Hugging Face's logo

ydshieh
/
clip-vit-base-patch32

Summarization Transformers TensorFlow
English clip zero-shot-image-classification Eval Results Inference Endpoints
Model card Files Community
1
ydshieh HF staff commited on
Commit
6790848
•
1 Parent(s): 21f4167

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +155 -0
config.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/clip-vit-base-patch32",
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
+ "finetuning_task": null,
27
+ "forced_bos_token_id": null,
28
+ "forced_eos_token_id": null,
29
+ "hidden_act": "quick_gelu",
30
+ "hidden_size": 512,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1"
34
+ },
35
+ "initializer_factor": 1.0,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 2048,
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": 8,
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": "4.13.0.dev0",
78
+ "use_bfloat16": false,
79
+ "vocab_size": 49408
80
+ },
81
+ "text_config_dict": null,
82
+ "transformers_version": null,
83
+ "vision_config": {
84
+ "_name_or_path": "",
85
+ "add_cross_attention": false,
86
+ "architectures": null,
87
+ "attention_dropout": 0.0,
88
+ "bad_words_ids": null,
89
+ "bos_token_id": null,
90
+ "chunk_size_feed_forward": 0,
91
+ "cross_attention_hidden_size": null,
92
+ "decoder_start_token_id": null,
93
+ "diversity_penalty": 0.0,
94
+ "do_sample": false,
95
+ "dropout": 0.0,
96
+ "early_stopping": false,
97
+ "encoder_no_repeat_ngram_size": 0,
98
+ "eos_token_id": null,
99
+ "finetuning_task": null,
100
+ "forced_bos_token_id": null,
101
+ "forced_eos_token_id": null,
102
+ "hidden_act": "quick_gelu",
103
+ "hidden_size": 768,
104
+ "id2label": {
105
+ "0": "LABEL_0",
106
+ "1": "LABEL_1"
107
+ },
108
+ "image_size": 224,
109
+ "initializer_factor": 1.0,
110
+ "initializer_range": 0.02,
111
+ "intermediate_size": 3072,
112
+ "is_decoder": false,
113
+ "is_encoder_decoder": false,
114
+ "label2id": {
115
+ "LABEL_0": 0,
116
+ "LABEL_1": 1
117
+ },
118
+ "layer_norm_eps": 1e-05,
119
+ "length_penalty": 1.0,
120
+ "max_length": 20,
121
+ "min_length": 0,
122
+ "model_type": "clip_vision_model",
123
+ "no_repeat_ngram_size": 0,
124
+ "num_attention_heads": 12,
125
+ "num_beam_groups": 1,
126
+ "num_beams": 1,
127
+ "num_hidden_layers": 12,
128
+ "num_return_sequences": 1,
129
+ "output_attentions": false,
130
+ "output_hidden_states": false,
131
+ "output_scores": false,
132
+ "pad_token_id": null,
133
+ "patch_size": 32,
134
+ "prefix": null,
135
+ "problem_type": null,
136
+ "pruned_heads": {},
137
+ "remove_invalid_values": false,
138
+ "repetition_penalty": 1.0,
139
+ "return_dict": true,
140
+ "return_dict_in_generate": false,
141
+ "sep_token_id": null,
142
+ "task_specific_params": null,
143
+ "temperature": 1.0,
144
+ "tie_encoder_decoder": false,
145
+ "tie_word_embeddings": true,
146
+ "tokenizer_class": null,
147
+ "top_k": 50,
148
+ "top_p": 1.0,
149
+ "torch_dtype": null,
150
+ "torchscript": false,
151
+ "transformers_version": "4.13.0.dev0",
152
+ "use_bfloat16": false
153
+ },
154
+ "vision_config_dict": null
155
+ }