Hugging Face's logo

kylewhite0314
/
multimodal-vision-ocr

Safetensors
blip
Model card Files
xet
 Community
kylewhite0314 commited on
Commit
b7cf507
·
verified ·
1 Parent(s): feb334b

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. config.json +89 -0
  2. generation_config.json +29 -0
  3. model.safetensors +3 -0
  4. processor_config.json +26 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +22 -0
config.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BlipForConditionalGeneration"
4
+ ],
5
+ "dtype": "float32",
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
+ "add_cross_attention": false,
15
+ "attention_probs_dropout_prob": 0.0,
16
+ "bos_token_id": 30522,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "dtype": "float32",
20
+ "encoder_hidden_size": 768,
21
+ "eos_token_id": 2,
22
+ "finetuning_task": null,
23
+ "hidden_act": "gelu",
24
+ "hidden_dropout_prob": 0.0,
25
+ "hidden_size": 768,
26
+ "initializer_factor": 1.0,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 3072,
29
+ "is_decoder": true,
30
+ "label_smoothing": 0.0,
31
+ "layer_norm_eps": 1e-12,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "blip_text_model",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 0,
37
+ "prefix": null,
38
+ "projection_dim": 768,
39
+ "pruned_heads": {},
40
+ "sep_token_id": 102,
41
+ "task_specific_params": null,
42
+ "tf_legacy_loss": false,
43
+ "tie_encoder_decoder": false,
44
+ "tie_word_embeddings": true,
45
+ "tokenizer_class": null,
46
+ "torchscript": false,
47
+ "use_bfloat16": false,
48
+ "use_cache": true,
49
+ "vocab_size": 30524
50
+ },
51
+ "tie_word_embeddings": true,
52
+ "transformers_version": "5.13.1",
53
+ "vision_config": {
54
+ "add_cross_attention": false,
55
+ "attention_dropout": 0.0,
56
+ "bos_token_id": null,
57
+ "cross_attention_hidden_size": null,
58
+ "decoder_start_token_id": null,
59
+ "dropout": 0.0,
60
+ "dtype": "float32",
61
+ "eos_token_id": null,
62
+ "finetuning_task": null,
63
+ "hidden_act": "gelu",
64
+ "hidden_size": 768,
65
+ "image_size": 384,
66
+ "initializer_factor": 1.0,
67
+ "initializer_range": 0.02,
68
+ "intermediate_size": 3072,
69
+ "is_decoder": false,
70
+ "layer_norm_eps": 1e-05,
71
+ "model_type": "blip_vision_model",
72
+ "num_attention_heads": 12,
73
+ "num_channels": 3,
74
+ "num_hidden_layers": 12,
75
+ "pad_token_id": null,
76
+ "patch_size": 16,
77
+ "prefix": null,
78
+ "projection_dim": 512,
79
+ "pruned_heads": {},
80
+ "sep_token_id": null,
81
+ "task_specific_params": null,
82
+ "tf_legacy_loss": false,
83
+ "tie_encoder_decoder": false,
84
+ "tie_word_embeddings": true,
85
+ "tokenizer_class": null,
86
+ "torchscript": false,
87
+ "use_bfloat16": false
88
+ }
89
+ }
generation_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 30522,
4
+ "diversity_penalty": 0.0,
5
+ "do_sample": false,
6
+ "early_stopping": false,
7
+ "encoder_no_repeat_ngram_size": 0,
8
+ "eos_token_id": 2,
9
+ "length_penalty": 1.0,
10
+ "max_length": 20,
11
+ "min_length": 0,
12
+ "no_repeat_ngram_size": 0,
13
+ "num_beam_groups": 1,
14
+ "num_beams": 1,
15
+ "num_return_sequences": 1,
16
+ "output_attentions": false,
17
+ "output_hidden_states": false,
18
+ "output_scores": false,
19
+ "pad_token_id": 0,
20
+ "remove_invalid_values": false,
21
+ "repetition_penalty": 1.0,
22
+ "return_dict_in_generate": false,
23
+ "temperature": 1.0,
24
+ "top_k": 50,
25
+ "top_p": 1.0,
26
+ "transformers_version": "5.13.1",
27
+ "typical_p": 1.0,
28
+ "use_cache": true
29
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6586e1cbdea87452fef7bef0230277f38d0519a81fa724d804e2d01999fd16b3
3
+ size 895947208
processor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "do_convert_rgb": true,
4
+ "do_normalize": 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
+ "resample": 3,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 384,
22
+ "width": 384
23
+ }
24
+ },
25
+ "processor_class": "BlipProcessor"
26
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "is_local": false,
7
+ "local_files_only": false,
8
+ "mask_token": "[MASK]",
9
+ "model_input_names": [
10
+ "input_ids",
11
+ "attention_mask"
12
+ ],
13
+ "model_max_length": 512,
14
+ "never_split": null,
15
+ "pad_token": "[PAD]",
16
+ "processor_class": "BlipProcessor",
17
+ "sep_token": "[SEP]",
18
+ "strip_accents": null,
19
+ "tokenize_chinese_chars": true,
20
+ "tokenizer_class": "BertTokenizer",
21
+ "unk_token": "[UNK]"
22
+ }