Upload folder using huggingface_hub
Browse files- config.json +34 -0
- merges.txt +0 -0
- onnx/model.onnx +3 -0
- onnx/model_quantized.onnx +3 -0
- preprocessor_config.json +30 -0
- quantize_config.json +49 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +40 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/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 |
+
"bos_token_id": 0,
|
12 |
+
"dropout": 0.0,
|
13 |
+
"eos_token_id": 2,
|
14 |
+
"hidden_size": 768,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"max_length": 16,
|
17 |
+
"model_type": "owlvit_text_model",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"pad_token_id": 1
|
20 |
+
},
|
21 |
+
"text_config_dict": null,
|
22 |
+
"transformers_version": "4.36.0.dev0",
|
23 |
+
"vision_config": {
|
24 |
+
"dropout": 0.0,
|
25 |
+
"hidden_size": 1024,
|
26 |
+
"image_size": 840,
|
27 |
+
"intermediate_size": 4096,
|
28 |
+
"model_type": "owlvit_vision_model",
|
29 |
+
"num_attention_heads": 16,
|
30 |
+
"num_hidden_layers": 24,
|
31 |
+
"patch_size": 14
|
32 |
+
},
|
33 |
+
"vision_config_dict": null
|
34 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
onnx/model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bc50060fe7c668afb13a2ef10c1abd271d1d3d9839bf3fe67e4dc5c87418672
|
3 |
+
size 1733582161
|
onnx/model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a49df462c9a91cfb2fabbc4c0279583ed81c1d668632fac6000842aaad945772
|
3 |
+
size 437844773
|
preprocessor_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_size": {
|
3 |
+
"height": 840,
|
4 |
+
"width": 840
|
5 |
+
},
|
6 |
+
"do_center_crop": false,
|
7 |
+
"do_convert_rgb": true,
|
8 |
+
"do_normalize": true,
|
9 |
+
"do_rescale": true,
|
10 |
+
"do_resize": true,
|
11 |
+
"feature_extractor_type": "OwlViTFeatureExtractor",
|
12 |
+
"image_mean": [
|
13 |
+
0.48145466,
|
14 |
+
0.4578275,
|
15 |
+
0.40821073
|
16 |
+
],
|
17 |
+
"image_processor_type": "OwlViTFeatureExtractor",
|
18 |
+
"image_std": [
|
19 |
+
0.26862954,
|
20 |
+
0.26130258,
|
21 |
+
0.27577711
|
22 |
+
],
|
23 |
+
"processor_class": "OwlViTProcessor",
|
24 |
+
"resample": 3,
|
25 |
+
"rescale_factor": 0.00392156862745098,
|
26 |
+
"size": {
|
27 |
+
"height": 840,
|
28 |
+
"width": 840
|
29 |
+
}
|
30 |
+
}
|
quantize_config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"per_channel": true,
|
3 |
+
"reduce_range": true,
|
4 |
+
"per_model_config": {
|
5 |
+
"model": {
|
6 |
+
"op_types": [
|
7 |
+
"Sqrt",
|
8 |
+
"Shape",
|
9 |
+
"Gather",
|
10 |
+
"Softmax",
|
11 |
+
"Squeeze",
|
12 |
+
"Reciprocal",
|
13 |
+
"Greater",
|
14 |
+
"Expand",
|
15 |
+
"Sub",
|
16 |
+
"Unsqueeze",
|
17 |
+
"Equal",
|
18 |
+
"Where",
|
19 |
+
"Einsum",
|
20 |
+
"Pow",
|
21 |
+
"Log",
|
22 |
+
"ConstantOfShape",
|
23 |
+
"Cast",
|
24 |
+
"Abs",
|
25 |
+
"Sigmoid",
|
26 |
+
"ReduceSum",
|
27 |
+
"Erf",
|
28 |
+
"MatMul",
|
29 |
+
"Conv",
|
30 |
+
"ArgMax",
|
31 |
+
"Div",
|
32 |
+
"Elu",
|
33 |
+
"Less",
|
34 |
+
"Reshape",
|
35 |
+
"Add",
|
36 |
+
"Neg",
|
37 |
+
"Mul",
|
38 |
+
"Slice",
|
39 |
+
"Constant",
|
40 |
+
"Flatten",
|
41 |
+
"ReduceMean",
|
42 |
+
"Concat",
|
43 |
+
"Transpose",
|
44 |
+
"Range"
|
45 |
+
],
|
46 |
+
"weight_type": "QUInt8"
|
47 |
+
}
|
48 |
+
}
|
49 |
+
}
|
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.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"bos_token": "<|startoftext|>",
|
30 |
+
"clean_up_tokenization_spaces": true,
|
31 |
+
"do_lower_case": true,
|
32 |
+
"eos_token": "<|endoftext|>",
|
33 |
+
"errors": "replace",
|
34 |
+
"model_max_length": 16,
|
35 |
+
"pad_token": "!",
|
36 |
+
"processor_class": "OwlViTProcessor",
|
37 |
+
"tokenizer_class": "CLIPTokenizer",
|
38 |
+
"trust_remote_code": false,
|
39 |
+
"unk_token": "<|endoftext|>"
|
40 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|