End of training
Browse files- README.md +3 -1
- added_tokens.json +22 -0
- special_tokens_map.json +23 -1
- tokenizer.json +198 -0
- tokenizer_config.json +199 -1
README.md
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
datasets:
|
|
@@ -13,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# jupy-model_v5
|
| 15 |
|
| 16 |
-
This model
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 1 |
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: naver-clova-ix/donut-base
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
|
|
|
| 15 |
|
| 16 |
# jupy-model_v5
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
added_tokens.json
CHANGED
|
@@ -1,5 +1,27 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"<s_iitcdip>": 57523,
|
|
|
|
|
|
|
|
|
|
| 3 |
"<s_synthdog>": 57524,
|
|
|
|
| 4 |
"<sep/>": 57522
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"</s_EI_number>": 57545,
|
| 3 |
+
"</s_Exempt_FATCA_code>": 57539,
|
| 4 |
+
"</s_Exempt_pay_code>": 57538,
|
| 5 |
+
"</s_account_number>": 57528,
|
| 6 |
+
"</s_address>": 57526,
|
| 7 |
+
"</s_business_name>": 57531,
|
| 8 |
+
"</s_date>": 57525,
|
| 9 |
+
"</s_multi_line_address>": 57535,
|
| 10 |
+
"</s_name>": 57527,
|
| 11 |
+
"</s_ss_number>": 57534,
|
| 12 |
+
"</s_zip_address>": 57542,
|
| 13 |
+
"<s_EI_number>": 57533,
|
| 14 |
+
"<s_Exempt_FATCA_code>": 57532,
|
| 15 |
+
"<s_Exempt_pay_code>": 57544,
|
| 16 |
+
"<s_account_number>": 57546,
|
| 17 |
+
"<s_address>": 57540,
|
| 18 |
+
"<s_business_name>": 57529,
|
| 19 |
+
"<s_date>": 57536,
|
| 20 |
"<s_iitcdip>": 57523,
|
| 21 |
+
"<s_multi_line_address>": 57530,
|
| 22 |
+
"<s_name>": 57543,
|
| 23 |
+
"<s_ss_number>": 57537,
|
| 24 |
"<s_synthdog>": 57524,
|
| 25 |
+
"<s_zip_address>": 57541,
|
| 26 |
"<sep/>": 57522
|
| 27 |
}
|
special_tokens_map.json
CHANGED
|
@@ -1,7 +1,29 @@
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"</s>",
|
| 4 |
-
"<
|
|
|
|
|
|
|
| 5 |
],
|
| 6 |
"bos_token": {
|
| 7 |
"content": "<s>",
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
+
"</s_date>",
|
| 4 |
+
"</s_address>",
|
| 5 |
+
"</s_name>",
|
| 6 |
+
"</s_account_number>",
|
| 7 |
+
"<s_business_name>",
|
| 8 |
+
"<s_multi_line_address>",
|
| 9 |
+
"</s_business_name>",
|
| 10 |
+
"<s_Exempt_FATCA_code>",
|
| 11 |
+
"<s_EI_number>",
|
| 12 |
+
"</s_ss_number>",
|
| 13 |
+
"<s>",
|
| 14 |
+
"</s_multi_line_address>",
|
| 15 |
+
"<s_date>",
|
| 16 |
+
"<s_ss_number>",
|
| 17 |
+
"</s_Exempt_pay_code>",
|
| 18 |
+
"</s_Exempt_FATCA_code>",
|
| 19 |
+
"<s_address>",
|
| 20 |
+
"<s_zip_address>",
|
| 21 |
+
"</s_zip_address>",
|
| 22 |
+
"<s_name>",
|
| 23 |
"</s>",
|
| 24 |
+
"<s_Exempt_pay_code>",
|
| 25 |
+
"</s_EI_number>",
|
| 26 |
+
"<s_account_number>"
|
| 27 |
],
|
| 28 |
"bos_token": {
|
| 29 |
"content": "<s>",
|
tokenizer.json
CHANGED
|
@@ -88,6 +88,204 @@
|
|
| 88 |
"rstrip": false,
|
| 89 |
"normalized": false,
|
| 90 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
}
|
| 92 |
],
|
| 93 |
"normalizer": {
|
|
|
|
| 88 |
"rstrip": false,
|
| 89 |
"normalized": false,
|
| 90 |
"special": true
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"id": 57525,
|
| 94 |
+
"content": "</s_date>",
|
| 95 |
+
"single_word": false,
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"normalized": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"id": 57526,
|
| 103 |
+
"content": "</s_address>",
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"lstrip": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"normalized": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"id": 57527,
|
| 112 |
+
"content": "</s_name>",
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"lstrip": false,
|
| 115 |
+
"rstrip": false,
|
| 116 |
+
"normalized": false,
|
| 117 |
+
"special": true
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"id": 57528,
|
| 121 |
+
"content": "</s_account_number>",
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"lstrip": false,
|
| 124 |
+
"rstrip": false,
|
| 125 |
+
"normalized": false,
|
| 126 |
+
"special": true
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"id": 57529,
|
| 130 |
+
"content": "<s_business_name>",
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"lstrip": false,
|
| 133 |
+
"rstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"special": true
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"id": 57530,
|
| 139 |
+
"content": "<s_multi_line_address>",
|
| 140 |
+
"single_word": false,
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"rstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"special": true
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"id": 57531,
|
| 148 |
+
"content": "</s_business_name>",
|
| 149 |
+
"single_word": false,
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"id": 57532,
|
| 157 |
+
"content": "<s_Exempt_FATCA_code>",
|
| 158 |
+
"single_word": false,
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"id": 57533,
|
| 166 |
+
"content": "<s_EI_number>",
|
| 167 |
+
"single_word": false,
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"normalized": false,
|
| 171 |
+
"special": true
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"id": 57534,
|
| 175 |
+
"content": "</s_ss_number>",
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"lstrip": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"normalized": false,
|
| 180 |
+
"special": true
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"id": 57535,
|
| 184 |
+
"content": "</s_multi_line_address>",
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"lstrip": false,
|
| 187 |
+
"rstrip": false,
|
| 188 |
+
"normalized": false,
|
| 189 |
+
"special": true
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"id": 57536,
|
| 193 |
+
"content": "<s_date>",
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"lstrip": false,
|
| 196 |
+
"rstrip": false,
|
| 197 |
+
"normalized": false,
|
| 198 |
+
"special": true
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"id": 57537,
|
| 202 |
+
"content": "<s_ss_number>",
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"lstrip": false,
|
| 205 |
+
"rstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"special": true
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"id": 57538,
|
| 211 |
+
"content": "</s_Exempt_pay_code>",
|
| 212 |
+
"single_word": false,
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"rstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"special": true
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"id": 57539,
|
| 220 |
+
"content": "</s_Exempt_FATCA_code>",
|
| 221 |
+
"single_word": false,
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"id": 57540,
|
| 229 |
+
"content": "<s_address>",
|
| 230 |
+
"single_word": false,
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"normalized": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"id": 57541,
|
| 238 |
+
"content": "<s_zip_address>",
|
| 239 |
+
"single_word": false,
|
| 240 |
+
"lstrip": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"normalized": false,
|
| 243 |
+
"special": true
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"id": 57542,
|
| 247 |
+
"content": "</s_zip_address>",
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"lstrip": false,
|
| 250 |
+
"rstrip": false,
|
| 251 |
+
"normalized": false,
|
| 252 |
+
"special": true
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"id": 57543,
|
| 256 |
+
"content": "<s_name>",
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"lstrip": false,
|
| 259 |
+
"rstrip": false,
|
| 260 |
+
"normalized": false,
|
| 261 |
+
"special": true
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"id": 57544,
|
| 265 |
+
"content": "<s_Exempt_pay_code>",
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"lstrip": false,
|
| 268 |
+
"rstrip": false,
|
| 269 |
+
"normalized": false,
|
| 270 |
+
"special": true
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"id": 57545,
|
| 274 |
+
"content": "</s_EI_number>",
|
| 275 |
+
"single_word": false,
|
| 276 |
+
"lstrip": false,
|
| 277 |
+
"rstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"special": true
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"id": 57546,
|
| 283 |
+
"content": "<s_account_number>",
|
| 284 |
+
"single_word": false,
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"rstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"special": true
|
| 289 |
}
|
| 290 |
],
|
| 291 |
"normalizer": {
|
tokenizer_config.json
CHANGED
|
@@ -63,11 +63,209 @@
|
|
| 63 |
"rstrip": false,
|
| 64 |
"single_word": false,
|
| 65 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
}
|
| 67 |
},
|
| 68 |
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
"</s>",
|
| 70 |
-
"<
|
|
|
|
|
|
|
| 71 |
],
|
| 72 |
"bos_token": "<s>",
|
| 73 |
"clean_up_tokenization_spaces": true,
|
|
|
|
| 63 |
"rstrip": false,
|
| 64 |
"single_word": false,
|
| 65 |
"special": true
|
| 66 |
+
},
|
| 67 |
+
"57525": {
|
| 68 |
+
"content": "</s_date>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"57526": {
|
| 76 |
+
"content": "</s_address>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"57527": {
|
| 84 |
+
"content": "</s_name>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"57528": {
|
| 92 |
+
"content": "</s_account_number>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"57529": {
|
| 100 |
+
"content": "<s_business_name>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"57530": {
|
| 108 |
+
"content": "<s_multi_line_address>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"57531": {
|
| 116 |
+
"content": "</s_business_name>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"57532": {
|
| 124 |
+
"content": "<s_Exempt_FATCA_code>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"57533": {
|
| 132 |
+
"content": "<s_EI_number>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"57534": {
|
| 140 |
+
"content": "</s_ss_number>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"57535": {
|
| 148 |
+
"content": "</s_multi_line_address>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"57536": {
|
| 156 |
+
"content": "<s_date>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"57537": {
|
| 164 |
+
"content": "<s_ss_number>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"57538": {
|
| 172 |
+
"content": "</s_Exempt_pay_code>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"57539": {
|
| 180 |
+
"content": "</s_Exempt_FATCA_code>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"57540": {
|
| 188 |
+
"content": "<s_address>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"57541": {
|
| 196 |
+
"content": "<s_zip_address>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"57542": {
|
| 204 |
+
"content": "</s_zip_address>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"57543": {
|
| 212 |
+
"content": "<s_name>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"57544": {
|
| 220 |
+
"content": "<s_Exempt_pay_code>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"57545": {
|
| 228 |
+
"content": "</s_EI_number>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"57546": {
|
| 236 |
+
"content": "<s_account_number>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
}
|
| 243 |
},
|
| 244 |
"additional_special_tokens": [
|
| 245 |
+
"</s_date>",
|
| 246 |
+
"</s_address>",
|
| 247 |
+
"</s_name>",
|
| 248 |
+
"</s_account_number>",
|
| 249 |
+
"<s_business_name>",
|
| 250 |
+
"<s_multi_line_address>",
|
| 251 |
+
"</s_business_name>",
|
| 252 |
+
"<s_Exempt_FATCA_code>",
|
| 253 |
+
"<s_EI_number>",
|
| 254 |
+
"</s_ss_number>",
|
| 255 |
+
"<s>",
|
| 256 |
+
"</s_multi_line_address>",
|
| 257 |
+
"<s_date>",
|
| 258 |
+
"<s_ss_number>",
|
| 259 |
+
"</s_Exempt_pay_code>",
|
| 260 |
+
"</s_Exempt_FATCA_code>",
|
| 261 |
+
"<s_address>",
|
| 262 |
+
"<s_zip_address>",
|
| 263 |
+
"</s_zip_address>",
|
| 264 |
+
"<s_name>",
|
| 265 |
"</s>",
|
| 266 |
+
"<s_Exempt_pay_code>",
|
| 267 |
+
"</s_EI_number>",
|
| 268 |
+
"<s_account_number>"
|
| 269 |
],
|
| 270 |
"bos_token": "<s>",
|
| 271 |
"clean_up_tokenization_spaces": true,
|