Hugging Face's logo

microsoft
/
git-base-textvqa

Visual Question Answering
Transformers
PyTorch
Safetensors
English
git
image-text-to-text
vision
Model card Files Community
1
nielsr HF staff commited on
Commit
5692cfc
•
1 Parent(s): c3a375d

Upload processor

Browse files
Files changed (3) hide show
  1. preprocessor_config.json +9 -9
  2. tokenizer.json +10 -10
  3. tokenizer_config.json +4 -0
preprocessor_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "crop_size": {
3
- "height": 224,
4
- "width": 224
5
  },
6
  "do_center_crop": true,
7
  "do_convert_rgb": true,
@@ -9,20 +9,20 @@
9
  "do_rescale": true,
10
  "do_resize": true,
11
  "image_mean": [
12
- 0.485,
13
- 0.456,
14
- 0.406
15
  ],
16
  "image_processor_type": "CLIPImageProcessor",
17
  "image_std": [
18
- 0.229,
19
- 0.224,
20
- 0.225
21
  ],
22
  "processor_class": "GitProcessor",
23
  "resample": 3,
24
  "rescale_factor": 0.00392156862745098,
25
  "size": {
26
- "shortest_edge": 224
27
  }
28
  }
 
1
  {
2
  "crop_size": {
3
+ "height": 480,
4
+ "width": 480
5
  },
6
  "do_center_crop": true,
7
  "do_convert_rgb": true,
 
9
  "do_rescale": true,
10
  "do_resize": true,
11
  "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
  ],
16
  "image_processor_type": "CLIPImageProcessor",
17
  "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
  ],
22
  "processor_class": "GitProcessor",
23
  "resample": 3,
24
  "rescale_factor": 0.00392156862745098,
25
  "size": {
26
+ "shortest_edge": 480
27
  }
28
  }
tokenizer.json CHANGED
@@ -5,48 +5,48 @@
5
  "added_tokens": [
6
  {
7
  "id": 0,
8
- "special": true,
9
  "content": "[PAD]",
10
  "single_word": false,
11
  "lstrip": false,
12
  "rstrip": false,
13
- "normalized": false
 
14
  },
15
  {
16
  "id": 100,
17
- "special": true,
18
  "content": "[UNK]",
19
  "single_word": false,
20
  "lstrip": false,
21
  "rstrip": false,
22
- "normalized": false
 
23
  },
24
  {
25
  "id": 101,
26
- "special": true,
27
  "content": "[CLS]",
28
  "single_word": false,
29
  "lstrip": false,
30
  "rstrip": false,
31
- "normalized": false
 
32
  },
33
  {
34
  "id": 102,
35
- "special": true,
36
  "content": "[SEP]",
37
  "single_word": false,
38
  "lstrip": false,
39
  "rstrip": false,
40
- "normalized": false
 
41
  },
42
  {
43
  "id": 103,
44
- "special": true,
45
  "content": "[MASK]",
46
  "single_word": false,
47
  "lstrip": false,
48
  "rstrip": false,
49
- "normalized": false
 
50
  }
51
  ],
52
  "normalizer": {
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
 
8
  "content": "[PAD]",
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
  },
15
  {
16
  "id": 100,
 
17
  "content": "[UNK]",
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
  },
24
  {
25
  "id": 101,
 
26
  "content": "[CLS]",
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
  },
33
  {
34
  "id": 102,
 
35
  "content": "[SEP]",
36
  "single_word": false,
37
  "lstrip": false,
38
  "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
  },
42
  {
43
  "id": 103,
 
44
  "content": "[MASK]",
45
  "single_word": false,
46
  "lstrip": false,
47
  "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
  }
51
  ],
52
  "normalizer": {
tokenizer_config.json CHANGED
@@ -2,6 +2,10 @@
2
  "cls_token": "[CLS]",
3
  "do_lower_case": true,
4
  "mask_token": "[MASK]",
 
 
 
 
5
  "model_max_length": 512,
6
  "name_or_path": "bert-base-uncased",
7
  "pad_token": "[PAD]",
 
2
  "cls_token": "[CLS]",
3
  "do_lower_case": true,
4
  "mask_token": "[MASK]",
5
+ "model_input_names": [
6
+ "input_ids",
7
+ "attention_mask"
8
+ ],
9
  "model_max_length": 512,
10
  "name_or_path": "bert-base-uncased",
11
  "pad_token": "[PAD]",