Upload processor
Browse files- added_tokens.json +82 -0
- preprocessor_config.json +26 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +19 -0
- tokenizer.json +0 -0
- tokenizer_config.json +22 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"''": 57526,
|
| 3 |
+
"1": 57525,
|
| 4 |
+
"<s_iitcdip>": 57523,
|
| 5 |
+
"<s_synthdog>": 57524,
|
| 6 |
+
"<sep/>": 57522,
|
| 7 |
+
"a''1 ": 57582,
|
| 8 |
+
"a''16 ": 57586,
|
| 9 |
+
"a''2 ": 57583,
|
| 10 |
+
"a''4 ": 57584,
|
| 11 |
+
"a''8 ": 57585,
|
| 12 |
+
"a'1 ": 57577,
|
| 13 |
+
"a'16 ": 57581,
|
| 14 |
+
"a'2 ": 57578,
|
| 15 |
+
"a'4 ": 57579,
|
| 16 |
+
"a'8 ": 57580,
|
| 17 |
+
"b''1 ": 57592,
|
| 18 |
+
"b''16 ": 57596,
|
| 19 |
+
"b''2 ": 57593,
|
| 20 |
+
"b''4 ": 57594,
|
| 21 |
+
"b''8 ": 57595,
|
| 22 |
+
"b'1 ": 57587,
|
| 23 |
+
"b'16 ": 57591,
|
| 24 |
+
"b'2 ": 57588,
|
| 25 |
+
"b'4 ": 57589,
|
| 26 |
+
"b'8 ": 57590,
|
| 27 |
+
"c''1 ": 57532,
|
| 28 |
+
"c''16 ": 57536,
|
| 29 |
+
"c''2 ": 57533,
|
| 30 |
+
"c''4 ": 57534,
|
| 31 |
+
"c''8 ": 57535,
|
| 32 |
+
"c'1 ": 57527,
|
| 33 |
+
"c'16 ": 57531,
|
| 34 |
+
"c'2 ": 57528,
|
| 35 |
+
"c'4 ": 57529,
|
| 36 |
+
"c'8 ": 57530,
|
| 37 |
+
"d''1 ": 57542,
|
| 38 |
+
"d''16 ": 57546,
|
| 39 |
+
"d''2 ": 57543,
|
| 40 |
+
"d''4 ": 57544,
|
| 41 |
+
"d''8 ": 57545,
|
| 42 |
+
"d'1 ": 57537,
|
| 43 |
+
"d'16 ": 57541,
|
| 44 |
+
"d'2 ": 57538,
|
| 45 |
+
"d'4 ": 57539,
|
| 46 |
+
"d'8 ": 57540,
|
| 47 |
+
"e''1 ": 57552,
|
| 48 |
+
"e''16 ": 57556,
|
| 49 |
+
"e''2 ": 57553,
|
| 50 |
+
"e''4 ": 57554,
|
| 51 |
+
"e''8 ": 57555,
|
| 52 |
+
"e'1 ": 57547,
|
| 53 |
+
"e'16 ": 57551,
|
| 54 |
+
"e'2 ": 57548,
|
| 55 |
+
"e'4 ": 57549,
|
| 56 |
+
"e'8 ": 57550,
|
| 57 |
+
"f''1 ": 57562,
|
| 58 |
+
"f''16 ": 57566,
|
| 59 |
+
"f''2 ": 57563,
|
| 60 |
+
"f''4 ": 57564,
|
| 61 |
+
"f''8 ": 57565,
|
| 62 |
+
"f'1 ": 57557,
|
| 63 |
+
"f'16 ": 57561,
|
| 64 |
+
"f'2 ": 57558,
|
| 65 |
+
"f'4 ": 57559,
|
| 66 |
+
"f'8 ": 57560,
|
| 67 |
+
"g''1 ": 57572,
|
| 68 |
+
"g''16 ": 57576,
|
| 69 |
+
"g''2 ": 57573,
|
| 70 |
+
"g''4 ": 57574,
|
| 71 |
+
"g''8 ": 57575,
|
| 72 |
+
"g'1 ": 57567,
|
| 73 |
+
"g'16 ": 57571,
|
| 74 |
+
"g'2 ": 57568,
|
| 75 |
+
"g'4 ": 57569,
|
| 76 |
+
"g'8 ": 57570,
|
| 77 |
+
"r1 ": 57597,
|
| 78 |
+
"r16 ": 57601,
|
| 79 |
+
"r2 ": 57598,
|
| 80 |
+
"r4 ": 57599,
|
| 81 |
+
"r8 ": 57600
|
| 82 |
+
}
|
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 |
+
"height": 583,
|
| 24 |
+
"width": 409
|
| 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 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<s_iitcdip>",
|
| 4 |
+
"<s_synthdog>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": "<s>",
|
| 7 |
+
"cls_token": "<s>",
|
| 8 |
+
"eos_token": "</s>",
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "<mask>",
|
| 11 |
+
"lstrip": true,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<pad>",
|
| 17 |
+
"sep_token": "</s>",
|
| 18 |
+
"unk_token": "<unk>"
|
| 19 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"__type": "AddedToken",
|
| 7 |
+
"content": "<mask>",
|
| 8 |
+
"lstrip": true,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 14 |
+
"name_or_path": "./model_5",
|
| 15 |
+
"pad_token": "<pad>",
|
| 16 |
+
"processor_class": "DonutProcessor",
|
| 17 |
+
"sep_token": "</s>",
|
| 18 |
+
"sp_model_kwargs": {},
|
| 19 |
+
"special_tokens_map_file": null,
|
| 20 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 21 |
+
"unk_token": "<unk>"
|
| 22 |
+
}
|