Training in progress, epoch 0
Browse files- preprocessor_config.json +4 -4
- tokenizer.json +17 -3
- tokenizer_config.json +1 -1
preprocessor_config.json
CHANGED
@@ -19,8 +19,8 @@
|
|
19 |
"processor_class": "DonutProcessor",
|
20 |
"resample": 2,
|
21 |
"rescale_factor": 0.00392156862745098,
|
22 |
-
"size":
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
}
|
|
|
19 |
"processor_class": "DonutProcessor",
|
20 |
"resample": 2,
|
21 |
"rescale_factor": 0.00392156862745098,
|
22 |
+
"size": [
|
23 |
+
1667,
|
24 |
+
1191
|
25 |
+
]
|
26 |
}
|
tokenizer.json
CHANGED
@@ -1,7 +1,21 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
@@ -568,7 +582,7 @@
|
|
568 |
"lstrip": false,
|
569 |
"rstrip": false,
|
570 |
"normalized": true,
|
571 |
-
"special":
|
572 |
},
|
573 |
{
|
574 |
"id": 57580,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 768,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
+
"padding": {
|
10 |
+
"strategy": {
|
11 |
+
"Fixed": 768
|
12 |
+
},
|
13 |
+
"direction": "Right",
|
14 |
+
"pad_to_multiple_of": null,
|
15 |
+
"pad_id": 1,
|
16 |
+
"pad_type_id": 0,
|
17 |
+
"pad_token": "<pad>"
|
18 |
+
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
|
|
582 |
"lstrip": false,
|
583 |
"rstrip": false,
|
584 |
"normalized": true,
|
585 |
+
"special": false
|
586 |
},
|
587 |
{
|
588 |
"id": 57580,
|
tokenizer_config.json
CHANGED
@@ -502,7 +502,7 @@
|
|
502 |
"normalized": true,
|
503 |
"rstrip": false,
|
504 |
"single_word": false,
|
505 |
-
"special":
|
506 |
},
|
507 |
"57580": {
|
508 |
"content": "<s_header>",
|
|
|
502 |
"normalized": true,
|
503 |
"rstrip": false,
|
504 |
"single_word": false,
|
505 |
+
"special": false
|
506 |
},
|
507 |
"57580": {
|
508 |
"content": "<s_header>",
|