Felladrin commited on
Commit
4cba146
·
verified ·
1 Parent(s): 236430e

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers.js
3
+ base_model:
4
+ - google/owlvit-base-patch32
5
+ ---
6
+
7
+ # owlvit-base-patch32 (ONNX)
8
+
9
+ This is an ONNX version of [google/owlvit-base-patch32](https://huggingface.co/google/owlvit-base-patch32). It was automatically converted and uploaded using [this space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "google/owlvit-base-patch32",
4
+ "architectures": [
5
+ "OwlViTForObjectDetection"
6
+ ],
7
+ "initializer_factor": 1.0,
8
+ "logit_scale_init_value": 2.6592,
9
+ "model_type": "owlvit",
10
+ "projection_dim": 512,
11
+ "text_config": {
12
+ "bos_token_id": 0,
13
+ "dropout": 0.0,
14
+ "eos_token_id": 2,
15
+ "max_length": 16,
16
+ "model_type": "owlvit_text_model",
17
+ "pad_token_id": 1,
18
+ "torch_dtype": "float32"
19
+ },
20
+ "text_config_dict": null,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.49.0",
23
+ "vision_config": {
24
+ "dropout": 0.0,
25
+ "model_type": "owlvit_vision_model",
26
+ "torch_dtype": "float32"
27
+ },
28
+ "vision_config_dict": null
29
+ }
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:e4a282be53e414ba9372f27d156a6e442fd125770cdd2ac34e5cc62277daf324
3
+ size 611966733
onnx/model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c726aecfd57ec149efb1727f782f97cd853d0ac7a9bba52b8c4f810420e990f0
3
+ size 183942460
onnx/model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ab7d6485e13ced6d454a019dc20c5fc918457d65a5c5fccd32db4565b22971c
3
+ size 306285370
onnx/model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da62dbb5589017825d5ccd1e369c90ac967430d7963a7f6001f1c374ab44e852
3
+ size 156319651
onnx/model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:453588621a67a50e1e38421509db6ca487d9bb35cc81751c9a8061b0a767a479
3
+ size 191723992
onnx/model_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d19633f7d0db7839aa11a59a14d46be0d2ae4591238bbfd5728eee4c7c4e06a6
3
+ size 127306055
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aabff321fbd0953f2914a6c69e44bf2dfa05ca539319fd665b591d6832e9352f
3
+ size 156319651
onnx/model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aabff321fbd0953f2914a6c69e44bf2dfa05ca539319fd665b591d6832e9352f
3
+ size 156319651
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 768,
4
+ "width": 768
5
+ },
6
+ "do_center_crop": false,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "OwlViTFeatureExtractor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "processor_class": "OwlViTProcessor",
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 768,
27
+ "width": 768
28
+ }
29
+ }
quantize_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "modes": [
3
+ "fp16",
4
+ "q8",
5
+ "int8",
6
+ "uint8",
7
+ "q4",
8
+ "q4f16",
9
+ "bnb4"
10
+ ],
11
+ "per_channel": true,
12
+ "reduce_range": true,
13
+ "block_size": null,
14
+ "is_symmetric": true,
15
+ "accuracy_level": null,
16
+ "quant_type": 1,
17
+ "op_block_list": null
18
+ }
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": false,
31
+ "do_lower_case": true,
32
+ "eos_token": "<|endoftext|>",
33
+ "errors": "replace",
34
+ "extra_special_tokens": {},
35
+ "model_max_length": 16,
36
+ "pad_token": "!",
37
+ "processor_class": "OwlViTProcessor",
38
+ "tokenizer_class": "CLIPTokenizer",
39
+ "unk_token": "<|endoftext|>"
40
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff