End of training
Browse files- processor_config.json +29 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
processor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"do_align_long_axis": false,
|
| 5 |
+
"do_normalize": true,
|
| 6 |
+
"do_pad": true,
|
| 7 |
+
"do_rescale": true,
|
| 8 |
+
"do_resize": true,
|
| 9 |
+
"do_thumbnail": true,
|
| 10 |
+
"image_mean": [
|
| 11 |
+
0.5,
|
| 12 |
+
0.5,
|
| 13 |
+
0.5
|
| 14 |
+
],
|
| 15 |
+
"image_processor_type": "DonutImageProcessorFast",
|
| 16 |
+
"image_std": [
|
| 17 |
+
0.5,
|
| 18 |
+
0.5,
|
| 19 |
+
0.5
|
| 20 |
+
],
|
| 21 |
+
"resample": 2,
|
| 22 |
+
"rescale_factor": 0.00392156862745098,
|
| 23 |
+
"size": {
|
| 24 |
+
"height": 2338,
|
| 25 |
+
"width": 1654
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"processor_class": "DonutProcessor"
|
| 29 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"extra_special_tokens": [
|
| 7 |
+
"<s_variable_symbol>",
|
| 8 |
+
"<s_bic>",
|
| 9 |
+
"</s_iban>",
|
| 10 |
+
"</s_supp_register_id>",
|
| 11 |
+
"<s_cust_register_id>",
|
| 12 |
+
"<s_taxable_supply_date>",
|
| 13 |
+
"<s_const_symbol>",
|
| 14 |
+
"</s_invoice_number>",
|
| 15 |
+
"<s_supp_register_id>",
|
| 16 |
+
"<s_bank_account_number>",
|
| 17 |
+
"<s_payment_type>",
|
| 18 |
+
"</s_bic>",
|
| 19 |
+
"</s_variable_symbol>",
|
| 20 |
+
"</s_due_date>",
|
| 21 |
+
"</s_issue_date>",
|
| 22 |
+
"</s_payment_type>",
|
| 23 |
+
"</s_cust_register_id>",
|
| 24 |
+
"<s_supp_tax_id>",
|
| 25 |
+
"<s_iban>",
|
| 26 |
+
"<s_total>",
|
| 27 |
+
"</s_const_symbol>",
|
| 28 |
+
"</s_taxable_supply_date>",
|
| 29 |
+
"<s_cust_tax_id>",
|
| 30 |
+
"<s_invoice_number>",
|
| 31 |
+
"</s_total>",
|
| 32 |
+
"<s_due_date>",
|
| 33 |
+
"</s_bank_account_number>",
|
| 34 |
+
"</s_supp_tax_id>",
|
| 35 |
+
"<s_issue_date>",
|
| 36 |
+
"</s_cust_tax_id>",
|
| 37 |
+
"<s_cord-v2>",
|
| 38 |
+
"</s>"
|
| 39 |
+
],
|
| 40 |
+
"from_slow": true,
|
| 41 |
+
"is_local": false,
|
| 42 |
+
"mask_token": "<mask>",
|
| 43 |
+
"max_length": 768,
|
| 44 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 45 |
+
"pad_to_multiple_of": null,
|
| 46 |
+
"pad_token": "<pad>",
|
| 47 |
+
"pad_token_type_id": 0,
|
| 48 |
+
"padding_side": "right",
|
| 49 |
+
"processor_class": "DonutProcessor",
|
| 50 |
+
"sep_token": "</s>",
|
| 51 |
+
"sp_model_kwargs": {},
|
| 52 |
+
"stride": 0,
|
| 53 |
+
"tokenizer_class": "TokenizersBackend",
|
| 54 |
+
"truncation_side": "right",
|
| 55 |
+
"truncation_strategy": "longest_first",
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|