Hugging Face's logo

Xenova
/
clip-vit-base-patch16

Zero-Shot Image Classification
Transformers.js
ONNX
clip
Model card Files Community
Xenova HF staff commited on
Commit
152e33c
•
1 Parent(s): a69ef9d

Revert update to config.json

Browse files
Files changed (1) hide show
  1. config.json +162 -15
config.json CHANGED
@@ -1,20 +1,167 @@
1
  {
 
 
 
 
 
 
 
2
  "model_type": "clip",
3
- "img_encoder":{
4
- "backbone":"deit3_base_patch16_224_in21ft1k",
5
- "dim":768,
6
- "pooling":"cls",
7
- "output_dim":256,
8
- "backbone_type":"vit"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  },
10
- "text_encoder":{
11
- "backbone":"sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
12
- "backbone_type":"bert",
13
- "unimodal_n_layers":8,
14
- "dim":384,
15
- "pooling":"mean",
16
- "context_dim":768,
17
- "output_dim":256,
18
- "head_one_neuron":true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  }
20
  }
 
1
  {
2
+ "_commit_hash": "57c216476eefef5ab752ec549e440a49ae4ae5f3",
3
+ "_name_or_path": "openai/clip-vit-base-patch16",
4
+ "architectures": [
5
+ "CLIPModel"
6
+ ],
7
+ "initializer_factor": 1.0,
8
+ "logit_scale_init_value": 2.6592,
9
  "model_type": "clip",
10
+ "projection_dim": 512,
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": 512,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1"
37
+ },
38
+ "initializer_factor": 1.0,
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 2048,
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": 8,
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": 512,
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": "4.29.2",
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "vocab_size": 49408
87
  },
88
+ "transformers_version": null,
89
+ "vision_config": {
90
+ "_name_or_path": "",
91
+ "add_cross_attention": false,
92
+ "architectures": null,
93
+ "attention_dropout": 0.0,
94
+ "bad_words_ids": null,
95
+ "begin_suppress_tokens": null,
96
+ "bos_token_id": null,
97
+ "chunk_size_feed_forward": 0,
98
+ "cross_attention_hidden_size": null,
99
+ "decoder_start_token_id": null,
100
+ "diversity_penalty": 0.0,
101
+ "do_sample": false,
102
+ "dropout": 0.0,
103
+ "early_stopping": false,
104
+ "encoder_no_repeat_ngram_size": 0,
105
+ "eos_token_id": null,
106
+ "exponential_decay_length_penalty": 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": 768,
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": 3072,
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": 12,
133
+ "num_beam_groups": 1,
134
+ "num_beams": 1,
135
+ "num_channels": 3,
136
+ "num_hidden_layers": 12,
137
+ "num_return_sequences": 1,
138
+ "output_attentions": false,
139
+ "output_hidden_states": false,
140
+ "output_scores": false,
141
+ "pad_token_id": null,
142
+ "patch_size": 16,
143
+ "prefix": null,
144
+ "problem_type": null,
145
+ "projection_dim": 512,
146
+ "pruned_heads": {},
147
+ "remove_invalid_values": false,
148
+ "repetition_penalty": 1.0,
149
+ "return_dict": true,
150
+ "return_dict_in_generate": false,
151
+ "sep_token_id": null,
152
+ "suppress_tokens": null,
153
+ "task_specific_params": null,
154
+ "temperature": 1.0,
155
+ "tf_legacy_loss": false,
156
+ "tie_encoder_decoder": false,
157
+ "tie_word_embeddings": true,
158
+ "tokenizer_class": null,
159
+ "top_k": 50,
160
+ "top_p": 1.0,
161
+ "torch_dtype": null,
162
+ "torchscript": false,
163
+ "transformers_version": "4.29.2",
164
+ "typical_p": 1.0,
165
+ "use_bfloat16": false
166
  }
167
  }