Hugging Face's logo

openai
/
clip-vit-large-patch14

Zero-Shot Image Classification
Transformers
PyTorch
TensorFlow
JAX
Safetensors
clip
vision
Inference Endpoints
Model card Files Community
31
valhalla commited on
Commit
e4d7ab3
•
1 Parent(s): 149620b

add model

Browse files
Files changed (4) hide show
  1. config.json +167 -0
  2. flax_model.msgpack +3 -0
  3. pytorch_model.bin +3 -0
  4. tf_model.h5 +3 -0
config.json ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "clip-vit-large-patch14/",
3
+ "architectures": [
4
+ "CLIPModel"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "clip",
9
+ "projection_dim": 768,
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
+ "finetuning_task": null,
27
+ "forced_bos_token_id": null,
28
+ "forced_eos_token_id": null,
29
+ "hidden_act": "quick_gelu",
30
+ "hidden_size": 768,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1"
34
+ },
35
+ "initializer_factor": 1.0,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 3072,
38
+ "is_decoder": false,
39
+ "is_encoder_decoder": false,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1
43
+ },
44
+ "layer_norm_eps": 1e-05,
45
+ "length_penalty": 1.0,
46
+ "max_length": 20,
47
+ "max_position_embeddings": 77,
48
+ "min_length": 0,
49
+ "model_type": "clip_text_model",
50
+ "no_repeat_ngram_size": 0,
51
+ "num_attention_heads": 12,
52
+ "num_beam_groups": 1,
53
+ "num_beams": 1,
54
+ "num_hidden_layers": 12,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "pad_token_id": 1,
60
+ "prefix": null,
61
+ "problem_type": null,
62
+ "pruned_heads": {},
63
+ "remove_invalid_values": false,
64
+ "repetition_penalty": 1.0,
65
+ "return_dict": true,
66
+ "return_dict_in_generate": false,
67
+ "sep_token_id": null,
68
+ "task_specific_params": null,
69
+ "temperature": 1.0,
70
+ "tie_encoder_decoder": false,
71
+ "tie_word_embeddings": true,
72
+ "tokenizer_class": null,
73
+ "top_k": 50,
74
+ "top_p": 1.0,
75
+ "torch_dtype": null,
76
+ "torchscript": false,
77
+ "transformers_version": "4.16.0.dev0",
78
+ "use_bfloat16": false,
79
+ "vocab_size": 49408
80
+ },
81
+ "text_config_dict": {
82
+ "hidden_size": 768,
83
+ "intermediate_size": 3072,
84
+ "num_attention_heads": 12,
85
+ "num_hidden_layers": 12
86
+ },
87
+ "torch_dtype": "float32",
88
+ "transformers_version": null,
89
+ "vision_config": {
90
+ "_name_or_path": "",
91
+ "add_cross_attention": false,
92
+ "architectures": null,
93
+ "attention_dropout": 0.0,
94
+ "bad_words_ids": null,
95
+ "bos_token_id": null,
96
+ "chunk_size_feed_forward": 0,
97
+ "cross_attention_hidden_size": null,
98
+ "decoder_start_token_id": null,
99
+ "diversity_penalty": 0.0,
100
+ "do_sample": false,
101
+ "dropout": 0.0,
102
+ "early_stopping": false,
103
+ "encoder_no_repeat_ngram_size": 0,
104
+ "eos_token_id": null,
105
+ "finetuning_task": null,
106
+ "forced_bos_token_id": null,
107
+ "forced_eos_token_id": null,
108
+ "hidden_act": "quick_gelu",
109
+ "hidden_size": 1024,
110
+ "id2label": {
111
+ "0": "LABEL_0",
112
+ "1": "LABEL_1"
113
+ },
114
+ "image_size": 224,
115
+ "initializer_factor": 1.0,
116
+ "initializer_range": 0.02,
117
+ "intermediate_size": 4096,
118
+ "is_decoder": false,
119
+ "is_encoder_decoder": false,
120
+ "label2id": {
121
+ "LABEL_0": 0,
122
+ "LABEL_1": 1
123
+ },
124
+ "layer_norm_eps": 1e-05,
125
+ "length_penalty": 1.0,
126
+ "max_length": 20,
127
+ "min_length": 0,
128
+ "model_type": "clip_vision_model",
129
+ "no_repeat_ngram_size": 0,
130
+ "num_attention_heads": 16,
131
+ "num_beam_groups": 1,
132
+ "num_beams": 1,
133
+ "num_hidden_layers": 24,
134
+ "num_return_sequences": 1,
135
+ "output_attentions": false,
136
+ "output_hidden_states": false,
137
+ "output_scores": false,
138
+ "pad_token_id": null,
139
+ "patch_size": 14,
140
+ "prefix": null,
141
+ "problem_type": null,
142
+ "pruned_heads": {},
143
+ "remove_invalid_values": false,
144
+ "repetition_penalty": 1.0,
145
+ "return_dict": true,
146
+ "return_dict_in_generate": false,
147
+ "sep_token_id": null,
148
+ "task_specific_params": null,
149
+ "temperature": 1.0,
150
+ "tie_encoder_decoder": false,
151
+ "tie_word_embeddings": true,
152
+ "tokenizer_class": null,
153
+ "top_k": 50,
154
+ "top_p": 1.0,
155
+ "torch_dtype": null,
156
+ "torchscript": false,
157
+ "transformers_version": "4.16.0.dev0",
158
+ "use_bfloat16": false
159
+ },
160
+ "vision_config_dict": {
161
+ "hidden_size": 1024,
162
+ "intermediate_size": 4096,
163
+ "num_attention_heads": 16,
164
+ "num_hidden_layers": 24,
165
+ "patch_size": 14
166
+ }
167
+ }
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:156f677ed4495acd1ec7197249c091b85c240267c82f2f7f2e4eae4177931fed
3
+ size 1710486359
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1a17cdbe0f36fec524f5cafb1c261ea3bbbc13e346e0f74fc9eb0460dedd0d3
3
+ size 1710671599
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f154e925c18270d662d28f6261523c2ff6e80f1f05292cb034db41d5951c7a4
3
+ size 1711114176