Hugging Face's logo

Bennet1996
/
donut-small

Image-Text-to-Text
Transformers
PyTorch
TensorBoard
vision-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
Bennet1996 commited on
Commit
fd39f79
•
1 Parent(s): bfc946f

End of training

Browse files
Files changed (8) hide show
  1. added_tokens.json +33 -0
  2. generation_config.json +8 -0
  3. preprocessor_config.json +26 -0
  4. runs/May12_12-47-16_f8be8ec88a7a/events.out.tfevents.1683895646.f8be8ec88a7a.1256.0 +2 -2
  5. sentencepiece.bpe.model +3 -0
  6. special_tokens_map.json +39 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +21 -0
added_tokens.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_Brutto>": 57536,
3
+ "</s_Geburtsdatum>": 57526,
4
+ "</s_Gesamt-Brutto>": 57544,
5
+ "</s_Gesamtbrutto (EBeschV)>": 57546,
6
+ "</s_Gesamtbrutto>": 57550,
7
+ "</s_Gesetzl. Netto (EBeschV)>": 57548,
8
+ "</s_Gesetzl. Netto>": 57552,
9
+ "</s_Name>": 57534,
10
+ "</s_Netto-Verdienst>": 57542,
11
+ "</s_Netto>": 57532,
12
+ "</s_Stadt>": 57530,
13
+ "</s_Stpfl. Brutto>": 57538,
14
+ "</s_Straße>": 57528,
15
+ "</s_Summe Nettobez\\u00fcge>": 57540,
16
+ "<s_Brutto>": 57535,
17
+ "<s_Geburtsdatum>": 57525,
18
+ "<s_Gesamt-Brutto>": 57543,
19
+ "<s_Gesamtbrutto (EBeschV)>": 57545,
20
+ "<s_Gesamtbrutto>": 57549,
21
+ "<s_Gesetzl. Netto (EBeschV)>": 57547,
22
+ "<s_Gesetzl. Netto>": 57551,
23
+ "<s_Name>": 57533,
24
+ "<s_Netto-Verdienst>": 57541,
25
+ "<s_Netto>": 57531,
26
+ "<s_Stadt>": 57529,
27
+ "<s_Stpfl. Brutto>": 57537,
28
+ "<s_Straße>": 57527,
29
+ "<s_Summe Nettobez\\u00fcge>": 57539,
30
+ "<s_iitcdip>": 57523,
31
+ "<s_synthdog>": 57524,
32
+ "<sep/>": 57522
33
+ }
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": "4.29.1"
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/May12_12-47-16_f8be8ec88a7a/events.out.tfevents.1683895646.f8be8ec88a7a.1256.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0d16627d1a7208de4b7082c8961b02f1c05ac1c45970061fe561eae41f8fa08
3
- size 8846
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b35c6c5ecc3e10fecf207d59f3fefbefc5c9cdfebf36e3acf9d92cbcb495822
3
+ size 9200
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 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s_Geburtsdatum>",
4
+ "</s_Geburtsdatum>",
5
+ "<s_Straße>",
6
+ "</s_Straße>",
7
+ "<s_Stadt>",
8
+ "</s_Stadt>",
9
+ "<s_Name>",
10
+ "</s_Name>",
11
+ "<s_Stpfl. Brutto>",
12
+ "</s_Stpfl. Brutto>",
13
+ "<s_Summe Nettobez\\u00fcge>",
14
+ "</s_Summe Nettobez\\u00fcge>",
15
+ "<s_Netto-Verdienst>",
16
+ "</s_Netto-Verdienst>",
17
+ "<s_Gesamt-Brutto>",
18
+ "</s_Gesamt-Brutto>",
19
+ "<s_Gesamtbrutto>",
20
+ "</s_Gesamtbrutto>",
21
+ "<s_Gesetzl. Netto>",
22
+ "</s_Gesetzl. Netto>",
23
+ "<s>",
24
+ "</s>"
25
+ ],
26
+ "bos_token": "<s>",
27
+ "cls_token": "<s>",
28
+ "eos_token": "</s>",
29
+ "mask_token": {
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "pad_token": "<pad>",
37
+ "sep_token": "</s>",
38
+ "unk_token": "<unk>"
39
+ }
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
+ }