mrsarthakgupta
commited on
Commit
•
69d06ce
1
Parent(s):
b049201
Upload 5 files
Browse files- config.json +22 -0
- onnx/vision_model.onnx +3 -0
- onnx/vision_model_fp16.onnx +3 -0
- onnx/vision_model_quantized.onnx +3 -0
- preprocessor_config.json +45 -0
config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "models_nextmethod/meow_projection/",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPVisionModelWithProjection"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_size": 1024,
|
9 |
+
"image_size": 224,
|
10 |
+
"initializer_factor": 1.0,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 4096,
|
13 |
+
"layer_norm_eps": 1e-05,
|
14 |
+
"model_type": "clip_vision_model",
|
15 |
+
"num_attention_heads": 16,
|
16 |
+
"num_channels": 3,
|
17 |
+
"num_hidden_layers": 24,
|
18 |
+
"patch_size": 14,
|
19 |
+
"projection_dim": 512,
|
20 |
+
"torch_dtype": "float32",
|
21 |
+
"transformers_version": "4.41.2"
|
22 |
+
}
|
onnx/vision_model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a5524db3cef7539799004fca84fead5d242703bce550bf98a1479e1e570ebec
|
3 |
+
size 1215437847
|
onnx/vision_model_fp16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a5524db3cef7539799004fca84fead5d242703bce550bf98a1479e1e570ebec
|
3 |
+
size 1215437847
|
onnx/vision_model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d926ba443e4d2d5e4c2ffdac48a7f385c0f405b29263169e9dfeb3d2ef0a33e
|
3 |
+
size 305817686
|
preprocessor_config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_center_crop",
|
8 |
+
"crop_size",
|
9 |
+
"do_rescale",
|
10 |
+
"rescale_factor",
|
11 |
+
"do_normalize",
|
12 |
+
"image_mean",
|
13 |
+
"image_std",
|
14 |
+
"do_convert_rgb",
|
15 |
+
"return_tensors",
|
16 |
+
"data_format",
|
17 |
+
"input_data_format"
|
18 |
+
],
|
19 |
+
"crop_size": {
|
20 |
+
"height": 224,
|
21 |
+
"width": 224
|
22 |
+
},
|
23 |
+
"do_center_crop": true,
|
24 |
+
"do_convert_rgb": true,
|
25 |
+
"do_normalize": true,
|
26 |
+
"do_rescale": true,
|
27 |
+
"do_resize": true,
|
28 |
+
"image_mean": [
|
29 |
+
0.48145466,
|
30 |
+
0.4578275,
|
31 |
+
0.40821073
|
32 |
+
],
|
33 |
+
"image_processor_type": "CLIPImageProcessor",
|
34 |
+
"image_std": [
|
35 |
+
0.26862954,
|
36 |
+
0.26130258,
|
37 |
+
0.27577711
|
38 |
+
],
|
39 |
+
"processor_class": "CLIPProcessor",
|
40 |
+
"resample": 3,
|
41 |
+
"rescale_factor": 0.00392156862745098,
|
42 |
+
"size": {
|
43 |
+
"shortest_edge": 224
|
44 |
+
}
|
45 |
+
}
|