End of training
Browse files- README.md +8 -4
- added_tokens.json +8 -47
- preprocessor_config.json +4 -4
- special_tokens_map.json +70 -2
- tokenizer.json +0 -0
- tokenizer_config.json +34 -345
README.md
CHANGED
|
@@ -1,7 +1,11 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
|
|
|
|
|
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: DonutInvoiceCzechTrainer
|
| 7 |
results: []
|
|
@@ -12,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 12 |
|
| 13 |
# DonutInvoiceCzechTrainer
|
| 14 |
|
| 15 |
-
This model
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
|
@@ -32,12 +36,12 @@ More information needed
|
|
| 32 |
|
| 33 |
The following hyperparameters were used during training:
|
| 34 |
- learning_rate: 2e-05
|
| 35 |
-
- train_batch_size:
|
| 36 |
-
- eval_batch_size:
|
| 37 |
- seed: 42
|
| 38 |
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 39 |
- lr_scheduler_type: linear
|
| 40 |
-
- num_epochs:
|
| 41 |
- mixed_precision_training: Native AMP
|
| 42 |
|
| 43 |
### Training results
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: naver-clova-ix/donut-base
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- imagefolder
|
| 9 |
model-index:
|
| 10 |
- name: DonutInvoiceCzechTrainer
|
| 11 |
results: []
|
|
|
|
| 16 |
|
| 17 |
# DonutInvoiceCzechTrainer
|
| 18 |
|
| 19 |
+
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.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
- learning_rate: 2e-05
|
| 39 |
+
- train_batch_size: 1
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 3
|
| 45 |
- mixed_precision_training: Native AMP
|
| 46 |
|
| 47 |
### Training results
|
added_tokens.json
CHANGED
|
@@ -1,52 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"</
|
| 3 |
-
"</
|
| 4 |
-
"</
|
| 5 |
-
"</
|
| 6 |
-
"<
|
| 7 |
-
"<
|
| 8 |
-
"<
|
| 9 |
-
"</s_customer_tax_id>": 57531,
|
| 10 |
-
"</s_due_date>": 57561,
|
| 11 |
-
"</s_invoice_number>": 57548,
|
| 12 |
-
"</s_issue_date>": 57569,
|
| 13 |
-
"</s_payment>": 57540,
|
| 14 |
-
"</s_supplier_name>": 57533,
|
| 15 |
-
"</s_supplier_register_id>": 57551,
|
| 16 |
-
"</s_supplier_tax_id>": 57542,
|
| 17 |
-
"</s_taxable_supply_date>": 57532,
|
| 18 |
-
"</s_total_price>": 57538,
|
| 19 |
-
"</s_total_vat>": 57568,
|
| 20 |
-
"</s_variable_symbol>": 57566,
|
| 21 |
-
"</s_vat>": 57530,
|
| 22 |
-
"</s_vat_base>": 57562,
|
| 23 |
-
"</s_vat_items>": 57536,
|
| 24 |
-
"</s_vat_percentage>": 57563,
|
| 25 |
-
"<s_BIC>": 57526,
|
| 26 |
-
"<s_IBAN>": 57528,
|
| 27 |
-
"<s_bank_account_number>": 57565,
|
| 28 |
-
"<s_const_symbol>": 57552,
|
| 29 |
-
"<s_cord-v2>": 57571,
|
| 30 |
-
"<s_currency>": 57535,
|
| 31 |
-
"<s_customer_name>": 57539,
|
| 32 |
-
"<s_customer_register_id>": 57544,
|
| 33 |
-
"<s_customer_tax_id>": 57549,
|
| 34 |
-
"<s_due_date>": 57527,
|
| 35 |
"<s_iitcdip>": 57523,
|
| 36 |
-
"<s_invoice_number>": 57556,
|
| 37 |
-
"<s_issue_date>": 57567,
|
| 38 |
-
"<s_payment>": 57547,
|
| 39 |
-
"<s_supplier_name>": 57558,
|
| 40 |
-
"<s_supplier_register_id>": 57559,
|
| 41 |
-
"<s_supplier_tax_id>": 57545,
|
| 42 |
"<s_synthdog>": 57524,
|
| 43 |
-
"<
|
| 44 |
-
"<s_total_price>": 57564,
|
| 45 |
-
"<s_total_vat>": 57550,
|
| 46 |
-
"<s_variable_symbol>": 57570,
|
| 47 |
-
"<s_vat>": 57543,
|
| 48 |
-
"<s_vat_base>": 57546,
|
| 49 |
-
"<s_vat_items>": 57534,
|
| 50 |
-
"<s_vat_percentage>": 57555,
|
| 51 |
"<sep/>": 57522
|
| 52 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"</s_address>": 57532,
|
| 3 |
+
"</s_company>": 57530,
|
| 4 |
+
"</s_date>": 57528,
|
| 5 |
+
"</s_total>": 57526,
|
| 6 |
+
"<s_address>": 57531,
|
| 7 |
+
"<s_company>": 57529,
|
| 8 |
+
"<s_date>": 57527,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
"<s_iitcdip>": 57523,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
"<s_synthdog>": 57524,
|
| 11 |
+
"<s_total>": 57525,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
"<sep/>": 57522
|
| 13 |
}
|
preprocessor_config.json
CHANGED
|
@@ -19,8 +19,8 @@
|
|
| 19 |
"processor_class": "DonutProcessor",
|
| 20 |
"resample": 2,
|
| 21 |
"rescale_factor": 0.00392156862745098,
|
| 22 |
-
"size":
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
}
|
|
|
|
| 19 |
"processor_class": "DonutProcessor",
|
| 20 |
"resample": 2,
|
| 21 |
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": [
|
| 23 |
+
720,
|
| 24 |
+
960
|
| 25 |
+
]
|
| 26 |
}
|
special_tokens_map.json
CHANGED
|
@@ -1,7 +1,75 @@
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
-
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
],
|
| 6 |
"bos_token": {
|
| 7 |
"content": "<s>",
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<s_total>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "</s_total>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"content": "<s_date>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"content": "</s_date>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"content": "<s_company>",
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"normalized": false,
|
| 35 |
+
"rstrip": false,
|
| 36 |
+
"single_word": false
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"content": "</s_company>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"content": "<s_address>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"content": "</s_address>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"content": "<s>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"content": "</s>",
|
| 68 |
+
"lstrip": false,
|
| 69 |
+
"normalized": false,
|
| 70 |
+
"rstrip": false,
|
| 71 |
+
"single_word": false
|
| 72 |
+
}
|
| 73 |
],
|
| 74 |
"bos_token": {
|
| 75 |
"content": "<s>",
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -65,385 +65,81 @@
|
|
| 65 |
"special": true
|
| 66 |
},
|
| 67 |
"57525": {
|
| 68 |
-
"content": "<
|
| 69 |
"lstrip": false,
|
| 70 |
-
"normalized":
|
| 71 |
"rstrip": false,
|
| 72 |
"single_word": false,
|
| 73 |
-
"special":
|
| 74 |
},
|
| 75 |
"57526": {
|
| 76 |
-
"content": "<
|
| 77 |
"lstrip": false,
|
| 78 |
-
"normalized":
|
| 79 |
"rstrip": false,
|
| 80 |
"single_word": false,
|
| 81 |
-
"special":
|
| 82 |
},
|
| 83 |
"57527": {
|
| 84 |
-
"content": "<
|
| 85 |
"lstrip": false,
|
| 86 |
-
"normalized":
|
| 87 |
"rstrip": false,
|
| 88 |
"single_word": false,
|
| 89 |
-
"special":
|
| 90 |
},
|
| 91 |
"57528": {
|
| 92 |
-
"content": "<
|
| 93 |
"lstrip": false,
|
| 94 |
-
"normalized":
|
| 95 |
"rstrip": false,
|
| 96 |
"single_word": false,
|
| 97 |
-
"special":
|
| 98 |
},
|
| 99 |
"57529": {
|
| 100 |
-
"content": "<
|
| 101 |
"lstrip": false,
|
| 102 |
-
"normalized":
|
| 103 |
"rstrip": false,
|
| 104 |
"single_word": false,
|
| 105 |
-
"special":
|
| 106 |
},
|
| 107 |
"57530": {
|
| 108 |
-
"content": "</
|
| 109 |
"lstrip": false,
|
| 110 |
-
"normalized":
|
| 111 |
"rstrip": false,
|
| 112 |
"single_word": false,
|
| 113 |
-
"special":
|
| 114 |
},
|
| 115 |
"57531": {
|
| 116 |
-
"content": "<
|
| 117 |
"lstrip": false,
|
| 118 |
-
"normalized":
|
| 119 |
"rstrip": false,
|
| 120 |
"single_word": false,
|
| 121 |
-
"special":
|
| 122 |
},
|
| 123 |
"57532": {
|
| 124 |
-
"content": "</
|
| 125 |
-
"lstrip": false,
|
| 126 |
-
"normalized": true,
|
| 127 |
-
"rstrip": false,
|
| 128 |
-
"single_word": false,
|
| 129 |
-
"special": false
|
| 130 |
-
},
|
| 131 |
-
"57533": {
|
| 132 |
-
"content": "</s_supplier_name>",
|
| 133 |
-
"lstrip": false,
|
| 134 |
-
"normalized": true,
|
| 135 |
-
"rstrip": false,
|
| 136 |
-
"single_word": false,
|
| 137 |
-
"special": false
|
| 138 |
-
},
|
| 139 |
-
"57534": {
|
| 140 |
-
"content": "<s_vat_items>",
|
| 141 |
-
"lstrip": false,
|
| 142 |
-
"normalized": true,
|
| 143 |
-
"rstrip": false,
|
| 144 |
-
"single_word": false,
|
| 145 |
-
"special": false
|
| 146 |
-
},
|
| 147 |
-
"57535": {
|
| 148 |
-
"content": "<s_currency>",
|
| 149 |
-
"lstrip": false,
|
| 150 |
-
"normalized": true,
|
| 151 |
-
"rstrip": false,
|
| 152 |
-
"single_word": false,
|
| 153 |
-
"special": false
|
| 154 |
-
},
|
| 155 |
-
"57536": {
|
| 156 |
-
"content": "</s_vat_items>",
|
| 157 |
-
"lstrip": false,
|
| 158 |
-
"normalized": true,
|
| 159 |
-
"rstrip": false,
|
| 160 |
-
"single_word": false,
|
| 161 |
-
"special": false
|
| 162 |
-
},
|
| 163 |
-
"57537": {
|
| 164 |
-
"content": "</s_bank_account_number>",
|
| 165 |
-
"lstrip": false,
|
| 166 |
-
"normalized": true,
|
| 167 |
-
"rstrip": false,
|
| 168 |
-
"single_word": false,
|
| 169 |
-
"special": false
|
| 170 |
-
},
|
| 171 |
-
"57538": {
|
| 172 |
-
"content": "</s_total_price>",
|
| 173 |
-
"lstrip": false,
|
| 174 |
-
"normalized": true,
|
| 175 |
-
"rstrip": false,
|
| 176 |
-
"single_word": false,
|
| 177 |
-
"special": false
|
| 178 |
-
},
|
| 179 |
-
"57539": {
|
| 180 |
-
"content": "<s_customer_name>",
|
| 181 |
-
"lstrip": false,
|
| 182 |
-
"normalized": true,
|
| 183 |
-
"rstrip": false,
|
| 184 |
-
"single_word": false,
|
| 185 |
-
"special": false
|
| 186 |
-
},
|
| 187 |
-
"57540": {
|
| 188 |
-
"content": "</s_payment>",
|
| 189 |
-
"lstrip": false,
|
| 190 |
-
"normalized": true,
|
| 191 |
-
"rstrip": false,
|
| 192 |
-
"single_word": false,
|
| 193 |
-
"special": false
|
| 194 |
-
},
|
| 195 |
-
"57541": {
|
| 196 |
-
"content": "</s_currency>",
|
| 197 |
-
"lstrip": false,
|
| 198 |
-
"normalized": true,
|
| 199 |
-
"rstrip": false,
|
| 200 |
-
"single_word": false,
|
| 201 |
-
"special": false
|
| 202 |
-
},
|
| 203 |
-
"57542": {
|
| 204 |
-
"content": "</s_supplier_tax_id>",
|
| 205 |
-
"lstrip": false,
|
| 206 |
-
"normalized": true,
|
| 207 |
-
"rstrip": false,
|
| 208 |
-
"single_word": false,
|
| 209 |
-
"special": false
|
| 210 |
-
},
|
| 211 |
-
"57543": {
|
| 212 |
-
"content": "<s_vat>",
|
| 213 |
-
"lstrip": false,
|
| 214 |
-
"normalized": true,
|
| 215 |
-
"rstrip": false,
|
| 216 |
-
"single_word": false,
|
| 217 |
-
"special": false
|
| 218 |
-
},
|
| 219 |
-
"57544": {
|
| 220 |
-
"content": "<s_customer_register_id>",
|
| 221 |
-
"lstrip": false,
|
| 222 |
-
"normalized": true,
|
| 223 |
-
"rstrip": false,
|
| 224 |
-
"single_word": false,
|
| 225 |
-
"special": false
|
| 226 |
-
},
|
| 227 |
-
"57545": {
|
| 228 |
-
"content": "<s_supplier_tax_id>",
|
| 229 |
-
"lstrip": false,
|
| 230 |
-
"normalized": true,
|
| 231 |
-
"rstrip": false,
|
| 232 |
-
"single_word": false,
|
| 233 |
-
"special": false
|
| 234 |
-
},
|
| 235 |
-
"57546": {
|
| 236 |
-
"content": "<s_vat_base>",
|
| 237 |
-
"lstrip": false,
|
| 238 |
-
"normalized": true,
|
| 239 |
-
"rstrip": false,
|
| 240 |
-
"single_word": false,
|
| 241 |
-
"special": false
|
| 242 |
-
},
|
| 243 |
-
"57547": {
|
| 244 |
-
"content": "<s_payment>",
|
| 245 |
-
"lstrip": false,
|
| 246 |
-
"normalized": true,
|
| 247 |
-
"rstrip": false,
|
| 248 |
-
"single_word": false,
|
| 249 |
-
"special": false
|
| 250 |
-
},
|
| 251 |
-
"57548": {
|
| 252 |
-
"content": "</s_invoice_number>",
|
| 253 |
-
"lstrip": false,
|
| 254 |
-
"normalized": true,
|
| 255 |
-
"rstrip": false,
|
| 256 |
-
"single_word": false,
|
| 257 |
-
"special": false
|
| 258 |
-
},
|
| 259 |
-
"57549": {
|
| 260 |
-
"content": "<s_customer_tax_id>",
|
| 261 |
-
"lstrip": false,
|
| 262 |
-
"normalized": true,
|
| 263 |
-
"rstrip": false,
|
| 264 |
-
"single_word": false,
|
| 265 |
-
"special": false
|
| 266 |
-
},
|
| 267 |
-
"57550": {
|
| 268 |
-
"content": "<s_total_vat>",
|
| 269 |
-
"lstrip": false,
|
| 270 |
-
"normalized": true,
|
| 271 |
-
"rstrip": false,
|
| 272 |
-
"single_word": false,
|
| 273 |
-
"special": false
|
| 274 |
-
},
|
| 275 |
-
"57551": {
|
| 276 |
-
"content": "</s_supplier_register_id>",
|
| 277 |
-
"lstrip": false,
|
| 278 |
-
"normalized": true,
|
| 279 |
-
"rstrip": false,
|
| 280 |
-
"single_word": false,
|
| 281 |
-
"special": false
|
| 282 |
-
},
|
| 283 |
-
"57552": {
|
| 284 |
-
"content": "<s_const_symbol>",
|
| 285 |
-
"lstrip": false,
|
| 286 |
-
"normalized": true,
|
| 287 |
-
"rstrip": false,
|
| 288 |
-
"single_word": false,
|
| 289 |
-
"special": false
|
| 290 |
-
},
|
| 291 |
-
"57553": {
|
| 292 |
-
"content": "<s_taxable_supply_date>",
|
| 293 |
"lstrip": false,
|
| 294 |
-
"normalized":
|
| 295 |
-
"rstrip": false,
|
| 296 |
-
"single_word": false,
|
| 297 |
-
"special": false
|
| 298 |
-
},
|
| 299 |
-
"57554": {
|
| 300 |
-
"content": "</s_customer_register_id>",
|
| 301 |
-
"lstrip": false,
|
| 302 |
-
"normalized": true,
|
| 303 |
-
"rstrip": false,
|
| 304 |
-
"single_word": false,
|
| 305 |
-
"special": false
|
| 306 |
-
},
|
| 307 |
-
"57555": {
|
| 308 |
-
"content": "<s_vat_percentage>",
|
| 309 |
-
"lstrip": false,
|
| 310 |
-
"normalized": true,
|
| 311 |
-
"rstrip": false,
|
| 312 |
-
"single_word": false,
|
| 313 |
-
"special": false
|
| 314 |
-
},
|
| 315 |
-
"57556": {
|
| 316 |
-
"content": "<s_invoice_number>",
|
| 317 |
-
"lstrip": false,
|
| 318 |
-
"normalized": true,
|
| 319 |
-
"rstrip": false,
|
| 320 |
-
"single_word": false,
|
| 321 |
-
"special": false
|
| 322 |
-
},
|
| 323 |
-
"57557": {
|
| 324 |
-
"content": "</s_IBAN>",
|
| 325 |
-
"lstrip": false,
|
| 326 |
-
"normalized": true,
|
| 327 |
-
"rstrip": false,
|
| 328 |
-
"single_word": false,
|
| 329 |
-
"special": false
|
| 330 |
-
},
|
| 331 |
-
"57558": {
|
| 332 |
-
"content": "<s_supplier_name>",
|
| 333 |
-
"lstrip": false,
|
| 334 |
-
"normalized": true,
|
| 335 |
-
"rstrip": false,
|
| 336 |
-
"single_word": false,
|
| 337 |
-
"special": false
|
| 338 |
-
},
|
| 339 |
-
"57559": {
|
| 340 |
-
"content": "<s_supplier_register_id>",
|
| 341 |
-
"lstrip": false,
|
| 342 |
-
"normalized": true,
|
| 343 |
-
"rstrip": false,
|
| 344 |
-
"single_word": false,
|
| 345 |
-
"special": false
|
| 346 |
-
},
|
| 347 |
-
"57560": {
|
| 348 |
-
"content": "</s_customer_name>",
|
| 349 |
-
"lstrip": false,
|
| 350 |
-
"normalized": true,
|
| 351 |
-
"rstrip": false,
|
| 352 |
-
"single_word": false,
|
| 353 |
-
"special": false
|
| 354 |
-
},
|
| 355 |
-
"57561": {
|
| 356 |
-
"content": "</s_due_date>",
|
| 357 |
-
"lstrip": false,
|
| 358 |
-
"normalized": true,
|
| 359 |
-
"rstrip": false,
|
| 360 |
-
"single_word": false,
|
| 361 |
-
"special": false
|
| 362 |
-
},
|
| 363 |
-
"57562": {
|
| 364 |
-
"content": "</s_vat_base>",
|
| 365 |
-
"lstrip": false,
|
| 366 |
-
"normalized": true,
|
| 367 |
-
"rstrip": false,
|
| 368 |
-
"single_word": false,
|
| 369 |
-
"special": false
|
| 370 |
-
},
|
| 371 |
-
"57563": {
|
| 372 |
-
"content": "</s_vat_percentage>",
|
| 373 |
-
"lstrip": false,
|
| 374 |
-
"normalized": true,
|
| 375 |
-
"rstrip": false,
|
| 376 |
-
"single_word": false,
|
| 377 |
-
"special": false
|
| 378 |
-
},
|
| 379 |
-
"57564": {
|
| 380 |
-
"content": "<s_total_price>",
|
| 381 |
-
"lstrip": false,
|
| 382 |
-
"normalized": true,
|
| 383 |
-
"rstrip": false,
|
| 384 |
-
"single_word": false,
|
| 385 |
-
"special": false
|
| 386 |
-
},
|
| 387 |
-
"57565": {
|
| 388 |
-
"content": "<s_bank_account_number>",
|
| 389 |
-
"lstrip": false,
|
| 390 |
-
"normalized": true,
|
| 391 |
-
"rstrip": false,
|
| 392 |
-
"single_word": false,
|
| 393 |
-
"special": false
|
| 394 |
-
},
|
| 395 |
-
"57566": {
|
| 396 |
-
"content": "</s_variable_symbol>",
|
| 397 |
-
"lstrip": false,
|
| 398 |
-
"normalized": true,
|
| 399 |
-
"rstrip": false,
|
| 400 |
-
"single_word": false,
|
| 401 |
-
"special": false
|
| 402 |
-
},
|
| 403 |
-
"57567": {
|
| 404 |
-
"content": "<s_issue_date>",
|
| 405 |
-
"lstrip": false,
|
| 406 |
-
"normalized": true,
|
| 407 |
-
"rstrip": false,
|
| 408 |
-
"single_word": false,
|
| 409 |
-
"special": false
|
| 410 |
-
},
|
| 411 |
-
"57568": {
|
| 412 |
-
"content": "</s_total_vat>",
|
| 413 |
-
"lstrip": false,
|
| 414 |
-
"normalized": true,
|
| 415 |
-
"rstrip": false,
|
| 416 |
-
"single_word": false,
|
| 417 |
-
"special": false
|
| 418 |
-
},
|
| 419 |
-
"57569": {
|
| 420 |
-
"content": "</s_issue_date>",
|
| 421 |
-
"lstrip": false,
|
| 422 |
-
"normalized": true,
|
| 423 |
-
"rstrip": false,
|
| 424 |
-
"single_word": false,
|
| 425 |
-
"special": false
|
| 426 |
-
},
|
| 427 |
-
"57570": {
|
| 428 |
-
"content": "<s_variable_symbol>",
|
| 429 |
-
"lstrip": false,
|
| 430 |
-
"normalized": true,
|
| 431 |
-
"rstrip": false,
|
| 432 |
-
"single_word": false,
|
| 433 |
-
"special": false
|
| 434 |
-
},
|
| 435 |
-
"57571": {
|
| 436 |
-
"content": "<s_cord-v2>",
|
| 437 |
-
"lstrip": false,
|
| 438 |
-
"normalized": true,
|
| 439 |
"rstrip": false,
|
| 440 |
"single_word": false,
|
| 441 |
-
"special":
|
| 442 |
}
|
| 443 |
},
|
| 444 |
"additional_special_tokens": [
|
| 445 |
-
"<
|
| 446 |
-
"<
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 447 |
],
|
| 448 |
"bos_token": "<s>",
|
| 449 |
"clean_up_tokenization_spaces": false,
|
|
@@ -451,18 +147,11 @@
|
|
| 451 |
"eos_token": "</s>",
|
| 452 |
"extra_special_tokens": {},
|
| 453 |
"mask_token": "<mask>",
|
| 454 |
-
"max_length": 512,
|
| 455 |
"model_max_length": 1000000000000000019884624838656,
|
| 456 |
-
"pad_to_multiple_of": null,
|
| 457 |
"pad_token": "<pad>",
|
| 458 |
-
"pad_token_type_id": 0,
|
| 459 |
-
"padding_side": "right",
|
| 460 |
"processor_class": "DonutProcessor",
|
| 461 |
"sep_token": "</s>",
|
| 462 |
"sp_model_kwargs": {},
|
| 463 |
-
"stride": 0,
|
| 464 |
"tokenizer_class": "XLMRobertaTokenizer",
|
| 465 |
-
"truncation_side": "right",
|
| 466 |
-
"truncation_strategy": "longest_first",
|
| 467 |
"unk_token": "<unk>"
|
| 468 |
}
|
|
|
|
| 65 |
"special": true
|
| 66 |
},
|
| 67 |
"57525": {
|
| 68 |
+
"content": "<s_total>",
|
| 69 |
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
"rstrip": false,
|
| 72 |
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
},
|
| 75 |
"57526": {
|
| 76 |
+
"content": "</s_total>",
|
| 77 |
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
"rstrip": false,
|
| 80 |
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
},
|
| 83 |
"57527": {
|
| 84 |
+
"content": "<s_date>",
|
| 85 |
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
"rstrip": false,
|
| 88 |
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
},
|
| 91 |
"57528": {
|
| 92 |
+
"content": "</s_date>",
|
| 93 |
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
"rstrip": false,
|
| 96 |
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
},
|
| 99 |
"57529": {
|
| 100 |
+
"content": "<s_company>",
|
| 101 |
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
"rstrip": false,
|
| 104 |
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
},
|
| 107 |
"57530": {
|
| 108 |
+
"content": "</s_company>",
|
| 109 |
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
"rstrip": false,
|
| 112 |
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
},
|
| 115 |
"57531": {
|
| 116 |
+
"content": "<s_address>",
|
| 117 |
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
"rstrip": false,
|
| 120 |
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
},
|
| 123 |
"57532": {
|
| 124 |
+
"content": "</s_address>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 125 |
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 127 |
"rstrip": false,
|
| 128 |
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
}
|
| 131 |
},
|
| 132 |
"additional_special_tokens": [
|
| 133 |
+
"<s_total>",
|
| 134 |
+
"</s_total>",
|
| 135 |
+
"<s_date>",
|
| 136 |
+
"</s_date>",
|
| 137 |
+
"<s_company>",
|
| 138 |
+
"</s_company>",
|
| 139 |
+
"<s_address>",
|
| 140 |
+
"</s_address>",
|
| 141 |
+
"<s>",
|
| 142 |
+
"</s>"
|
| 143 |
],
|
| 144 |
"bos_token": "<s>",
|
| 145 |
"clean_up_tokenization_spaces": false,
|
|
|
|
| 147 |
"eos_token": "</s>",
|
| 148 |
"extra_special_tokens": {},
|
| 149 |
"mask_token": "<mask>",
|
|
|
|
| 150 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 151 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
| 152 |
"processor_class": "DonutProcessor",
|
| 153 |
"sep_token": "</s>",
|
| 154 |
"sp_model_kwargs": {},
|
|
|
|
| 155 |
"tokenizer_class": "XLMRobertaTokenizer",
|
|
|
|
|
|
|
| 156 |
"unk_token": "<unk>"
|
| 157 |
}
|