Commit
·
4be42b9
1
Parent(s):
9b79c22
Training in progress, epoch 0
Browse files- added_tokens.json +41 -0
- preprocessor_config.json +26 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +21 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s_1_data_rozhdeniya>": 35075,
|
| 3 |
+
"</s_1_data_vydachi>": 35063,
|
| 4 |
+
"</s_1_familiya>": 35067,
|
| 5 |
+
"</s_1_imya>": 35069,
|
| 6 |
+
"</s_1_kod_podrazdeleniya>": 35065,
|
| 7 |
+
"</s_1_mashinnyj_tekst_1>": 35085,
|
| 8 |
+
"</s_1_mashinnyj_tekst_2>": 35087,
|
| 9 |
+
"</s_1_mesto_rozhdeniya1>": 35077,
|
| 10 |
+
"</s_1_mesto_rozhdeniya2>": 35079,
|
| 11 |
+
"</s_1_mesto_rozhdeniya3>": 35089,
|
| 12 |
+
"</s_1_otchestvo>": 35071,
|
| 13 |
+
"</s_1_pasport_vydan1>": 35057,
|
| 14 |
+
"</s_1_pasport_vydan2>": 35061,
|
| 15 |
+
"</s_1_pasport_vydan3>": 35091,
|
| 16 |
+
"</s_1_pol>": 35073,
|
| 17 |
+
"</s_1_seriya_nomer_1>": 35081,
|
| 18 |
+
"</s_1_seriya_nomer_2>": 35083,
|
| 19 |
+
"</s_name>": 35059,
|
| 20 |
+
"<s_1_data_rozhdeniya>": 35074,
|
| 21 |
+
"<s_1_data_vydachi>": 35062,
|
| 22 |
+
"<s_1_familiya>": 35066,
|
| 23 |
+
"<s_1_imya>": 35068,
|
| 24 |
+
"<s_1_kod_podrazdeleniya>": 35064,
|
| 25 |
+
"<s_1_mashinnyj_tekst_1>": 35084,
|
| 26 |
+
"<s_1_mashinnyj_tekst_2>": 35086,
|
| 27 |
+
"<s_1_mesto_rozhdeniya1>": 35076,
|
| 28 |
+
"<s_1_mesto_rozhdeniya2>": 35078,
|
| 29 |
+
"<s_1_mesto_rozhdeniya3>": 35088,
|
| 30 |
+
"<s_1_otchestvo>": 35070,
|
| 31 |
+
"<s_1_pasport_vydan1>": 35056,
|
| 32 |
+
"<s_1_pasport_vydan2>": 35060,
|
| 33 |
+
"<s_1_pasport_vydan3>": 35090,
|
| 34 |
+
"<s_1_pol>": 35072,
|
| 35 |
+
"<s_1_seriya_nomer_1>": 35080,
|
| 36 |
+
"<s_1_seriya_nomer_2>": 35082,
|
| 37 |
+
"<s_500k>": 35054,
|
| 38 |
+
"<s_a4>": 35092,
|
| 39 |
+
"<s_donut_rus>": 35055,
|
| 40 |
+
"<s_name>": 35058
|
| 41 |
+
}
|
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 |
+
1200,
|
| 24 |
+
1600
|
| 25 |
+
]
|
| 26 |
+
}
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef009ae2ede7beded780cfa82e11d2d977473cb6ddf9c3b5bdce3c367497fc01
|
| 3 |
+
size 943862
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
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 |
+
}
|