Hugging Face's logo

Xenova
/
chinese-clip-vit-base-patch16

Zero-Shot Image Classification
Transformers.js
ONNX
chinese_clip
Model card Files
xet
Community
1
Xenova HF Staff commited on
Commit
bba8c8c
·
1 Parent(s): 0a1b0f6

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. config.json +33 -0
  2. onnx/model.onnx +3 -0
  3. onnx/model_quantized.onnx +3 -0
  4. preprocessor_config.json +29 -0
  5. quantize_config.json +39 -0
  6. special_tokens_map.json +7 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +58 -0
  9. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "OFA-Sys/chinese-clip-vit-base-patch16",
3
+ "architectures": [
4
+ "ChineseCLIPModel"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "initializer_range": 0.02,
8
+ "logit_scale_init_value": 2.6592,
9
+ "model_type": "chinese_clip",
10
+ "projection_dim": 512,
11
+ "text_config": {
12
+ "architectures": [
13
+ "ChineseCLIPTextModel"
14
+ ],
15
+ "bos_token_id": 0,
16
+ "directionality": "bidi",
17
+ "eos_token_id": 2,
18
+ "model_type": "chinese_clip_text_model",
19
+ "output_past": true,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "vocab_size": 21128
26
+ },
27
+ "transformers_version": "4.36.0.dev0",
28
+ "vision_config": {
29
+ "dropout": 0.0,
30
+ "model_type": "chinese_clip_vision_model",
31
+ "patch_size": 16
32
+ }
33
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4e282affd5f09e196856cc63fbd0e77c576f598fdf6f6bb78ee61f1ef7cd770
3
+ size 753665706
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2c2849329eafb24100acec5a9421a39f8cb445296444c5c98855b69e5e7a751
3
+ size 190842404
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
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": "ChineseCLIPFeatureExtractor",
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "ChineseCLIPFeatureExtractor",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 224,
27
+ "width": 224
28
+ }
29
+ }
quantize_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "model": {
6
+ "op_types": [
7
+ "Constant",
8
+ "ReduceMean",
9
+ "Reshape",
10
+ "Sub",
11
+ "Abs",
12
+ "MatMul",
13
+ "Sqrt",
14
+ "Slice",
15
+ "Where",
16
+ "Cast",
17
+ "Div",
18
+ "Concat",
19
+ "Shape",
20
+ "Softmax",
21
+ "Equal",
22
+ "Erf",
23
+ "Transpose",
24
+ "ReduceSum",
25
+ "Unsqueeze",
26
+ "Mul",
27
+ "Exp",
28
+ "Conv",
29
+ "Gather",
30
+ "Add",
31
+ "Pow",
32
+ "Expand",
33
+ "Sigmoid",
34
+ "ConstantOfShape"
35
+ ],
36
+ "weight_type": "QUInt8"
37
+ }
38
+ }
39
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "processor_class": "ChineseCLIPProcessor",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff