Bennet1996
commited on
Commit
•
be1782f
1
Parent(s):
977565f
End of training
Browse files- added_tokens.json +17 -0
- generation_config.json +8 -0
- preprocessor_config.json +26 -0
- runs/May10_14-25-06_fcee317add31/events.out.tfevents.1683728709.fcee317add31.362.4 +2 -2
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +0 -0
- tokenizer_config.json +21 -0
added_tokens.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s_Brutto>": 57536,
|
3 |
+
"</s_Geburtsdatum>": 57526,
|
4 |
+
"</s_Name>": 57534,
|
5 |
+
"</s_Netto>": 57532,
|
6 |
+
"</s_Stadt>": 57530,
|
7 |
+
"</s_Straße>": 57528,
|
8 |
+
"<s_Brutto>": 57535,
|
9 |
+
"<s_Geburtsdatum>": 57525,
|
10 |
+
"<s_Name>": 57533,
|
11 |
+
"<s_Netto>": 57531,
|
12 |
+
"<s_Stadt>": 57529,
|
13 |
+
"<s_Straße>": 57527,
|
14 |
+
"<s_iitcdip>": 57523,
|
15 |
+
"<s_synthdog>": 57524,
|
16 |
+
"<sep/>": 57522
|
17 |
+
}
|
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": "4.28.1"
|
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/May10_14-25-06_fcee317add31/events.out.tfevents.1683728709.fcee317add31.362.4
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:295efcdc45a79e97f108628bfcd13c265696d70e0dee23a1e6c5cda01d685727
|
3 |
+
size 9380
|
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 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_Netto>",
|
10 |
+
"</s_Netto>",
|
11 |
+
"<s_Name>",
|
12 |
+
"</s_Name>",
|
13 |
+
"<s_Brutto>",
|
14 |
+
"</s_Brutto>",
|
15 |
+
"<s>",
|
16 |
+
"</s>"
|
17 |
+
],
|
18 |
+
"bos_token": "<s>",
|
19 |
+
"cls_token": "<s>",
|
20 |
+
"eos_token": "</s>",
|
21 |
+
"mask_token": {
|
22 |
+
"content": "<mask>",
|
23 |
+
"lstrip": true,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"pad_token": "<pad>",
|
29 |
+
"sep_token": "</s>",
|
30 |
+
"unk_token": "<unk>"
|
31 |
+
}
|
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 |
+
}
|