geolocal commited on
Commit
8dec737
1 Parent(s): b5f5cc8

StreetCLIP Upload

Browse files
Files changed (2) hide show
  1. config.json +184 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,184 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "ce19dc912ca5cd21c8a653c79e251e808ccabcd1",
3
+ "_name_or_path": "openai/clip-vit-large-patch14-336",
4
+ "architectures": [
5
+ "CLIPModel"
6
+ ],
7
+ "initializer_factor": 1.0,
8
+ "logit_scale_init_value": 2.6592,
9
+ "model_type": "clip",
10
+ "projection_dim": 768,
11
+ "text_config": {
12
+ "_name_or_path": "",
13
+ "add_cross_attention": false,
14
+ "architectures": null,
15
+ "attention_dropout": 0.0,
16
+ "bad_words_ids": null,
17
+ "begin_suppress_tokens": null,
18
+ "bos_token_id": 0,
19
+ "chunk_size_feed_forward": 0,
20
+ "cross_attention_hidden_size": null,
21
+ "decoder_start_token_id": null,
22
+ "diversity_penalty": 0.0,
23
+ "do_sample": false,
24
+ "dropout": 0.0,
25
+ "early_stopping": false,
26
+ "encoder_no_repeat_ngram_size": 0,
27
+ "eos_token_id": 2,
28
+ "exponential_decay_length_penalty": null,
29
+ "finetuning_task": null,
30
+ "forced_bos_token_id": null,
31
+ "forced_eos_token_id": null,
32
+ "hidden_act": "quick_gelu",
33
+ "hidden_size": 768,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1"
37
+ },
38
+ "initializer_factor": 1.0,
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 3072,
41
+ "is_decoder": false,
42
+ "is_encoder_decoder": false,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1
46
+ },
47
+ "layer_norm_eps": 1e-05,
48
+ "length_penalty": 1.0,
49
+ "max_length": 20,
50
+ "max_position_embeddings": 77,
51
+ "min_length": 0,
52
+ "model_type": "clip_text_model",
53
+ "no_repeat_ngram_size": 0,
54
+ "num_attention_heads": 12,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_hidden_layers": 12,
58
+ "num_return_sequences": 1,
59
+ "output_attentions": false,
60
+ "output_hidden_states": false,
61
+ "output_scores": false,
62
+ "pad_token_id": 1,
63
+ "prefix": null,
64
+ "problem_type": null,
65
+ "projection_dim": 768,
66
+ "pruned_heads": {},
67
+ "remove_invalid_values": false,
68
+ "repetition_penalty": 1.0,
69
+ "return_dict": true,
70
+ "return_dict_in_generate": false,
71
+ "sep_token_id": null,
72
+ "suppress_tokens": null,
73
+ "task_specific_params": null,
74
+ "temperature": 1.0,
75
+ "tf_legacy_loss": false,
76
+ "tie_encoder_decoder": false,
77
+ "tie_word_embeddings": true,
78
+ "tokenizer_class": null,
79
+ "top_k": 50,
80
+ "top_p": 1.0,
81
+ "torch_dtype": null,
82
+ "torchscript": false,
83
+ "transformers_version": "4.23.1",
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "vocab_size": 49408
87
+ },
88
+ "text_config_dict": {
89
+ "hidden_size": 768,
90
+ "intermediate_size": 3072,
91
+ "num_attention_heads": 12,
92
+ "num_hidden_layers": 12,
93
+ "projection_dim": 768
94
+ },
95
+ "torch_dtype": "float32",
96
+ "transformers_version": null,
97
+ "vision_config": {
98
+ "_name_or_path": "",
99
+ "add_cross_attention": false,
100
+ "architectures": null,
101
+ "attention_dropout": 0.0,
102
+ "bad_words_ids": null,
103
+ "begin_suppress_tokens": null,
104
+ "bos_token_id": null,
105
+ "chunk_size_feed_forward": 0,
106
+ "cross_attention_hidden_size": null,
107
+ "decoder_start_token_id": null,
108
+ "diversity_penalty": 0.0,
109
+ "do_sample": false,
110
+ "dropout": 0.0,
111
+ "early_stopping": false,
112
+ "encoder_no_repeat_ngram_size": 0,
113
+ "eos_token_id": null,
114
+ "exponential_decay_length_penalty": null,
115
+ "finetuning_task": null,
116
+ "forced_bos_token_id": null,
117
+ "forced_eos_token_id": null,
118
+ "hidden_act": "quick_gelu",
119
+ "hidden_size": 1024,
120
+ "id2label": {
121
+ "0": "LABEL_0",
122
+ "1": "LABEL_1"
123
+ },
124
+ "image_size": 336,
125
+ "initializer_factor": 1.0,
126
+ "initializer_range": 0.02,
127
+ "intermediate_size": 4096,
128
+ "is_decoder": false,
129
+ "is_encoder_decoder": false,
130
+ "label2id": {
131
+ "LABEL_0": 0,
132
+ "LABEL_1": 1
133
+ },
134
+ "layer_norm_eps": 1e-05,
135
+ "length_penalty": 1.0,
136
+ "max_length": 20,
137
+ "min_length": 0,
138
+ "model_type": "clip_vision_model",
139
+ "no_repeat_ngram_size": 0,
140
+ "num_attention_heads": 16,
141
+ "num_beam_groups": 1,
142
+ "num_beams": 1,
143
+ "num_channels": 3,
144
+ "num_hidden_layers": 24,
145
+ "num_return_sequences": 1,
146
+ "output_attentions": false,
147
+ "output_hidden_states": false,
148
+ "output_scores": false,
149
+ "pad_token_id": null,
150
+ "patch_size": 14,
151
+ "prefix": null,
152
+ "problem_type": null,
153
+ "projection_dim": 768,
154
+ "pruned_heads": {},
155
+ "remove_invalid_values": false,
156
+ "repetition_penalty": 1.0,
157
+ "return_dict": true,
158
+ "return_dict_in_generate": false,
159
+ "sep_token_id": null,
160
+ "suppress_tokens": null,
161
+ "task_specific_params": null,
162
+ "temperature": 1.0,
163
+ "tf_legacy_loss": false,
164
+ "tie_encoder_decoder": false,
165
+ "tie_word_embeddings": true,
166
+ "tokenizer_class": null,
167
+ "top_k": 50,
168
+ "top_p": 1.0,
169
+ "torch_dtype": null,
170
+ "torchscript": false,
171
+ "transformers_version": "4.23.1",
172
+ "typical_p": 1.0,
173
+ "use_bfloat16": false
174
+ },
175
+ "vision_config_dict": {
176
+ "hidden_size": 1024,
177
+ "image_size": 336,
178
+ "intermediate_size": 4096,
179
+ "num_attention_heads": 16,
180
+ "num_hidden_layers": 24,
181
+ "patch_size": 14,
182
+ "projection_dim": 768
183
+ }
184
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf6dc3802a8bf9301560b1aa0cd1fa983b4139f96a1befc43802e387401fe6c0
3
+ size 1711981793