{
  "_name_or_path": "WAC_MIM/trained_models/pytorch_model.bin",
  "architectures": [
    "VisionTransformer"
  ],
  "attention_implementation": "sdpa",
  "attention_probability_dropout_probability": 0.1,
  "dropout_probability": 0.1,
  "embedding_size": 128,
  "hidden_activation_function": "gelu",
  "hidden_size": 256,
  "image_size": 224,
  "initializer_factor": 1.0,
  "intermediate_size": 1024,
  "layer_norm_eps": 1e-12,
  "num_attention_heads": 4,
  "num_channels": 3,
  "num_hidden_layers": 12,
  "num_intermediate_layers": 3,
  "patch_size": 16,
  "qkv_bias": false,
  "remove_last_layer": false,
  "share_layer_norm": true,
  "stop_gradient": false,
  "torch_dtype": "float32",
  "transformers_version": "4.48.3",
  "use_mask_token": false
}