Hugging Face's logo

google
/
owlvit-large-patch14

Zero-Shot Object Detection
Transformers
PyTorch
owlvit
vision
Model card Files Community
8
Alara Dirik commited on
Commit
29432f9
•
1 Parent(s): ebf7be1

Added model and processor

Browse files
Files changed (7) hide show
  1. config.json +160 -0
  2. merges.txt +0 -0
  3. preprocessor_config.json +22 -0
  4. pytorch_model.bin +3 -0
  5. special_tokens_map.json +24 -0
  6. tokenizer_config.json +35 -0
  7. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "adirik/owlvit-large-patch14",
3
+ "architectures": [
4
+ "OwlViTForObjectDetection"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "owlvit",
9
+ "projection_dim": 768,
10
+ "text_config": {
11
+ "_name_or_path": "",
12
+ "add_cross_attention": false,
13
+ "architectures": null,
14
+ "attention_dropout": 0.0,
15
+ "bad_words_ids": null,
16
+ "bos_token_id": 49406,
17
+ "chunk_size_feed_forward": 0,
18
+ "cross_attention_hidden_size": null,
19
+ "decoder_start_token_id": null,
20
+ "diversity_penalty": 0.0,
21
+ "do_sample": false,
22
+ "dropout": 0.0,
23
+ "early_stopping": false,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": 49407,
26
+ "exponential_decay_length_penalty": null,
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "hidden_act": "quick_gelu",
31
+ "hidden_size": 768,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1"
35
+ },
36
+ "initializer_factor": 1.0,
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 3072,
39
+ "is_decoder": false,
40
+ "is_encoder_decoder": false,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1
44
+ },
45
+ "layer_norm_eps": 1e-05,
46
+ "length_penalty": 1.0,
47
+ "max_length": 20,
48
+ "max_position_embeddings": 16,
49
+ "min_length": 0,
50
+ "model_type": "owlvit_text_model",
51
+ "no_repeat_ngram_size": 0,
52
+ "num_attention_heads": 12,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_hidden_layers": 12,
56
+ "num_return_sequences": 1,
57
+ "output_attentions": false,
58
+ "output_hidden_states": false,
59
+ "output_scores": false,
60
+ "pad_token_id": 0,
61
+ "prefix": null,
62
+ "problem_type": null,
63
+ "pruned_heads": {},
64
+ "remove_invalid_values": false,
65
+ "repetition_penalty": 1.0,
66
+ "return_dict": true,
67
+ "return_dict_in_generate": false,
68
+ "sep_token_id": null,
69
+ "task_specific_params": null,
70
+ "temperature": 1.0,
71
+ "tie_encoder_decoder": false,
72
+ "tie_word_embeddings": true,
73
+ "tokenizer_class": null,
74
+ "top_k": 50,
75
+ "top_p": 1.0,
76
+ "torch_dtype": null,
77
+ "torchscript": false,
78
+ "transformers_version": "4.21.0.dev0",
79
+ "typical_p": 1.0,
80
+ "use_bfloat16": false,
81
+ "vocab_size": 49408
82
+ },
83
+ "text_config_dict": null,
84
+ "torch_dtype": "float32",
85
+ "transformers_version": null,
86
+ "vision_config": {
87
+ "_name_or_path": "",
88
+ "add_cross_attention": false,
89
+ "architectures": null,
90
+ "attention_dropout": 0.0,
91
+ "bad_words_ids": null,
92
+ "bos_token_id": null,
93
+ "chunk_size_feed_forward": 0,
94
+ "cross_attention_hidden_size": null,
95
+ "decoder_start_token_id": null,
96
+ "diversity_penalty": 0.0,
97
+ "do_sample": false,
98
+ "dropout": 0.0,
99
+ "early_stopping": false,
100
+ "encoder_no_repeat_ngram_size": 0,
101
+ "eos_token_id": null,
102
+ "exponential_decay_length_penalty": null,
103
+ "finetuning_task": null,
104
+ "forced_bos_token_id": null,
105
+ "forced_eos_token_id": null,
106
+ "hidden_act": "quick_gelu",
107
+ "hidden_size": 1024,
108
+ "id2label": {
109
+ "0": "LABEL_0",
110
+ "1": "LABEL_1"
111
+ },
112
+ "image_size": 840,
113
+ "initializer_factor": 1.0,
114
+ "initializer_range": 0.02,
115
+ "intermediate_size": 4096,
116
+ "is_decoder": false,
117
+ "is_encoder_decoder": false,
118
+ "label2id": {
119
+ "LABEL_0": 0,
120
+ "LABEL_1": 1
121
+ },
122
+ "layer_norm_eps": 1e-05,
123
+ "length_penalty": 1.0,
124
+ "max_length": 20,
125
+ "min_length": 0,
126
+ "model_type": "owlvit_vision_model",
127
+ "no_repeat_ngram_size": 0,
128
+ "num_attention_heads": 16,
129
+ "num_beam_groups": 1,
130
+ "num_beams": 1,
131
+ "num_hidden_layers": 24,
132
+ "num_return_sequences": 1,
133
+ "output_attentions": false,
134
+ "output_hidden_states": false,
135
+ "output_scores": false,
136
+ "pad_token_id": null,
137
+ "patch_size": 14,
138
+ "prefix": null,
139
+ "problem_type": null,
140
+ "pruned_heads": {},
141
+ "remove_invalid_values": false,
142
+ "repetition_penalty": 1.0,
143
+ "return_dict": true,
144
+ "return_dict_in_generate": false,
145
+ "sep_token_id": null,
146
+ "task_specific_params": null,
147
+ "temperature": 1.0,
148
+ "tie_encoder_decoder": false,
149
+ "tie_word_embeddings": true,
150
+ "tokenizer_class": null,
151
+ "top_k": 50,
152
+ "top_p": 1.0,
153
+ "torch_dtype": null,
154
+ "torchscript": false,
155
+ "transformers_version": "4.21.0.dev0",
156
+ "typical_p": 1.0,
157
+ "use_bfloat16": false
158
+ },
159
+ "vision_config_dict": null
160
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": 840,
3
+ "do_center_crop": true,
4
+ "do_convert_rgb": true,
5
+ "do_normalize": true,
6
+ "do_resize": true,
7
+ "feature_extractor_type": "OwlViTFeatureExtractor",
8
+ "image_mean": [
9
+ 0.48145466,
10
+ 0.4578275,
11
+ 0.40821073
12
+ ],
13
+ "image_std": [
14
+ 0.26862954,
15
+ 0.26130258,
16
+ 0.27577711
17
+ ],
18
+ "processor_class": "OwlViTProcessor",
19
+ "resample": 3,
20
+ "rescale": true,
21
+ "size": 840
22
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16c6725be23de3c3975d2358b1768da908f16e46afa5ec76d0a59a41cad27dec
3
+ size 1735729705
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "!",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "do_lower_case": true,
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 16,
22
+ "name_or_path": "openai/clip-vit-base-patch32",
23
+ "pad_token": "!",
24
+ "processor_class": "OwlViTProcessor",
25
+ "special_tokens_map_file": "/Users/adirik/.cache/huggingface/transformers/18a566598f286c9139f88160c99f84eec492a26bd22738fa9cb44d5b7e0a5c76.cce1206abbad28826f000510f22f354e53e66a97f7c23745a7dfe27609cc07f5",
26
+ "tokenizer_class": "CLIPTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<|endoftext|>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff