Hugging Face's logo

acceler-technology
/
dev-lhdn-parse-donut-model

Image-to-Text
Transformers
Safetensors
vision-encoder-decoder
image-text-to-text
donut
document-parsing
lhdn
ebc
Model card Files
xet
 Community
kwyong commited on
Commit
9d5338f
·
verified ·
1 Parent(s): 8522f91

Robust set training 1 (3 Epoch)

Browse files
Files changed (4) hide show
  1. preprocessor_config.json +4 -4
  2. special_tokens_map.json +4 -4
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +9 -2
preprocessor_config.json CHANGED
@@ -19,8 +19,8 @@
19
  "processor_class": "DonutProcessor",
20
  "resample": 2,
21
  "rescale_factor": 0.00392156862745098,
22
- "size": [
23
- 1800,
24
- 1350
25
- ]
26
  }
 
19
  "processor_class": "DonutProcessor",
20
  "resample": 2,
21
  "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "height": 1350,
24
+ "width": 1800
25
+ }
26
  }
special_tokens_map.json CHANGED
@@ -6,21 +6,21 @@
6
  "bos_token": {
7
  "content": "<s>",
8
  "lstrip": false,
9
- "normalized": false,
10
  "rstrip": false,
11
  "single_word": false
12
  },
13
  "cls_token": {
14
  "content": "<s>",
15
  "lstrip": false,
16
- "normalized": false,
17
  "rstrip": false,
18
  "single_word": false
19
  },
20
  "eos_token": {
21
  "content": "</s>",
22
  "lstrip": false,
23
- "normalized": false,
24
  "rstrip": false,
25
  "single_word": false
26
  },
@@ -41,7 +41,7 @@
41
  "sep_token": {
42
  "content": "</s>",
43
  "lstrip": false,
44
- "normalized": false,
45
  "rstrip": false,
46
  "single_word": false
47
  },
 
6
  "bos_token": {
7
  "content": "<s>",
8
  "lstrip": false,
9
+ "normalized": true,
10
  "rstrip": false,
11
  "single_word": false
12
  },
13
  "cls_token": {
14
  "content": "<s>",
15
  "lstrip": false,
16
+ "normalized": true,
17
  "rstrip": false,
18
  "single_word": false
19
  },
20
  "eos_token": {
21
  "content": "</s>",
22
  "lstrip": false,
23
+ "normalized": true,
24
  "rstrip": false,
25
  "single_word": false
26
  },
 
41
  "sep_token": {
42
  "content": "</s>",
43
  "lstrip": false,
44
+ "normalized": true,
45
  "rstrip": false,
46
  "single_word": false
47
  },
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -6,7 +6,7 @@
6
  "normalized": true,
7
  "rstrip": false,
8
  "single_word": false,
9
- "special": false
10
  },
11
  "1": {
12
  "content": "<pad>",
@@ -22,7 +22,7 @@
22
  "normalized": true,
23
  "rstrip": false,
24
  "single_word": false,
25
- "special": false
26
  },
27
  "3": {
28
  "content": "<unk>",
@@ -267,11 +267,18 @@
267
  "eos_token": "</s>",
268
  "extra_special_tokens": {},
269
  "mask_token": "<mask>",
 
270
  "model_max_length": 1000000000000000019884624838656,
 
271
  "pad_token": "<pad>",
 
 
272
  "processor_class": "DonutProcessor",
273
  "sep_token": "</s>",
274
  "sp_model_kwargs": {},
 
275
  "tokenizer_class": "XLMRobertaTokenizer",
 
 
276
  "unk_token": "<unk>"
277
  }
 
6
  "normalized": true,
7
  "rstrip": false,
8
  "single_word": false,
9
+ "special": true
10
  },
11
  "1": {
12
  "content": "<pad>",
 
22
  "normalized": true,
23
  "rstrip": false,
24
  "single_word": false,
25
+ "special": true
26
  },
27
  "3": {
28
  "content": "<unk>",
 
267
  "eos_token": "</s>",
268
  "extra_special_tokens": {},
269
  "mask_token": "<mask>",
270
+ "max_length": 1000,
271
  "model_max_length": 1000000000000000019884624838656,
272
+ "pad_to_multiple_of": null,
273
  "pad_token": "<pad>",
274
+ "pad_token_type_id": 0,
275
+ "padding_side": "right",
276
  "processor_class": "DonutProcessor",
277
  "sep_token": "</s>",
278
  "sp_model_kwargs": {},
279
+ "stride": 0,
280
  "tokenizer_class": "XLMRobertaTokenizer",
281
+ "truncation_side": "right",
282
+ "truncation_strategy": "longest_first",
283
  "unk_token": "<unk>"
284
  }