Zero-Shot Image Classification
Transformers
Safetensors
siglip
vision
Inference Endpoints
File size: 576 Bytes
c0d525b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
{
  "architectures": [
    "SiglipModel"
  ],
  "initializer_factor": 1.0,
  "model_type": "siglip",
  "text_config": {
    "hidden_size": 1152,
    "intermediate_size": 4304,
    "model_type": "siglip_text_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 27
  },
  "torch_dtype": "float32",
  "transformers_version": "4.37.0.dev0",
  "vision_config": {
    "hidden_size": 1152,
    "image_size": 384,
    "intermediate_size": 4304,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 27,
    "patch_size": 14
  }
}