nreimers commited on
Commit
b3e1470
1 Parent(s): bc10f52
0_CLIPModel/config.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/clip-vit-base-patch16",
3
+ "architectures": [
4
+ "CLIPModel"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "clip",
9
+ "projection_dim": 512,
10
+ "text_config": {
11
+ "_name_or_path": "",
12
+ "add_cross_attention": false,
13
+ "architectures": null,
14
+ "attention_dropout": 0.0,
15
+ "bad_words_ids": null,
16
+ "bos_token_id": 0,
17
+ "chunk_size_feed_forward": 0,
18
+ "cross_attention_hidden_size": null,
19
+ "decoder_start_token_id": null,
20
+ "diversity_penalty": 0.0,
21
+ "do_sample": false,
22
+ "dropout": 0.0,
23
+ "early_stopping": false,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": 2,
26
+ "exponential_decay_length_penalty": null,
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "hidden_act": "quick_gelu",
31
+ "hidden_size": 512,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1"
35
+ },
36
+ "initializer_factor": 1.0,
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 2048,
39
+ "is_decoder": false,
40
+ "is_encoder_decoder": false,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1
44
+ },
45
+ "layer_norm_eps": 1e-05,
46
+ "length_penalty": 1.0,
47
+ "max_length": 20,
48
+ "max_position_embeddings": 77,
49
+ "min_length": 0,
50
+ "model_type": "clip_text_model",
51
+ "no_repeat_ngram_size": 0,
52
+ "num_attention_heads": 8,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_hidden_layers": 12,
56
+ "num_return_sequences": 1,
57
+ "output_attentions": false,
58
+ "output_hidden_states": false,
59
+ "output_scores": false,
60
+ "pad_token_id": 1,
61
+ "prefix": null,
62
+ "problem_type": null,
63
+ "pruned_heads": {},
64
+ "remove_invalid_values": false,
65
+ "repetition_penalty": 1.0,
66
+ "return_dict": true,
67
+ "return_dict_in_generate": false,
68
+ "sep_token_id": null,
69
+ "task_specific_params": null,
70
+ "temperature": 1.0,
71
+ "tie_encoder_decoder": false,
72
+ "tie_word_embeddings": true,
73
+ "tokenizer_class": null,
74
+ "top_k": 50,
75
+ "top_p": 1.0,
76
+ "torch_dtype": null,
77
+ "torchscript": false,
78
+ "transformers_version": "4.18.0",
79
+ "typical_p": 1.0,
80
+ "use_bfloat16": false,
81
+ "vocab_size": 49408
82
+ },
83
+ "text_config_dict": null,
84
+ "torch_dtype": "float32",
85
+ "transformers_version": null,
86
+ "vision_config": {
87
+ "_name_or_path": "",
88
+ "add_cross_attention": false,
89
+ "architectures": null,
90
+ "attention_dropout": 0.0,
91
+ "bad_words_ids": null,
92
+ "bos_token_id": null,
93
+ "chunk_size_feed_forward": 0,
94
+ "cross_attention_hidden_size": null,
95
+ "decoder_start_token_id": null,
96
+ "diversity_penalty": 0.0,
97
+ "do_sample": false,
98
+ "dropout": 0.0,
99
+ "early_stopping": false,
100
+ "encoder_no_repeat_ngram_size": 0,
101
+ "eos_token_id": null,
102
+ "exponential_decay_length_penalty": null,
103
+ "finetuning_task": null,
104
+ "forced_bos_token_id": null,
105
+ "forced_eos_token_id": null,
106
+ "hidden_act": "quick_gelu",
107
+ "hidden_size": 768,
108
+ "id2label": {
109
+ "0": "LABEL_0",
110
+ "1": "LABEL_1"
111
+ },
112
+ "image_size": 224,
113
+ "initializer_factor": 1.0,
114
+ "initializer_range": 0.02,
115
+ "intermediate_size": 3072,
116
+ "is_decoder": false,
117
+ "is_encoder_decoder": false,
118
+ "label2id": {
119
+ "LABEL_0": 0,
120
+ "LABEL_1": 1
121
+ },
122
+ "layer_norm_eps": 1e-05,
123
+ "length_penalty": 1.0,
124
+ "max_length": 20,
125
+ "min_length": 0,
126
+ "model_type": "clip_vision_model",
127
+ "no_repeat_ngram_size": 0,
128
+ "num_attention_heads": 12,
129
+ "num_beam_groups": 1,
130
+ "num_beams": 1,
131
+ "num_hidden_layers": 12,
132
+ "num_return_sequences": 1,
133
+ "output_attentions": false,
134
+ "output_hidden_states": false,
135
+ "output_scores": false,
136
+ "pad_token_id": null,
137
+ "patch_size": 16,
138
+ "prefix": null,
139
+ "problem_type": null,
140
+ "pruned_heads": {},
141
+ "remove_invalid_values": false,
142
+ "repetition_penalty": 1.0,
143
+ "return_dict": true,
144
+ "return_dict_in_generate": false,
145
+ "sep_token_id": null,
146
+ "task_specific_params": null,
147
+ "temperature": 1.0,
148
+ "tie_encoder_decoder": false,
149
+ "tie_word_embeddings": true,
150
+ "tokenizer_class": null,
151
+ "top_k": 50,
152
+ "top_p": 1.0,
153
+ "torch_dtype": null,
154
+ "torchscript": false,
155
+ "transformers_version": "4.18.0",
156
+ "typical_p": 1.0,
157
+ "use_bfloat16": false
158
+ },
159
+ "vision_config_dict": {
160
+ "patch_size": 16
161
+ }
162
+ }
0_CLIPModel/merges.txt ADDED
The diff for this file is too large to render. See raw diff
0_CLIPModel/preprocessor_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": 224,
3
+ "do_center_crop": true,
4
+ "do_normalize": true,
5
+ "do_resize": true,
6
+ "feature_extractor_type": "CLIPFeatureExtractor",
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "processor_class": "CLIPProcessor",
18
+ "resample": 3,
19
+ "size": 224
20
+ }
0_CLIPModel/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66d22a979777b2936ec3f52e25757ab93673ebf7bc0d523789df3a4355db8a44
3
+ size 598613921
0_CLIPModel/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}
0_CLIPModel/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
0_CLIPModel/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": "<|endoftext|>", "errors": "replace", "add_prefix_space": false, "do_lower_case": true, "name_or_path": "openai/clip-vit-base-patch16", "model_max_length": 77, "special_tokens_map_file": "./special_tokens_map.json", "tokenizer_class": "CLIPTokenizer", "processor_class": "CLIPProcessor"}
0_CLIPModel/vocab.json ADDED
The diff for this file is too large to render. See raw diff
README.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: sentence-similarity
3
+ tags:
4
+ - sentence-transformers
5
+ - feature-extraction
6
+ - sentence-similarity
7
+ ---
8
+
9
+ # clip-ViT-B-16
10
+
11
+ This is the Image & Text model [CLIP](https://arxiv.org/abs/2103.00020), which maps text and images to a shared vector space. For applications of the models, have a look in our documentation [SBERT.net - Image Search](https://www.sbert.net/examples/applications/image-search/README.html)
12
+
13
+ ## Usage
14
+
15
+ After installing [sentence-transformers](https://sbert.net) (`pip install sentence-transformers`), the usage of this model is easy:
16
+
17
+
18
+ ```python
19
+ from sentence_transformers import SentenceTransformer, util
20
+ from PIL import Image
21
+
22
+ #Load CLIP model
23
+ model = SentenceTransformer('clip-ViT-B-16')
24
+
25
+ #Encode an image:
26
+ img_emb = model.encode(Image.open('two_dogs_in_snow.jpg'))
27
+
28
+ #Encode text descriptions
29
+ text_emb = model.encode(['Two dogs in the snow', 'A cat on a table', 'A picture of London at night'])
30
+
31
+ #Compute cosine similarities
32
+ cos_scores = util.cos_sim(img_emb, text_emb)
33
+ print(cos_scores)
34
+ ```
35
+
36
+ See our [SBERT.net - Image Search](https://www.sbert.net/examples/applications/image-search/README.html) documentation for more examples how the model can be used for image search, zero-shot image classification, image clustering and image deduplication.
37
+
38
+ ## Performance
39
+
40
+ In the following table we find the zero-shot ImageNet validation set accuracy:
41
+
42
+ | Model | Top 1 Performance |
43
+ | --- | :---: |
44
+ | [clip-ViT-B-32](https://huggingface.co/sentence-transformers/clip-ViT-B-32) | 63.3 |
45
+ | [clip-ViT-B-16](https://huggingface.co/sentence-transformers/clip-ViT-B-16) | 68.1 |
46
+ | [clip-ViT-L-14](https://huggingface.co/sentence-transformers/clip-ViT-L-14) | 75.4 |
47
+
48
+ For a multilingual version of the CLIP model for 50+ languages have a look at: [clip-ViT-B-32-multilingual-v1](https://huggingface.co/sentence-transformers/clip-ViT-B-32-multilingual-v1)
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.2.0",
4
+ "transformers": "4.18.0",
5
+ "pytorch": "1.11.0"
6
+ }
7
+ }
modules.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "0_CLIPModel",
6
+ "type": "sentence_transformers.models.CLIPModel"
7
+ }
8
+ ]