Hugging Face's logo

jihadzakki
/
blip1-medvqa

Visual Question Answering
Transformers
Safetensors
blip
medical
vqa
Inference Endpoints
Model card Files Community
jihadzakki commited on
Commit
0d8bbf7
•
1 Parent(s): 2c4afba

Upload 8 files

Browse files
Files changed (8) hide show
  1. config.json +27 -0
  2. generation_config.json +7 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +41 -0
  5. special_tokens_map.json +37 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +62 -0
  8. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Salesforce/blip-vqa-capfilt-large",
3
+ "architectures": [
4
+ "BlipForQuestionAnswering"
5
+ ],
6
+ "image_text_hidden_size": 256,
7
+ "initializer_factor": 1.0,
8
+ "initializer_range": 0.02,
9
+ "label_smoothing": 0.0,
10
+ "logit_scale_init_value": 2.6592,
11
+ "model_type": "blip",
12
+ "projection_dim": 512,
13
+ "text_config": {
14
+ "initializer_factor": 1.0,
15
+ "model_type": "blip_text_model",
16
+ "num_attention_heads": 12
17
+ },
18
+ "torch_dtype": "float32",
19
+ "transformers_version": "4.40.2",
20
+ "vision_config": {
21
+ "dropout": 0.0,
22
+ "initializer_factor": 1.0,
23
+ "initializer_range": 0.02,
24
+ "model_type": "blip_vision_model",
25
+ "num_channels": 3
26
+ }
27
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 30522,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.40.2"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34b6de0bf84912aef329a53886dfcd7b5e858f1f1d70de312308c9c014ac1252
3
+ size 1538792184
preprocessor_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "do_rescale",
8
+ "rescale_factor",
9
+ "do_normalize",
10
+ "image_mean",
11
+ "image_std",
12
+ "do_convert_rgb",
13
+ "return_tensors",
14
+ "data_format",
15
+ "input_data_format"
16
+ ],
17
+ "do_convert_rgb": true,
18
+ "do_normalize": true,
19
+ "do_pad": true,
20
+ "do_rescale": true,
21
+ "do_resize": true,
22
+ "image_mean": [
23
+ 0.48145466,
24
+ 0.4578275,
25
+ 0.40821073
26
+ ],
27
+ "image_processor_type": "BlipImageProcessor",
28
+ "image_std": [
29
+ 0.26862954,
30
+ 0.26130258,
31
+ 0.27577711
32
+ ],
33
+ "processor_class": "BlipProcessor",
34
+ "resample": 3,
35
+ "rescale_factor": 0.00392156862745098,
36
+ "size": {
37
+ "height": 384,
38
+ "width": 384
39
+ },
40
+ "size_divisor": 32
41
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
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
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff