Hugging Face's logo

quadranttechnologies
/
qhub-blip-image-captioning-finetuned

Image-to-Text
Transformers
PyTorch
TensorFlow
Safetensors
English
blip
image-text-to-text
art
Inference Endpoints
Model card Files Community
6
sguna commited on
Commit
d3ef6fd
•
1 Parent(s): ee85458

Upload 5 files

Browse files
Files changed (3) hide show
  1. preprocessor_config.json +26 -17
  2. special_tokens_map.json +37 -7
  3. tokenizer_config.json +62 -21
preprocessor_config.json CHANGED
@@ -1,17 +1,26 @@
1
- {
2
- "do_normalize": true,
3
- "do_resize": true,
4
- "image_mean": [
5
- 0.48145466,
6
- 0.4578275,
7
- 0.40821073
8
- ],
9
- "image_processor_type": "BlipImageProcessor",
10
- "image_std": [
11
- 0.26862954,
12
- 0.26130258,
13
- 0.27577711
14
- ],
15
- "processor_class": "BlipProcessor",
16
- "size": 384
17
- }
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_processor_type": "BlipImageProcessor",
13
+ "image_std": [
14
+ 0.26862954,
15
+ 0.26130258,
16
+ 0.27577711
17
+ ],
18
+ "processor_class": "BlipProcessor",
19
+ "resample": 3,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "height": 384,
23
+ "width": 384
24
+ },
25
+ "size_divisor": 32
26
+ }
special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer_config.json CHANGED
@@ -1,21 +1,62 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "do_basic_tokenize": true,
4
- "do_lower_case": true,
5
- "mask_token": "[MASK]",
6
- "model_max_length": 512,
7
- "name_or_path": "bert-base-uncased",
8
- "never_split": null,
9
- "pad_token": "[PAD]",
10
- "processor_class": "BlipProcessor",
11
- "sep_token": "[SEP]",
12
- "special_tokens_map_file": null,
13
- "strip_accents": null,
14
- "tokenize_chinese_chars": true,
15
- "tokenizer_class": "BertTokenizer",
16
- "unk_token": "[UNK]",
17
- "model_input_names": [
18
- "input_ids",
19
- "attention_mask"
20
- ]
21
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_input_names": [
50
+ "input_ids",
51
+ "attention_mask"
52
+ ],
53
+ "model_max_length": 512,
54
+ "never_split": null,
55
+ "pad_token": "[PAD]",
56
+ "processor_class": "BlipProcessor",
57
+ "sep_token": "[SEP]",
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "unk_token": "[UNK]"
62
+ }