Training done
Browse files- preprocessor_config.json +5 -7
- tokenizer.json +0 -0
- tokenizer_config.json +2 -2
preprocessor_config.json
CHANGED
@@ -2,15 +2,14 @@
|
|
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,
|
@@ -18,9 +17,8 @@
|
|
18 |
],
|
19 |
"processor_class": "DonutProcessor",
|
20 |
"resample": 2,
|
21 |
-
"
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
}
|
26 |
}
|
|
|
2 |
"do_align_long_axis": false,
|
3 |
"do_normalize": true,
|
4 |
"do_pad": true,
|
|
|
5 |
"do_resize": true,
|
6 |
"do_thumbnail": true,
|
7 |
+
"feature_extractor_type": "DonutFeatureExtractor",
|
8 |
"image_mean": [
|
9 |
0.5,
|
10 |
0.5,
|
11 |
0.5
|
12 |
],
|
|
|
13 |
"image_std": [
|
14 |
0.5,
|
15 |
0.5,
|
|
|
17 |
],
|
18 |
"processor_class": "DonutProcessor",
|
19 |
"resample": 2,
|
20 |
+
"size": [
|
21 |
+
960,
|
22 |
+
1280
|
23 |
+
]
|
|
|
24 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,5 @@
|
|
1 |
{
|
2 |
"bos_token": "<s>",
|
3 |
-
"clean_up_tokenization_spaces": true,
|
4 |
"cls_token": "<s>",
|
5 |
"eos_token": "</s>",
|
6 |
"mask_token": {
|
@@ -11,11 +10,12 @@
|
|
11 |
"rstrip": false,
|
12 |
"single_word": false
|
13 |
},
|
14 |
-
"
|
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 |
}
|
|
|
1 |
{
|
2 |
"bos_token": "<s>",
|
|
|
3 |
"cls_token": "<s>",
|
4 |
"eos_token": "</s>",
|
5 |
"mask_token": {
|
|
|
10 |
"rstrip": false,
|
11 |
"single_word": false
|
12 |
},
|
13 |
+
"name_or_path": "naver-clova-ix/donut-base",
|
14 |
"pad_token": "<pad>",
|
15 |
"processor_class": "DonutProcessor",
|
16 |
"sep_token": "</s>",
|
17 |
"sp_model_kwargs": {},
|
18 |
+
"special_tokens_map_file": null,
|
19 |
"tokenizer_class": "XLMRobertaTokenizer",
|
20 |
"unk_token": "<unk>"
|
21 |
}
|