,
|
| 278 |
+
"normalized": true,
|
| 279 |
+
"special": false
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"id": 57546,
|
| 283 |
+
"content": "</s_issued_by>",
|
| 284 |
+
"single_word": false,
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"rstrip": false,
|
| 287 |
+
"normalized": true,
|
| 288 |
+
"special": false
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"id": 57547,
|
| 292 |
"content": "<s_id_card>",
|
| 293 |
"single_word": false,
|
| 294 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -97,7 +97,7 @@
|
|
| 97 |
"special": false
|
| 98 |
},
|
| 99 |
"57529": {
|
| 100 |
-
"content": "<
|
| 101 |
"lstrip": false,
|
| 102 |
"normalized": true,
|
| 103 |
"rstrip": false,
|
|
@@ -105,7 +105,7 @@
|
|
| 105 |
"special": false
|
| 106 |
},
|
| 107 |
"57530": {
|
| 108 |
-
"content": "</
|
| 109 |
"lstrip": false,
|
| 110 |
"normalized": true,
|
| 111 |
"rstrip": false,
|
|
@@ -113,7 +113,7 @@
|
|
| 113 |
"special": false
|
| 114 |
},
|
| 115 |
"57531": {
|
| 116 |
-
"content": "<
|
| 117 |
"lstrip": false,
|
| 118 |
"normalized": true,
|
| 119 |
"rstrip": false,
|
|
@@ -121,7 +121,7 @@
|
|
| 121 |
"special": false
|
| 122 |
},
|
| 123 |
"57532": {
|
| 124 |
-
"content": "</
|
| 125 |
"lstrip": false,
|
| 126 |
"normalized": true,
|
| 127 |
"rstrip": false,
|
|
@@ -129,7 +129,7 @@
|
|
| 129 |
"special": false
|
| 130 |
},
|
| 131 |
"57533": {
|
| 132 |
-
"content": "<
|
| 133 |
"lstrip": false,
|
| 134 |
"normalized": true,
|
| 135 |
"rstrip": false,
|
|
@@ -137,7 +137,7 @@
|
|
| 137 |
"special": false
|
| 138 |
},
|
| 139 |
"57534": {
|
| 140 |
-
"content": "</
|
| 141 |
"lstrip": false,
|
| 142 |
"normalized": true,
|
| 143 |
"rstrip": false,
|
|
@@ -145,7 +145,7 @@
|
|
| 145 |
"special": false
|
| 146 |
},
|
| 147 |
"57535": {
|
| 148 |
-
"content": "<
|
| 149 |
"lstrip": false,
|
| 150 |
"normalized": true,
|
| 151 |
"rstrip": false,
|
|
@@ -153,7 +153,7 @@
|
|
| 153 |
"special": false
|
| 154 |
},
|
| 155 |
"57536": {
|
| 156 |
-
"content": "</
|
| 157 |
"lstrip": false,
|
| 158 |
"normalized": true,
|
| 159 |
"rstrip": false,
|
|
@@ -161,7 +161,7 @@
|
|
| 161 |
"special": false
|
| 162 |
},
|
| 163 |
"57537": {
|
| 164 |
-
"content": "<
|
| 165 |
"lstrip": false,
|
| 166 |
"normalized": true,
|
| 167 |
"rstrip": false,
|
|
@@ -169,7 +169,7 @@
|
|
| 169 |
"special": false
|
| 170 |
},
|
| 171 |
"57538": {
|
| 172 |
-
"content": "</
|
| 173 |
"lstrip": false,
|
| 174 |
"normalized": true,
|
| 175 |
"rstrip": false,
|
|
@@ -177,6 +177,70 @@
|
|
| 177 |
"special": false
|
| 178 |
},
|
| 179 |
"57539": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 180 |
"content": "<s_id_card>",
|
| 181 |
"lstrip": false,
|
| 182 |
"normalized": true,
|
|
|
|
| 97 |
"special": false
|
| 98 |
},
|
| 99 |
"57529": {
|
| 100 |
+
"content": "<s_Date Naissance>",
|
| 101 |
"lstrip": false,
|
| 102 |
"normalized": true,
|
| 103 |
"rstrip": false,
|
|
|
|
| 105 |
"special": false
|
| 106 |
},
|
| 107 |
"57530": {
|
| 108 |
+
"content": "</s_Date Naissance>",
|
| 109 |
"lstrip": false,
|
| 110 |
"normalized": true,
|
| 111 |
"rstrip": false,
|
|
|
|
| 113 |
"special": false
|
| 114 |
},
|
| 115 |
"57531": {
|
| 116 |
+
"content": "<s_Nationalite>",
|
| 117 |
"lstrip": false,
|
| 118 |
"normalized": true,
|
| 119 |
"rstrip": false,
|
|
|
|
| 121 |
"special": false
|
| 122 |
},
|
| 123 |
"57532": {
|
| 124 |
+
"content": "</s_Nationalite>",
|
| 125 |
"lstrip": false,
|
| 126 |
"normalized": true,
|
| 127 |
"rstrip": false,
|
|
|
|
| 129 |
"special": false
|
| 130 |
},
|
| 131 |
"57533": {
|
| 132 |
+
"content": "<s_Numero Carte>",
|
| 133 |
"lstrip": false,
|
| 134 |
"normalized": true,
|
| 135 |
"rstrip": false,
|
|
|
|
| 137 |
"special": false
|
| 138 |
},
|
| 139 |
"57534": {
|
| 140 |
+
"content": "</s_Numero Carte>",
|
| 141 |
"lstrip": false,
|
| 142 |
"normalized": true,
|
| 143 |
"rstrip": false,
|
|
|
|
| 145 |
"special": false
|
| 146 |
},
|
| 147 |
"57535": {
|
| 148 |
+
"content": "<s_Sexe>",
|
| 149 |
"lstrip": false,
|
| 150 |
"normalized": true,
|
| 151 |
"rstrip": false,
|
|
|
|
| 153 |
"special": false
|
| 154 |
},
|
| 155 |
"57536": {
|
| 156 |
+
"content": "</s_Sexe>",
|
| 157 |
"lstrip": false,
|
| 158 |
"normalized": true,
|
| 159 |
"rstrip": false,
|
|
|
|
| 161 |
"special": false
|
| 162 |
},
|
| 163 |
"57537": {
|
| 164 |
+
"content": "<s_type>",
|
| 165 |
"lstrip": false,
|
| 166 |
"normalized": true,
|
| 167 |
"rstrip": false,
|
|
|
|
| 169 |
"special": false
|
| 170 |
},
|
| 171 |
"57538": {
|
| 172 |
+
"content": "</s_type>",
|
| 173 |
"lstrip": false,
|
| 174 |
"normalized": true,
|
| 175 |
"rstrip": false,
|
|
|
|
| 177 |
"special": false
|
| 178 |
},
|
| 179 |
"57539": {
|
| 180 |
+
"content": "<s_address>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": true,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": false
|
| 186 |
+
},
|
| 187 |
+
"57540": {
|
| 188 |
+
"content": "</s_address>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": true,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": false
|
| 194 |
+
},
|
| 195 |
+
"57541": {
|
| 196 |
+
"content": "<s_valid_until>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": true,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": false
|
| 202 |
+
},
|
| 203 |
+
"57542": {
|
| 204 |
+
"content": "</s_valid_until>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": true,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": false
|
| 210 |
+
},
|
| 211 |
+
"57543": {
|
| 212 |
+
"content": "<s_issued_on>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": true,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": false
|
| 218 |
+
},
|
| 219 |
+
"57544": {
|
| 220 |
+
"content": "</s_issued_on>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": true,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": false
|
| 226 |
+
},
|
| 227 |
+
"57545": {
|
| 228 |
+
"content": "<s_issued_by>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": true,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": false
|
| 234 |
+
},
|
| 235 |
+
"57546": {
|
| 236 |
+
"content": "</s_issued_by>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": true,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": false
|
| 242 |
+
},
|
| 243 |
+
"57547": {
|
| 244 |
"content": "<s_id_card>",
|
| 245 |
"lstrip": false,
|
| 246 |
"normalized": true,
|