|
{ |
|
"architectures": [ |
|
"SiglipVisionTransformer" |
|
], |
|
"auto_map": { |
|
"AutoConfig": "modeling_navit_siglip.SiglipVisionConfig", |
|
"AutoModel": "modeling_navit_siglip.SiglipVisionTransformer", |
|
"AutoModelForCausalLM": "modeling_navit_siglip.SiglipVisionTransformer" |
|
}, |
|
"attention_dropout": 0.0, |
|
"hidden_act": "gelu_pytorch_tanh", |
|
"hidden_size": 1152, |
|
"image_size": 980, |
|
"intermediate_size": 4304, |
|
"layer_norm_eps": 1e-06, |
|
"model_type": "siglip_vision_model", |
|
"num_attention_heads": 16, |
|
"num_channels": 3, |
|
"num_hidden_layers": 27, |
|
"patch_size": 14, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.40.0" |
|
} |
|
|