sylvain471 commited on
Commit
a636e89
1 Parent(s): 841d846

Upload processor

Browse files
added_tokens.json CHANGED
@@ -1,5 +1,10 @@
1
  {
 
 
 
 
2
  "<s_iitcdip>": 57523,
3
  "<s_synthdog>": 57524,
 
4
  "<sep/>": 57522
5
  }
 
1
  {
2
+ "</s_carburant>": 57526,
3
+ "</s_volume>": 57528,
4
+ "<s_carburant>": 57525,
5
+ "<s_fuel-v2>": 57529,
6
  "<s_iitcdip>": 57523,
7
  "<s_synthdog>": 57524,
8
+ "<s_volume>": 57527,
9
  "<sep/>": 57522
10
  }
preprocessor_config.json CHANGED
@@ -1,5 +1,23 @@
1
  {
2
- "do_align_long_axis": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "do_normalize": true,
4
  "do_pad": true,
5
  "do_rescale": true,
@@ -19,8 +37,8 @@
19
  "processor_class": "DonutProcessor",
20
  "resample": 2,
21
  "rescale_factor": 0.00392156862745098,
22
- "size": {
23
- "height": 2560,
24
- "width": 1920
25
- }
26
  }
 
1
  {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "do_thumbnail",
8
+ "do_align_long_axis",
9
+ "do_pad",
10
+ "random_padding",
11
+ "do_rescale",
12
+ "rescale_factor",
13
+ "do_normalize",
14
+ "image_mean",
15
+ "image_std",
16
+ "return_tensors",
17
+ "data_format",
18
+ "input_data_format"
19
+ ],
20
+ "do_align_long_axis": false,
21
  "do_normalize": true,
22
  "do_pad": true,
23
  "do_rescale": true,
 
37
  "processor_class": "DonutProcessor",
38
  "resample": 2,
39
  "rescale_factor": 0.00392156862745098,
40
+ "size": [
41
+ 960,
42
+ 1280
43
+ ]
44
  }
tokenizer.json CHANGED
@@ -74,6 +74,51 @@
74
  "rstrip": false,
75
  "normalized": false,
76
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
77
  }
78
  ],
79
  "normalizer": {
 
74
  "rstrip": false,
75
  "normalized": false,
76
  "special": true
77
+ },
78
+ {
79
+ "id": 57525,
80
+ "content": "<s_carburant>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": true,
85
+ "special": false
86
+ },
87
+ {
88
+ "id": 57526,
89
+ "content": "</s_carburant>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": true,
94
+ "special": false
95
+ },
96
+ {
97
+ "id": 57527,
98
+ "content": "<s_volume>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": true,
103
+ "special": false
104
+ },
105
+ {
106
+ "id": 57528,
107
+ "content": "</s_volume>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": true,
112
+ "special": false
113
+ },
114
+ {
115
+ "id": 57529,
116
+ "content": "<s_fuel-v2>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": true,
121
+ "special": false
122
  }
123
  ],
124
  "normalizer": {
tokenizer_config.json CHANGED
@@ -63,6 +63,46 @@
63
  "rstrip": false,
64
  "single_word": false,
65
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66
  }
67
  },
68
  "additional_special_tokens": [
 
63
  "rstrip": false,
64
  "single_word": false,
65
  "special": true
66
+ },
67
+ "57525": {
68
+ "content": "<s_carburant>",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "57526": {
76
+ "content": "</s_carburant>",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "57527": {
84
+ "content": "<s_volume>",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "57528": {
92
+ "content": "</s_volume>",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "57529": {
100
+ "content": "<s_fuel-v2>",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
  }
107
  },
108
  "additional_special_tokens": [