Upload 5 files
Browse files- preprocessor_config.json +12 -3
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +21 -0
preprocessor_config.json
CHANGED
@@ -1,19 +1,28 @@
|
|
1 |
{
|
2 |
-
"crop_size":
|
|
|
|
|
|
|
3 |
"do_center_crop": false,
|
4 |
"do_normalize": true,
|
|
|
5 |
"do_resize": true,
|
6 |
-
"feature_extractor_type": "DeiTFeatureExtractor",
|
7 |
"image_mean": [
|
8 |
0.5,
|
9 |
0.5,
|
10 |
0.5
|
11 |
],
|
|
|
12 |
"image_std": [
|
13 |
0.5,
|
14 |
0.5,
|
15 |
0.5
|
16 |
],
|
|
|
17 |
"resample": 3,
|
18 |
-
"
|
|
|
|
|
|
|
|
|
19 |
}
|
|
|
1 |
{
|
2 |
+
"crop_size": {
|
3 |
+
"height": 224,
|
4 |
+
"width": 224
|
5 |
+
},
|
6 |
"do_center_crop": false,
|
7 |
"do_normalize": true,
|
8 |
+
"do_rescale": true,
|
9 |
"do_resize": true,
|
|
|
10 |
"image_mean": [
|
11 |
0.5,
|
12 |
0.5,
|
13 |
0.5
|
14 |
],
|
15 |
+
"image_processor_type": "DeiTImageProcessor",
|
16 |
"image_std": [
|
17 |
0.5,
|
18 |
0.5,
|
19 |
0.5
|
20 |
],
|
21 |
+
"processor_class": "TrOCRProcessor",
|
22 |
"resample": 3,
|
23 |
+
"rescale_factor": 0.00392156862745098,
|
24 |
+
"size": {
|
25 |
+
"height": 384,
|
26 |
+
"width": 384
|
27 |
+
}
|
28 |
}
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f5e2fefcf793761a76a6bfb8ad35489f9c203b25557673284b6d032f41043f4
|
3 |
+
size 1356293
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
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": "TrOCRProcessor",
|
17 |
+
"sep_token": "</s>",
|
18 |
+
"sp_model_kwargs": {},
|
19 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
20 |
+
"unk_token": "<unk>"
|
21 |
+
}
|