Commit
•
8d40eac
1
Parent(s):
3d11f88
End of training
Browse files- README.md +74 -0
- added_tokens.json +45 -0
- generation_config.json +8 -0
- preprocessor_config.json +26 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +311 -0
- tokenizer.json +0 -0
- tokenizer_config.json +444 -0
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: naver-clova-ix/donut-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- imagefolder
|
| 8 |
+
model-index:
|
| 9 |
+
- name: donut-base-vishnu3
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# donut-base-vishnu3
|
| 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 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.7699
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 2e-05
|
| 40 |
+
- train_batch_size: 2
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 15
|
| 46 |
+
- mixed_precision_training: Native AMP
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
+
| 3.4209 | 1.0 | 127 | 2.1796 |
|
| 53 |
+
| 2.2026 | 2.0 | 254 | 1.5003 |
|
| 54 |
+
| 1.3437 | 3.0 | 381 | 1.2493 |
|
| 55 |
+
| 1.5722 | 4.0 | 508 | 1.1311 |
|
| 56 |
+
| 0.8412 | 5.0 | 635 | 1.0430 |
|
| 57 |
+
| 0.4204 | 6.0 | 762 | 0.9765 |
|
| 58 |
+
| 0.4769 | 7.0 | 889 | 0.9437 |
|
| 59 |
+
| 0.2852 | 8.0 | 1016 | 0.8951 |
|
| 60 |
+
| 0.4611 | 9.0 | 1143 | 0.8431 |
|
| 61 |
+
| 0.2971 | 10.0 | 1270 | 0.8496 |
|
| 62 |
+
| 0.2414 | 11.0 | 1397 | 0.8118 |
|
| 63 |
+
| 0.3451 | 12.0 | 1524 | 0.7813 |
|
| 64 |
+
| 0.1289 | 13.0 | 1651 | 0.7743 |
|
| 65 |
+
| 0.1248 | 14.0 | 1778 | 0.7769 |
|
| 66 |
+
| 0.122 | 15.0 | 1905 | 0.7699 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- Transformers 4.35.0
|
| 72 |
+
- Pytorch 2.1.0+cu118
|
| 73 |
+
- Datasets 2.14.6
|
| 74 |
+
- Tokenizers 0.14.1
|
added_tokens.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s_DOB>": 57557,
|
| 3 |
+
"</s_POB>": 57532,
|
| 4 |
+
"</s_POB_city>": 57541,
|
| 5 |
+
"</s_POB_province>": 57563,
|
| 6 |
+
"</s_child_first_name>": 57531,
|
| 7 |
+
"</s_child_last_name>": 57560,
|
| 8 |
+
"</s_child_middle_name>": 57553,
|
| 9 |
+
"</s_city>": 57533,
|
| 10 |
+
"</s_father_first_name>": 57530,
|
| 11 |
+
"</s_father_last_name>": 57551,
|
| 12 |
+
"</s_father_middle_name>": 57564,
|
| 13 |
+
"</s_father_nationalty>": 57547,
|
| 14 |
+
"</s_father_religion>": 57528,
|
| 15 |
+
"</s_local_reg_no>": 57555,
|
| 16 |
+
"</s_mother_first_name>": 57546,
|
| 17 |
+
"</s_mother_last_name>": 57544,
|
| 18 |
+
"</s_mother_middle_name>": 57550,
|
| 19 |
+
"</s_mother_nationalty>": 57554,
|
| 20 |
+
"</s_mother_religion>": 57561,
|
| 21 |
+
"</s_province>": 57562,
|
| 22 |
+
"<s_DOB>": 57542,
|
| 23 |
+
"<s_POB>": 57537,
|
| 24 |
+
"<s_POB_city>": 57540,
|
| 25 |
+
"<s_POB_province>": 57543,
|
| 26 |
+
"<s_child_first_name>": 57548,
|
| 27 |
+
"<s_child_last_name>": 57538,
|
| 28 |
+
"<s_child_middle_name>": 57539,
|
| 29 |
+
"<s_city>": 57545,
|
| 30 |
+
"<s_father_first_name>": 57535,
|
| 31 |
+
"<s_father_last_name>": 57527,
|
| 32 |
+
"<s_father_middle_name>": 57549,
|
| 33 |
+
"<s_father_nationalty>": 57558,
|
| 34 |
+
"<s_father_religion>": 57552,
|
| 35 |
+
"<s_iitcdip>": 57523,
|
| 36 |
+
"<s_local_reg_no>": 57529,
|
| 37 |
+
"<s_mother_first_name>": 57559,
|
| 38 |
+
"<s_mother_last_name>": 57526,
|
| 39 |
+
"<s_mother_middle_name>": 57536,
|
| 40 |
+
"<s_mother_nationalty>": 57556,
|
| 41 |
+
"<s_mother_religion>": 57534,
|
| 42 |
+
"<s_province>": 57525,
|
| 43 |
+
"<s_synthdog>": 57524,
|
| 44 |
+
"<sep/>": 57522
|
| 45 |
+
}
|
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": "4.35.0"
|
| 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 |
+
800,
|
| 24 |
+
1200
|
| 25 |
+
]
|
| 26 |
+
}
|
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 +1,311 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<s_province>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "<s_mother_last_name>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"content": "<s_father_last_name>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"content": "</s_father_religion>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"content": "<s_local_reg_no>",
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"normalized": false,
|
| 35 |
+
"rstrip": false,
|
| 36 |
+
"single_word": false
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"content": "</s_father_first_name>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"content": "</s_child_first_name>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"content": "</s_POB>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"content": "</s_city>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"content": "<s_mother_religion>",
|
| 68 |
+
"lstrip": false,
|
| 69 |
+
"normalized": false,
|
| 70 |
+
"rstrip": false,
|
| 71 |
+
"single_word": false
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"content": "<s_father_first_name>",
|
| 75 |
+
"lstrip": false,
|
| 76 |
+
"normalized": false,
|
| 77 |
+
"rstrip": false,
|
| 78 |
+
"single_word": false
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"content": "<s_mother_middle_name>",
|
| 82 |
+
"lstrip": false,
|
| 83 |
+
"normalized": false,
|
| 84 |
+
"rstrip": false,
|
| 85 |
+
"single_word": false
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"content": "<s_POB>",
|
| 89 |
+
"lstrip": false,
|
| 90 |
+
"normalized": false,
|
| 91 |
+
"rstrip": false,
|
| 92 |
+
"single_word": false
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"content": "<s_child_last_name>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"content": "<s_child_middle_name>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"content": "<s_POB_city>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"content": "</s_POB_city>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"content": "<s_DOB>",
|
| 124 |
+
"lstrip": false,
|
| 125 |
+
"normalized": false,
|
| 126 |
+
"rstrip": false,
|
| 127 |
+
"single_word": false
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"content": "<s_POB_province>",
|
| 131 |
+
"lstrip": false,
|
| 132 |
+
"normalized": false,
|
| 133 |
+
"rstrip": false,
|
| 134 |
+
"single_word": false
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"content": "</s_mother_last_name>",
|
| 138 |
+
"lstrip": false,
|
| 139 |
+
"normalized": false,
|
| 140 |
+
"rstrip": false,
|
| 141 |
+
"single_word": false
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"content": "<s_city>",
|
| 145 |
+
"lstrip": false,
|
| 146 |
+
"normalized": false,
|
| 147 |
+
"rstrip": false,
|
| 148 |
+
"single_word": false
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"content": "<s>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"content": "</s_mother_first_name>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"content": "</s_father_nationalty>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"content": "<s_child_first_name>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"content": "<s_father_middle_name>",
|
| 180 |
+
"lstrip": false,
|
| 181 |
+
"normalized": false,
|
| 182 |
+
"rstrip": false,
|
| 183 |
+
"single_word": false
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"content": "</s_mother_middle_name>",
|
| 187 |
+
"lstrip": false,
|
| 188 |
+
"normalized": false,
|
| 189 |
+
"rstrip": false,
|
| 190 |
+
"single_word": false
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"content": "</s_father_last_name>",
|
| 194 |
+
"lstrip": false,
|
| 195 |
+
"normalized": false,
|
| 196 |
+
"rstrip": false,
|
| 197 |
+
"single_word": false
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"content": "<s_father_religion>",
|
| 201 |
+
"lstrip": false,
|
| 202 |
+
"normalized": false,
|
| 203 |
+
"rstrip": false,
|
| 204 |
+
"single_word": false
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"content": "</s_child_middle_name>",
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"normalized": false,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"content": "</s_mother_nationalty>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"content": "</s>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"content": "</s_local_reg_no>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"content": "<s_mother_nationalty>",
|
| 236 |
+
"lstrip": false,
|
| 237 |
+
"normalized": false,
|
| 238 |
+
"rstrip": false,
|
| 239 |
+
"single_word": false
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"content": "</s_DOB>",
|
| 243 |
+
"lstrip": false,
|
| 244 |
+
"normalized": false,
|
| 245 |
+
"rstrip": false,
|
| 246 |
+
"single_word": false
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"content": "<s_father_nationalty>",
|
| 250 |
+
"lstrip": false,
|
| 251 |
+
"normalized": false,
|
| 252 |
+
"rstrip": false,
|
| 253 |
+
"single_word": false
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"content": "<s_mother_first_name>",
|
| 257 |
+
"lstrip": false,
|
| 258 |
+
"normalized": false,
|
| 259 |
+
"rstrip": false,
|
| 260 |
+
"single_word": false
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"content": "</s_child_last_name>",
|
| 264 |
+
"lstrip": false,
|
| 265 |
+
"normalized": false,
|
| 266 |
+
"rstrip": false,
|
| 267 |
+
"single_word": false
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"content": "</s_mother_religion>",
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"normalized": false,
|
| 273 |
+
"rstrip": false,
|
| 274 |
+
"single_word": false
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"content": "</s_province>",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"content": "</s_POB_province>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"content": "</s_father_middle_name>",
|
| 292 |
+
"lstrip": false,
|
| 293 |
+
"normalized": false,
|
| 294 |
+
"rstrip": false,
|
| 295 |
+
"single_word": false
|
| 296 |
+
}
|
| 297 |
+
],
|
| 298 |
+
"bos_token": "<s>",
|
| 299 |
+
"cls_token": "<s>",
|
| 300 |
+
"eos_token": "</s>",
|
| 301 |
+
"mask_token": {
|
| 302 |
+
"content": "<mask>",
|
| 303 |
+
"lstrip": true,
|
| 304 |
+
"normalized": true,
|
| 305 |
+
"rstrip": false,
|
| 306 |
+
"single_word": false
|
| 307 |
+
},
|
| 308 |
+
"pad_token": "<pad>",
|
| 309 |
+
"sep_token": "</s>",
|
| 310 |
+
"unk_token": "<unk>"
|
| 311 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,444 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"57521": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"57522": {
|
| 44 |
+
"content": "<sep/>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"57523": {
|
| 52 |
+
"content": "<s_iitcdip>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"57524": {
|
| 60 |
+
"content": "<s_synthdog>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"57525": {
|
| 68 |
+
"content": "<s_province>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"57526": {
|
| 76 |
+
"content": "<s_mother_last_name>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"57527": {
|
| 84 |
+
"content": "<s_father_last_name>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"57528": {
|
| 92 |
+
"content": "</s_father_religion>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"57529": {
|
| 100 |
+
"content": "<s_local_reg_no>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"57530": {
|
| 108 |
+
"content": "</s_father_first_name>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"57531": {
|
| 116 |
+
"content": "</s_child_first_name>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"57532": {
|
| 124 |
+
"content": "</s_POB>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"57533": {
|
| 132 |
+
"content": "</s_city>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"57534": {
|
| 140 |
+
"content": "<s_mother_religion>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"57535": {
|
| 148 |
+
"content": "<s_father_first_name>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"57536": {
|
| 156 |
+
"content": "<s_mother_middle_name>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"57537": {
|
| 164 |
+
"content": "<s_POB>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"57538": {
|
| 172 |
+
"content": "<s_child_last_name>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"57539": {
|
| 180 |
+
"content": "<s_child_middle_name>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"57540": {
|
| 188 |
+
"content": "<s_POB_city>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"57541": {
|
| 196 |
+
"content": "</s_POB_city>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"57542": {
|
| 204 |
+
"content": "<s_DOB>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"57543": {
|
| 212 |
+
"content": "<s_POB_province>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"57544": {
|
| 220 |
+
"content": "</s_mother_last_name>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"57545": {
|
| 228 |
+
"content": "<s_city>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"57546": {
|
| 236 |
+
"content": "</s_mother_first_name>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"57547": {
|
| 244 |
+
"content": "</s_father_nationalty>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"57548": {
|
| 252 |
+
"content": "<s_child_first_name>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"57549": {
|
| 260 |
+
"content": "<s_father_middle_name>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"57550": {
|
| 268 |
+
"content": "</s_mother_middle_name>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"57551": {
|
| 276 |
+
"content": "</s_father_last_name>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"57552": {
|
| 284 |
+
"content": "<s_father_religion>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"57553": {
|
| 292 |
+
"content": "</s_child_middle_name>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"57554": {
|
| 300 |
+
"content": "</s_mother_nationalty>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"57555": {
|
| 308 |
+
"content": "</s_local_reg_no>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"57556": {
|
| 316 |
+
"content": "<s_mother_nationalty>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"57557": {
|
| 324 |
+
"content": "</s_DOB>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"57558": {
|
| 332 |
+
"content": "<s_father_nationalty>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"57559": {
|
| 340 |
+
"content": "<s_mother_first_name>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"57560": {
|
| 348 |
+
"content": "</s_child_last_name>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"57561": {
|
| 356 |
+
"content": "</s_mother_religion>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"57562": {
|
| 364 |
+
"content": "</s_province>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"57563": {
|
| 372 |
+
"content": "</s_POB_province>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"57564": {
|
| 380 |
+
"content": "</s_father_middle_name>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
}
|
| 387 |
+
},
|
| 388 |
+
"additional_special_tokens": [
|
| 389 |
+
"<s_province>",
|
| 390 |
+
"<s_mother_last_name>",
|
| 391 |
+
"<s_father_last_name>",
|
| 392 |
+
"</s_father_religion>",
|
| 393 |
+
"<s_local_reg_no>",
|
| 394 |
+
"</s_father_first_name>",
|
| 395 |
+
"</s_child_first_name>",
|
| 396 |
+
"</s_POB>",
|
| 397 |
+
"</s_city>",
|
| 398 |
+
"<s_mother_religion>",
|
| 399 |
+
"<s_father_first_name>",
|
| 400 |
+
"<s_mother_middle_name>",
|
| 401 |
+
"<s_POB>",
|
| 402 |
+
"<s_child_last_name>",
|
| 403 |
+
"<s_child_middle_name>",
|
| 404 |
+
"<s_POB_city>",
|
| 405 |
+
"</s_POB_city>",
|
| 406 |
+
"<s_DOB>",
|
| 407 |
+
"<s_POB_province>",
|
| 408 |
+
"</s_mother_last_name>",
|
| 409 |
+
"<s_city>",
|
| 410 |
+
"<s>",
|
| 411 |
+
"</s_mother_first_name>",
|
| 412 |
+
"</s_father_nationalty>",
|
| 413 |
+
"<s_child_first_name>",
|
| 414 |
+
"<s_father_middle_name>",
|
| 415 |
+
"</s_mother_middle_name>",
|
| 416 |
+
"</s_father_last_name>",
|
| 417 |
+
"<s_father_religion>",
|
| 418 |
+
"</s_child_middle_name>",
|
| 419 |
+
"</s_mother_nationalty>",
|
| 420 |
+
"</s>",
|
| 421 |
+
"</s_local_reg_no>",
|
| 422 |
+
"<s_mother_nationalty>",
|
| 423 |
+
"</s_DOB>",
|
| 424 |
+
"<s_father_nationalty>",
|
| 425 |
+
"<s_mother_first_name>",
|
| 426 |
+
"</s_child_last_name>",
|
| 427 |
+
"</s_mother_religion>",
|
| 428 |
+
"</s_province>",
|
| 429 |
+
"</s_POB_province>",
|
| 430 |
+
"</s_father_middle_name>"
|
| 431 |
+
],
|
| 432 |
+
"bos_token": "<s>",
|
| 433 |
+
"clean_up_tokenization_spaces": true,
|
| 434 |
+
"cls_token": "<s>",
|
| 435 |
+
"eos_token": "</s>",
|
| 436 |
+
"mask_token": "<mask>",
|
| 437 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 438 |
+
"pad_token": "<pad>",
|
| 439 |
+
"processor_class": "DonutProcessor",
|
| 440 |
+
"sep_token": "</s>",
|
| 441 |
+
"sp_model_kwargs": {},
|
| 442 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 443 |
+
"unk_token": "<unk>"
|
| 444 |
+
}
|