Zero-Shot Image Classification
Transformers
Safetensors
siglip
vision
Inference Endpoints
Merve Noyan
new config
932e6d2
raw
history blame
603 Bytes
{
"architectures": [
"SiglipModel"
],
"initializer_factor": 1.0,
"model_type": "siglip",
"text_config": {
"has_head": false,
"hidden_size": 1152,
"intermediate_size": 4304,
"model_type": "siglip_text_model",
"num_attention_heads": 16,
"num_hidden_layers": 27,
"vocab_size": 250000
},
"torch_dtype": "float32",
"transformers_version": "4.45.0.dev0",
"vision_config": {
"hidden_size": 1152,
"image_size": 256,
"intermediate_size": 4304,
"model_type": "siglip_vision_model",
"num_attention_heads": 16,
"num_hidden_layers": 27
}
}