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 +23 -0
- quantize_config.json +43 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +32 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "CIDAS/clipseg-rd64",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPSegForImageSegmentation"
|
5 |
+
],
|
6 |
+
"conditional_layer": 0,
|
7 |
+
"decoder_attention_dropout": 0.0,
|
8 |
+
"decoder_hidden_act": "quick_gelu",
|
9 |
+
"decoder_intermediate_size": 2048,
|
10 |
+
"decoder_num_attention_heads": 4,
|
11 |
+
"extract_layers": [
|
12 |
+
3,
|
13 |
+
6,
|
14 |
+
9
|
15 |
+
],
|
16 |
+
"initializer_factor": 1.0,
|
17 |
+
"logit_scale_init_value": 2.6592,
|
18 |
+
"model_type": "clipseg",
|
19 |
+
"projection_dim": 512,
|
20 |
+
"reduce_dim": 64,
|
21 |
+
"text_config": {
|
22 |
+
"bos_token_id": 0,
|
23 |
+
"dropout": 0.0,
|
24 |
+
"eos_token_id": 2,
|
25 |
+
"model_type": "clipseg_text_model"
|
26 |
+
},
|
27 |
+
"transformers_version": "4.37.0.dev0",
|
28 |
+
"use_complex_transposed_convolution": false,
|
29 |
+
"vision_config": {
|
30 |
+
"dropout": 0.0,
|
31 |
+
"model_type": "clipseg_vision_model",
|
32 |
+
"patch_size": 16
|
33 |
+
}
|
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 sha256:6134b4555d4eb6a758caae66f7338d39a75a25b061bec1fa089a372badbc3c74
|
3 |
+
size 545201523
|
onnx/model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3a00e7d77ccf59ed38c2a2d1b64de430145aa9fe9048bdcd98800a6dda4d864
|
3 |
+
size 138548175
|
preprocessor_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"do_rescale": true,
|
4 |
+
"do_resize": true,
|
5 |
+
"image_mean": [
|
6 |
+
0.485,
|
7 |
+
0.456,
|
8 |
+
0.406
|
9 |
+
],
|
10 |
+
"image_processor_type": "ViTImageProcessor",
|
11 |
+
"image_std": [
|
12 |
+
0.229,
|
13 |
+
0.224,
|
14 |
+
0.225
|
15 |
+
],
|
16 |
+
"processor_class": "CLIPSegProcessor",
|
17 |
+
"resample": 2,
|
18 |
+
"rescale_factor": 0.00392156862745098,
|
19 |
+
"size": {
|
20 |
+
"height": 352,
|
21 |
+
"width": 352
|
22 |
+
}
|
23 |
+
}
|
quantize_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"per_channel": true,
|
3 |
+
"reduce_range": true,
|
4 |
+
"per_model_config": {
|
5 |
+
"model": {
|
6 |
+
"op_types": [
|
7 |
+
"Transpose",
|
8 |
+
"Add",
|
9 |
+
"MatMul",
|
10 |
+
"Reshape",
|
11 |
+
"Sub",
|
12 |
+
"Less",
|
13 |
+
"ConstantOfShape",
|
14 |
+
"ArgMax",
|
15 |
+
"Expand",
|
16 |
+
"Constant",
|
17 |
+
"Softmax",
|
18 |
+
"ReduceMean",
|
19 |
+
"Where",
|
20 |
+
"Concat",
|
21 |
+
"Relu",
|
22 |
+
"Equal",
|
23 |
+
"Slice",
|
24 |
+
"Pow",
|
25 |
+
"Sqrt",
|
26 |
+
"Gemm",
|
27 |
+
"Range",
|
28 |
+
"Sigmoid",
|
29 |
+
"Unsqueeze",
|
30 |
+
"Cast",
|
31 |
+
"ConvTranspose",
|
32 |
+
"Div",
|
33 |
+
"Gather",
|
34 |
+
"Shape",
|
35 |
+
"Conv",
|
36 |
+
"Squeeze",
|
37 |
+
"Flatten",
|
38 |
+
"Mul"
|
39 |
+
],
|
40 |
+
"weight_type": "QUInt8"
|
41 |
+
}
|
42 |
+
}
|
43 |
+
}
|
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": "<|endoftext|>",
|
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 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"49406": {
|
5 |
+
"content": "<|startoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"49407": {
|
13 |
+
"content": "<|endoftext|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
}
|
20 |
+
},
|
21 |
+
"bos_token": "<|startoftext|>",
|
22 |
+
"clean_up_tokenization_spaces": true,
|
23 |
+
"do_lower_case": true,
|
24 |
+
"eos_token": "<|endoftext|>",
|
25 |
+
"errors": "replace",
|
26 |
+
"model_max_length": 77,
|
27 |
+
"pad_token": "<|endoftext|>",
|
28 |
+
"processor_class": "CLIPSegProcessor",
|
29 |
+
"tokenizer_class": "CLIPTokenizer",
|
30 |
+
"trust_remote_code": false,
|
31 |
+
"unk_token": "<|endoftext|>"
|
32 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|