The model parameters have been renamed and a config file has been provided to enable its usage with the CLIPModel in the transformers library.

#2
Files changed (3) hide show
  1. config.json +157 -0
  2. preprocessor_config.json +19 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "dropout": 0.0,
21
+ "early_stopping": false,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": 2,
24
+ "finetuning_task": null,
25
+ "forced_bos_token_id": null,
26
+ "forced_eos_token_id": null,
27
+ "hidden_act": "quick_gelu",
28
+ "hidden_size": 512,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "initializer_factor": 1.0,
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 2048,
36
+ "is_decoder": false,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-05,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 77,
46
+ "min_length": 0,
47
+ "model_type": "clip_text_model",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_attention_heads": 8,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 12,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": 1,
58
+ "prefix": null,
59
+ "problem_type": null,
60
+ "projection_dim" : 512,
61
+ "pruned_heads": {},
62
+ "remove_invalid_values": false,
63
+ "repetition_penalty": 1.0,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "sep_token_id": null,
67
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tie_encoder_decoder": false,
70
+ "tie_word_embeddings": true,
71
+ "tokenizer_class": null,
72
+ "top_k": 50,
73
+ "top_p": 1.0,
74
+ "torch_dtype": null,
75
+ "torchscript": false,
76
+ "transformers_version": "4.12.0.dev0",
77
+ "use_bfloat16": false,
78
+ "vocab_size": 49408
79
+ },
80
+ "text_config_dict": null,
81
+ "torch_dtype": "float32",
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
+ "decoder_start_token_id": null,
92
+ "diversity_penalty": 0.0,
93
+ "do_sample": false,
94
+ "dropout": 0.0,
95
+ "early_stopping": false,
96
+ "encoder_no_repeat_ngram_size": 0,
97
+ "eos_token_id": null,
98
+ "finetuning_task": null,
99
+ "forced_bos_token_id": null,
100
+ "forced_eos_token_id": null,
101
+ "hidden_act": "quick_gelu",
102
+ "hidden_size": 768,
103
+ "id2label": {
104
+ "0": "LABEL_0",
105
+ "1": "LABEL_1"
106
+ },
107
+ "image_size": 224,
108
+ "initializer_factor": 1.0,
109
+ "initializer_range": 0.02,
110
+ "intermediate_size": 3072,
111
+ "is_decoder": false,
112
+ "is_encoder_decoder": false,
113
+ "label2id": {
114
+ "LABEL_0": 0,
115
+ "LABEL_1": 1
116
+ },
117
+ "layer_norm_eps": 1e-05,
118
+ "length_penalty": 1.0,
119
+ "max_length": 20,
120
+ "min_length": 0,
121
+ "model_type": "clip_vision_model",
122
+ "no_repeat_ngram_size": 0,
123
+ "num_attention_heads": 12,
124
+ "num_beam_groups": 1,
125
+ "num_beams": 1,
126
+ "num_hidden_layers": 12,
127
+ "num_return_sequences": 1,
128
+ "output_attentions": false,
129
+ "output_hidden_states": false,
130
+ "output_scores": false,
131
+ "pad_token_id": null,
132
+ "patch_size": 16,
133
+ "prefix": null,
134
+ "problem_type": null,
135
+ "projection_dim" : 512,
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": "4.12.0.dev0",
152
+ "use_bfloat16": false
153
+ },
154
+ "vision_config_dict": {
155
+ "patch_size": 16
156
+ }
157
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "resample": 3,
18
+ "size": 224
19
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20f43a7353ddf6e163025e779655a35009e5d4c8384ad716dc0039abff9a8652
3
+ size 598598078