nielsr HF staff commited on
Commit
b5c526c
1 Parent(s): 7511a4d

Upload processor

Browse files
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_align_long_axis": false,
3
+ "do_crop_margin": true,
4
+ "do_normalize": true,
5
+ "do_pad": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "do_thumbnail": true,
9
+ "image_mean": [
10
+ 0.485,
11
+ 0.456,
12
+ 0.406
13
+ ],
14
+ "image_processor_type": "NougatImageProcessor",
15
+ "image_std": [
16
+ 0.229,
17
+ 0.224,
18
+ 0.225
19
+ ],
20
+ "processor_class": "NougatProcessor",
21
+ "resample": 2,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "height": 896,
25
+ "width": 672
26
+ }
27
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": false,
4
+ "eos_token": "</s>",
5
+ "max_length": 3584,
6
+ "model_max_length": 3584,
7
+ "pad_to_multiple_of": null,
8
+ "pad_token": "<pad>",
9
+ "pad_token_type_id": 0,
10
+ "padding_side": "right",
11
+ "processor_class": "NougatProcessor",
12
+ "stride": 0,
13
+ "tokenizer_class": "NougatTokenizer",
14
+ "truncation_side": "right",
15
+ "truncation_strategy": "longest_first",
16
+ "unk_token": "<unk>",
17
+ "vocab_file": null
18
+ }