End of training
Browse files- README.md +51 -0
- added_tokens.json +136 -0
- generation_config.json +8 -0
- preprocessor_config.json +26 -0
- runs/Aug25_00-39-03_ip-172-31-42-230.eu-central-1.compute.internal/events.out.tfevents.1692923949.ip-172-31-42-230.eu-central-1.compute.internal.20091.0 +2 -2
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +95 -0
- tokenizer.json +0 -0
- tokenizer_config.json +21 -0
README.md
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: testt
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# testt
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [naver-clova-ix/donut-base-finetuned-cord-v2](https://huggingface.co/naver-clova-ix/donut-base-finetuned-cord-v2) on an unknown dataset.
|
| 16 |
+
|
| 17 |
+
## Model description
|
| 18 |
+
|
| 19 |
+
More information needed
|
| 20 |
+
|
| 21 |
+
## Intended uses & limitations
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Training and evaluation data
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training procedure
|
| 30 |
+
|
| 31 |
+
### Training hyperparameters
|
| 32 |
+
|
| 33 |
+
The following hyperparameters were used during training:
|
| 34 |
+
- learning_rate: 2e-05
|
| 35 |
+
- train_batch_size: 4
|
| 36 |
+
- eval_batch_size: 8
|
| 37 |
+
- seed: 42
|
| 38 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 39 |
+
- lr_scheduler_type: linear
|
| 40 |
+
- num_epochs: 20
|
| 41 |
+
|
| 42 |
+
### Training results
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
### Framework versions
|
| 47 |
+
|
| 48 |
+
- Transformers 4.30.1
|
| 49 |
+
- Pytorch 2.0.1+cu117
|
| 50 |
+
- Datasets 2.14.0
|
| 51 |
+
- Tokenizers 0.13.3
|
added_tokens.json
ADDED
|
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s_cashprice>": 57549,
|
| 3 |
+
"</s_changeprice>": 57551,
|
| 4 |
+
"</s_cnt>": 57529,
|
| 5 |
+
"</s_creditcardprice>": 57563,
|
| 6 |
+
"</s_discount_price>": 57557,
|
| 7 |
+
"</s_discountprice>": 57567,
|
| 8 |
+
"</s_emoneyprice>": 57569,
|
| 9 |
+
"</s_etc>": 57541,
|
| 10 |
+
"</s_h_bic>": 57643,
|
| 11 |
+
"</s_h_contactperson>": 57641,
|
| 12 |
+
"</s_h_creditorcity>": 57619,
|
| 13 |
+
"</s_h_creditorcountry>": 57617,
|
| 14 |
+
"</s_h_creditoriban>": 57615,
|
| 15 |
+
"</s_h_creditorname>": 57613,
|
| 16 |
+
"</s_h_creditorpobox>": 57649,
|
| 17 |
+
"</s_h_creditorpostcode>": 57611,
|
| 18 |
+
"</s_h_creditorsalestaxid>": 57609,
|
| 19 |
+
"</s_h_creditorsearch>": 57653,
|
| 20 |
+
"</s_h_creditorstreet>": 57607,
|
| 21 |
+
"</s_h_creditortaxid>": 57621,
|
| 22 |
+
"</s_h_currency1>": 57605,
|
| 23 |
+
"</s_h_deldate>": 57603,
|
| 24 |
+
"</s_h_deliverynotenumber>": 57631,
|
| 25 |
+
"</s_h_discount>": 57639,
|
| 26 |
+
"</s_h_documentdate>": 57601,
|
| 27 |
+
"</s_h_documenttype>": 57599,
|
| 28 |
+
"</s_h_extracharges>": 57597,
|
| 29 |
+
"</s_h_grossamount>": 57595,
|
| 30 |
+
"</s_h_invoicenumber>": 57593,
|
| 31 |
+
"</s_h_invoicerecipient>": 57591,
|
| 32 |
+
"</s_h_netamount1>": 57589,
|
| 33 |
+
"</s_h_ordernumber>": 57623,
|
| 34 |
+
"</s_h_paymentterms>": 57637,
|
| 35 |
+
"</s_h_receiptdate>": 57587,
|
| 36 |
+
"</s_h_recipientsalestaxid>": 57635,
|
| 37 |
+
"</s_h_recipienttaxid>": 57655,
|
| 38 |
+
"</s_h_taxamount1>": 57585,
|
| 39 |
+
"</s_h_taxamount2>": 57627,
|
| 40 |
+
"</s_h_taxamount3>": 57647,
|
| 41 |
+
"</s_h_taxbasisamount1>": 57583,
|
| 42 |
+
"</s_h_taxbasisamount2>": 57629,
|
| 43 |
+
"</s_h_taxbasisamount3>": 57651,
|
| 44 |
+
"</s_h_taxrate1>": 57581,
|
| 45 |
+
"</s_h_taxrate2>": 57625,
|
| 46 |
+
"</s_h_taxrate3>": 57645,
|
| 47 |
+
"</s_h_web>": 57633,
|
| 48 |
+
"</s_itemsubtotal>": 57577,
|
| 49 |
+
"</s_menu>": 57525,
|
| 50 |
+
"</s_menuqty_cnt>": 57555,
|
| 51 |
+
"</s_menutype_cnt>": 57553,
|
| 52 |
+
"</s_nm>": 57527,
|
| 53 |
+
"</s_num>": 57565,
|
| 54 |
+
"</s_othersvc_price>": 57573,
|
| 55 |
+
"</s_price>": 57531,
|
| 56 |
+
"</s_service_price>": 57537,
|
| 57 |
+
"</s_sub>": 57547,
|
| 58 |
+
"</s_sub_total>": 57533,
|
| 59 |
+
"</s_subtotal_price>": 57535,
|
| 60 |
+
"</s_tax_price>": 57539,
|
| 61 |
+
"</s_total>": 57543,
|
| 62 |
+
"</s_total_etc>": 57561,
|
| 63 |
+
"</s_total_price>": 57545,
|
| 64 |
+
"</s_unitprice>": 57559,
|
| 65 |
+
"</s_vatyn>": 57575,
|
| 66 |
+
"</s_void_menu>": 57571,
|
| 67 |
+
"<s_cashprice>": 57550,
|
| 68 |
+
"<s_changeprice>": 57552,
|
| 69 |
+
"<s_cnt>": 57530,
|
| 70 |
+
"<s_cord-v2>": 57579,
|
| 71 |
+
"<s_creditcardprice>": 57564,
|
| 72 |
+
"<s_discount_price>": 57558,
|
| 73 |
+
"<s_discountprice>": 57568,
|
| 74 |
+
"<s_emoneyprice>": 57570,
|
| 75 |
+
"<s_etc>": 57542,
|
| 76 |
+
"<s_h_bic>": 57642,
|
| 77 |
+
"<s_h_contactperson>": 57640,
|
| 78 |
+
"<s_h_creditorcity>": 57618,
|
| 79 |
+
"<s_h_creditorcountry>": 57616,
|
| 80 |
+
"<s_h_creditoriban>": 57614,
|
| 81 |
+
"<s_h_creditorname>": 57612,
|
| 82 |
+
"<s_h_creditorpobox>": 57648,
|
| 83 |
+
"<s_h_creditorpostcode>": 57610,
|
| 84 |
+
"<s_h_creditorsalestaxid>": 57608,
|
| 85 |
+
"<s_h_creditorsearch>": 57652,
|
| 86 |
+
"<s_h_creditorstreet>": 57606,
|
| 87 |
+
"<s_h_creditortaxid>": 57620,
|
| 88 |
+
"<s_h_currency1>": 57604,
|
| 89 |
+
"<s_h_deldate>": 57602,
|
| 90 |
+
"<s_h_deliverynotenumber>": 57630,
|
| 91 |
+
"<s_h_discount>": 57638,
|
| 92 |
+
"<s_h_documentdate>": 57600,
|
| 93 |
+
"<s_h_documenttype>": 57598,
|
| 94 |
+
"<s_h_extracharges>": 57596,
|
| 95 |
+
"<s_h_grossamount>": 57594,
|
| 96 |
+
"<s_h_invoicenumber>": 57592,
|
| 97 |
+
"<s_h_invoicerecipient>": 57590,
|
| 98 |
+
"<s_h_netamount1>": 57588,
|
| 99 |
+
"<s_h_ordernumber>": 57622,
|
| 100 |
+
"<s_h_paymentterms>": 57636,
|
| 101 |
+
"<s_h_receiptdate>": 57586,
|
| 102 |
+
"<s_h_recipientsalestaxid>": 57634,
|
| 103 |
+
"<s_h_recipienttaxid>": 57654,
|
| 104 |
+
"<s_h_taxamount1>": 57584,
|
| 105 |
+
"<s_h_taxamount2>": 57626,
|
| 106 |
+
"<s_h_taxamount3>": 57646,
|
| 107 |
+
"<s_h_taxbasisamount1>": 57582,
|
| 108 |
+
"<s_h_taxbasisamount2>": 57628,
|
| 109 |
+
"<s_h_taxbasisamount3>": 57650,
|
| 110 |
+
"<s_h_taxrate1>": 57580,
|
| 111 |
+
"<s_h_taxrate2>": 57624,
|
| 112 |
+
"<s_h_taxrate3>": 57644,
|
| 113 |
+
"<s_h_web>": 57632,
|
| 114 |
+
"<s_iitcdip>": 57523,
|
| 115 |
+
"<s_itemsubtotal>": 57578,
|
| 116 |
+
"<s_menu>": 57526,
|
| 117 |
+
"<s_menuqty_cnt>": 57556,
|
| 118 |
+
"<s_menutype_cnt>": 57554,
|
| 119 |
+
"<s_nm>": 57528,
|
| 120 |
+
"<s_num>": 57566,
|
| 121 |
+
"<s_othersvc_price>": 57574,
|
| 122 |
+
"<s_price>": 57532,
|
| 123 |
+
"<s_service_price>": 57538,
|
| 124 |
+
"<s_sub>": 57548,
|
| 125 |
+
"<s_sub_total>": 57534,
|
| 126 |
+
"<s_subtotal_price>": 57536,
|
| 127 |
+
"<s_synthdog>": 57524,
|
| 128 |
+
"<s_tax_price>": 57540,
|
| 129 |
+
"<s_total>": 57544,
|
| 130 |
+
"<s_total_etc>": 57562,
|
| 131 |
+
"<s_total_price>": 57546,
|
| 132 |
+
"<s_unitprice>": 57560,
|
| 133 |
+
"<s_vatyn>": 57576,
|
| 134 |
+
"<s_void_menu>": 57572,
|
| 135 |
+
"<sep/>": 57522
|
| 136 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"forced_eos_token_id": 2,
|
| 6 |
+
"pad_token_id": 1,
|
| 7 |
+
"transformers_version": "4.30.1"
|
| 8 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_align_long_axis": false,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_pad": true,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"do_thumbnail": true,
|
| 8 |
+
"image_mean": [
|
| 9 |
+
0.5,
|
| 10 |
+
0.5,
|
| 11 |
+
0.5
|
| 12 |
+
],
|
| 13 |
+
"image_processor_type": "DonutImageProcessor",
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "DonutProcessor",
|
| 20 |
+
"resample": 2,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": [
|
| 23 |
+
720,
|
| 24 |
+
960
|
| 25 |
+
]
|
| 26 |
+
}
|
runs/Aug25_00-39-03_ip-172-31-42-230.eu-central-1.compute.internal/events.out.tfevents.1692923949.ip-172-31-42-230.eu-central-1.compute.internal.20091.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd7fa10181daf1e18d42471f3c6218962636e6925a09fff0ec2d0ddaf232c813
|
| 3 |
+
size 22423
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
|
| 3 |
+
size 1296245
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<s_h_taxrate1>",
|
| 4 |
+
"</s_h_taxrate1>",
|
| 5 |
+
"<s_h_taxbasisamount1>",
|
| 6 |
+
"</s_h_taxbasisamount1>",
|
| 7 |
+
"<s_h_taxamount1>",
|
| 8 |
+
"</s_h_taxamount1>",
|
| 9 |
+
"<s_h_receiptdate>",
|
| 10 |
+
"</s_h_receiptdate>",
|
| 11 |
+
"<s_h_netamount1>",
|
| 12 |
+
"</s_h_netamount1>",
|
| 13 |
+
"<s_h_invoicerecipient>",
|
| 14 |
+
"</s_h_invoicerecipient>",
|
| 15 |
+
"<s_h_invoicenumber>",
|
| 16 |
+
"</s_h_invoicenumber>",
|
| 17 |
+
"<s_h_grossamount>",
|
| 18 |
+
"</s_h_grossamount>",
|
| 19 |
+
"<s_h_extracharges>",
|
| 20 |
+
"</s_h_extracharges>",
|
| 21 |
+
"<s_h_documenttype>",
|
| 22 |
+
"</s_h_documenttype>",
|
| 23 |
+
"<s_h_documentdate>",
|
| 24 |
+
"</s_h_documentdate>",
|
| 25 |
+
"<s_h_deldate>",
|
| 26 |
+
"</s_h_deldate>",
|
| 27 |
+
"<s_h_currency1>",
|
| 28 |
+
"</s_h_currency1>",
|
| 29 |
+
"<s_h_creditorstreet>",
|
| 30 |
+
"</s_h_creditorstreet>",
|
| 31 |
+
"<s_h_creditorsalestaxid>",
|
| 32 |
+
"</s_h_creditorsalestaxid>",
|
| 33 |
+
"<s_h_creditorpostcode>",
|
| 34 |
+
"</s_h_creditorpostcode>",
|
| 35 |
+
"<s_h_creditorname>",
|
| 36 |
+
"</s_h_creditorname>",
|
| 37 |
+
"<s_h_creditoriban>",
|
| 38 |
+
"</s_h_creditoriban>",
|
| 39 |
+
"<s_h_creditorcountry>",
|
| 40 |
+
"</s_h_creditorcountry>",
|
| 41 |
+
"<s_h_creditorcity>",
|
| 42 |
+
"</s_h_creditorcity>",
|
| 43 |
+
"<s_h_creditortaxid>",
|
| 44 |
+
"</s_h_creditortaxid>",
|
| 45 |
+
"<s_h_ordernumber>",
|
| 46 |
+
"</s_h_ordernumber>",
|
| 47 |
+
"<s_h_taxrate2>",
|
| 48 |
+
"</s_h_taxrate2>",
|
| 49 |
+
"<s_h_taxamount2>",
|
| 50 |
+
"</s_h_taxamount2>",
|
| 51 |
+
"<s_h_taxbasisamount2>",
|
| 52 |
+
"</s_h_taxbasisamount2>",
|
| 53 |
+
"<s_h_deliverynotenumber>",
|
| 54 |
+
"</s_h_deliverynotenumber>",
|
| 55 |
+
"<s_h_web>",
|
| 56 |
+
"</s_h_web>",
|
| 57 |
+
"<s_h_recipientsalestaxid>",
|
| 58 |
+
"</s_h_recipientsalestaxid>",
|
| 59 |
+
"<s_h_paymentterms>",
|
| 60 |
+
"</s_h_paymentterms>",
|
| 61 |
+
"<s_h_discount>",
|
| 62 |
+
"</s_h_discount>",
|
| 63 |
+
"<s_h_contactperson>",
|
| 64 |
+
"</s_h_contactperson>",
|
| 65 |
+
"<s_h_bic>",
|
| 66 |
+
"</s_h_bic>",
|
| 67 |
+
"<s_h_taxrate3>",
|
| 68 |
+
"</s_h_taxrate3>",
|
| 69 |
+
"<s_h_taxamount3>",
|
| 70 |
+
"</s_h_taxamount3>",
|
| 71 |
+
"<s_h_creditorpobox>",
|
| 72 |
+
"</s_h_creditorpobox>",
|
| 73 |
+
"<s_h_taxbasisamount3>",
|
| 74 |
+
"</s_h_taxbasisamount3>",
|
| 75 |
+
"<s_h_creditorsearch>",
|
| 76 |
+
"</s_h_creditorsearch>",
|
| 77 |
+
"<s_h_recipienttaxid>",
|
| 78 |
+
"</s_h_recipienttaxid>",
|
| 79 |
+
"<s>",
|
| 80 |
+
"</s>"
|
| 81 |
+
],
|
| 82 |
+
"bos_token": "<s>",
|
| 83 |
+
"cls_token": "<s>",
|
| 84 |
+
"eos_token": "</s>",
|
| 85 |
+
"mask_token": {
|
| 86 |
+
"content": "<mask>",
|
| 87 |
+
"lstrip": true,
|
| 88 |
+
"normalized": true,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false
|
| 91 |
+
},
|
| 92 |
+
"pad_token": "<pad>",
|
| 93 |
+
"sep_token": "</s>",
|
| 94 |
+
"unk_token": "<unk>"
|
| 95 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"mask_token": {
|
| 7 |
+
"__type": "AddedToken",
|
| 8 |
+
"content": "<mask>",
|
| 9 |
+
"lstrip": true,
|
| 10 |
+
"normalized": true,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"single_word": false
|
| 13 |
+
},
|
| 14 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 15 |
+
"pad_token": "<pad>",
|
| 16 |
+
"processor_class": "DonutProcessor",
|
| 17 |
+
"sep_token": "</s>",
|
| 18 |
+
"sp_model_kwargs": {},
|
| 19 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 20 |
+
"unk_token": "<unk>"
|
| 21 |
+
}
|