Hugging Face's logo

laion
/
CLIP-ViT-B-32-256x256-DataComp-s34B-b86K

Zero-Shot Image Classification
OpenCLIP
Safetensors
Model card Files Community
1

this file is missing (it may need to be adjusted)

#1
by wendlerc - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+166
-0
Files changed (1) hide show
  1. config.json +166 -0
config.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CLIPModel"
4
+ ],
5
+ "initializer_factor": 1.0,
6
+ "logit_scale_init_value": 2.6592,
7
+ "model_type": "clip",
8
+ "projection_dim": 512,
9
+ "text_config": {
10
+ "_name_or_path": "",
11
+ "add_cross_attention": false,
12
+ "architectures": null,
13
+ "attention_dropout": 0.0,
14
+ "bad_words_ids": null,
15
+ "bos_token_id": 0,
16
+ "chunk_size_feed_forward": 0,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "dropout": 0.0,
22
+ "early_stopping": false,
23
+ "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": 2,
25
+ "exponential_decay_length_penalty": null,
26
+ "finetuning_task": null,
27
+ "forced_bos_token_id": null,
28
+ "forced_eos_token_id": null,
29
+ "hidden_act": "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
+ "tf_legacy_loss": false,
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": "4.21.3",
79
+ "typical_p": 1.0,
80
+ "use_bfloat16": false,
81
+ "vocab_size": 49408
82
+ },
83
+ "text_config_dict": {
84
+ "hidden_act": "gelu"
85
+ },
86
+ "torch_dtype": "float32",
87
+ "transformers_version": null,
88
+ "vision_config": {
89
+ "_name_or_path": "",
90
+ "add_cross_attention": false,
91
+ "architectures": null,
92
+ "attention_dropout": 0.0,
93
+ "bad_words_ids": null,
94
+ "bos_token_id": null,
95
+ "chunk_size_feed_forward": 0,
96
+ "cross_attention_hidden_size": null,
97
+ "decoder_start_token_id": null,
98
+ "diversity_penalty": 0.0,
99
+ "do_sample": false,
100
+ "dropout": 0.0,
101
+ "early_stopping": false,
102
+ "encoder_no_repeat_ngram_size": 0,
103
+ "eos_token_id": null,
104
+ "exponential_decay_length_penalty": null,
105
+ "finetuning_task": null,
106
+ "forced_bos_token_id": null,
107
+ "forced_eos_token_id": null,
108
+ "hidden_act": "gelu",
109
+ "hidden_size": 768,
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": 3072,
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": 12,
131
+ "num_beam_groups": 1,
132
+ "num_beams": 1,
133
+ "num_channels": 3,
134
+ "num_hidden_layers": 12,
135
+ "num_return_sequences": 1,
136
+ "output_attentions": false,
137
+ "output_hidden_states": false,
138
+ "output_scores": false,
139
+ "pad_token_id": null,
140
+ "patch_size": 32,
141
+ "prefix": null,
142
+ "problem_type": null,
143
+ "pruned_heads": {},
144
+ "remove_invalid_values": false,
145
+ "repetition_penalty": 1.0,
146
+ "return_dict": true,
147
+ "return_dict_in_generate": false,
148
+ "sep_token_id": null,
149
+ "task_specific_params": null,
150
+ "temperature": 1.0,
151
+ "tf_legacy_loss": false,
152
+ "tie_encoder_decoder": false,
153
+ "tie_word_embeddings": true,
154
+ "tokenizer_class": null,
155
+ "top_k": 50,
156
+ "top_p": 1.0,
157
+ "torch_dtype": null,
158
+ "torchscript": false,
159
+ "transformers_version": "4.21.3",
160
+ "typical_p": 1.0,
161
+ "use_bfloat16": false
162
+ },
163
+ "vision_config_dict": {
164
+ "hidden_act": "gelu"
165
+ }
166
+ }