zeyadcode commited on
Commit
906f134
·
verified ·
1 Parent(s): 0eff78d

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Owlv2ForObjectDetection"
4
+ ],
5
+ "dtype": "float32",
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "owlv2",
9
+ "projection_dim": 512,
10
+ "text_config": {
11
+ "attention_dropout": 0.0,
12
+ "dtype": "float32",
13
+ "hidden_act": "quick_gelu",
14
+ "hidden_size": 512,
15
+ "initializer_factor": 1.0,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 2048,
18
+ "layer_norm_eps": 1e-05,
19
+ "max_position_embeddings": 16,
20
+ "model_type": "owlv2_text_model",
21
+ "num_attention_heads": 8,
22
+ "num_hidden_layers": 12,
23
+ "vocab_size": 49408
24
+ },
25
+ "transformers_version": "4.57.6",
26
+ "vision_config": {
27
+ "attention_dropout": 0.0,
28
+ "dtype": "float32",
29
+ "hidden_act": "quick_gelu",
30
+ "hidden_size": 768,
31
+ "image_size": 960,
32
+ "initializer_factor": 1.0,
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "layer_norm_eps": 1e-05,
36
+ "model_type": "owlv2_vision_model",
37
+ "num_attention_heads": 12,
38
+ "num_channels": 3,
39
+ "num_hidden_layers": 12,
40
+ "patch_size": 16
41
+ }
42
+ }
ov_owlv2_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c28f4a154991d51d9a4b4ab896bb6a8059aab39b59568a371d9a32b564e7ea84
3
+ size 306812706
ov_owlv2_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_pad": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Owlv2ImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "processor_class": "Owlv2Processor",
18
+ "resample": 2,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 960,
22
+ "width": 960
23
+ }
24
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "!",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "!",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49406": {
13
+ "content": "<|startoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "49407": {
21
+ "content": "<|endoftext|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [],
30
+ "bos_token": "<|startoftext|>",
31
+ "clean_up_tokenization_spaces": true,
32
+ "do_lower_case": true,
33
+ "eos_token": "<|endoftext|>",
34
+ "errors": "replace",
35
+ "extra_special_tokens": {},
36
+ "model_max_length": 16,
37
+ "pad_token": "!",
38
+ "processor_class": "Owlv2Processor",
39
+ "tokenizer_class": "CLIPTokenizer",
40
+ "unk_token": "<|endoftext|>"
41
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff