Hugging Face's logo

humane-lab
/
CFT-CLIP

Zero-Shot Image Classification
Transformers
PyTorch
English
clip
Inference Endpoints
Model card Files Community
yejunyoon commited on
Commit
384e323
•
1 Parent(s): 314dd93

add:file

Browse files
Files changed (3) hide show
  1. config.json +171 -0
  2. pytorch_model.bin +3 -0
  3. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "projection_dim" : 768,
63
+ "pruned_heads": {},
64
+ "remove_invalid_values": false,
65
+ "repetition_penalty": 1.0,
66
+ "return_dict": true,
67
+ "return_dict_in_generate": false,
68
+ "sep_token_id": null,
69
+ "task_specific_params": null,
70
+ "temperature": 1.0,
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": "4.16.0.dev0",
79
+ "use_bfloat16": false,
80
+ "vocab_size": 49408
81
+ },
82
+ "text_config_dict": {
83
+ "hidden_size": 768,
84
+ "intermediate_size": 3072,
85
+ "num_attention_heads": 12,
86
+ "num_hidden_layers": 12,
87
+ "projection_dim": 768
88
+ },
89
+ "torch_dtype": "float32",
90
+ "transformers_version": null,
91
+ "vision_config": {
92
+ "_name_or_path": "",
93
+ "add_cross_attention": false,
94
+ "architectures": null,
95
+ "attention_dropout": 0.0,
96
+ "bad_words_ids": null,
97
+ "bos_token_id": null,
98
+ "chunk_size_feed_forward": 0,
99
+ "cross_attention_hidden_size": null,
100
+ "decoder_start_token_id": null,
101
+ "diversity_penalty": 0.0,
102
+ "do_sample": false,
103
+ "dropout": 0.0,
104
+ "early_stopping": false,
105
+ "encoder_no_repeat_ngram_size": 0,
106
+ "eos_token_id": null,
107
+ "finetuning_task": null,
108
+ "forced_bos_token_id": null,
109
+ "forced_eos_token_id": null,
110
+ "hidden_act": "quick_gelu",
111
+ "hidden_size": 1024,
112
+ "id2label": {
113
+ "0": "LABEL_0",
114
+ "1": "LABEL_1"
115
+ },
116
+ "image_size": 224,
117
+ "initializer_factor": 1.0,
118
+ "initializer_range": 0.02,
119
+ "intermediate_size": 4096,
120
+ "is_decoder": false,
121
+ "is_encoder_decoder": false,
122
+ "label2id": {
123
+ "LABEL_0": 0,
124
+ "LABEL_1": 1
125
+ },
126
+ "layer_norm_eps": 1e-05,
127
+ "length_penalty": 1.0,
128
+ "max_length": 20,
129
+ "min_length": 0,
130
+ "model_type": "clip_vision_model",
131
+ "no_repeat_ngram_size": 0,
132
+ "num_attention_heads": 16,
133
+ "num_beam_groups": 1,
134
+ "num_beams": 1,
135
+ "num_hidden_layers": 24,
136
+ "num_return_sequences": 1,
137
+ "output_attentions": false,
138
+ "output_hidden_states": false,
139
+ "output_scores": false,
140
+ "pad_token_id": null,
141
+ "patch_size": 14,
142
+ "prefix": null,
143
+ "problem_type": null,
144
+ "projection_dim" : 768,
145
+ "pruned_heads": {},
146
+ "remove_invalid_values": false,
147
+ "repetition_penalty": 1.0,
148
+ "return_dict": true,
149
+ "return_dict_in_generate": false,
150
+ "sep_token_id": null,
151
+ "task_specific_params": null,
152
+ "temperature": 1.0,
153
+ "tie_encoder_decoder": false,
154
+ "tie_word_embeddings": true,
155
+ "tokenizer_class": null,
156
+ "top_k": 50,
157
+ "top_p": 1.0,
158
+ "torch_dtype": null,
159
+ "torchscript": false,
160
+ "transformers_version": "4.16.0.dev0",
161
+ "use_bfloat16": false
162
+ },
163
+ "vision_config_dict": {
164
+ "hidden_size": 1024,
165
+ "intermediate_size": 4096,
166
+ "num_attention_heads": 16,
167
+ "num_hidden_layers": 24,
168
+ "patch_size": 14,
169
+ "projection_dim": 768
170
+ }
171
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed9a08a6b94048d026515774300e6744d23cfbfb67a6ef45e57acf4ce86ce4fa
3
+ size 1710668259
vocab.json ADDED
The diff for this file is too large to render. See raw diff