{
  "architectures": [
    "MPIXELForPreTraining"
  ],
  "attention_probs_dropout_prob": 0.1,
  "decoder_hidden_size": 512,
  "decoder_intermediate_size": 2048,
  "decoder_num_attention_heads": 16,
  "decoder_num_hidden_layers": 8,
  "dtype": "float32",
  "head_init": "pytorch",
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 1024,
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "layer_norm_eps": 1e-12,
  "mask_ratio": 0.25,
  "max_num_patches": 512,
  "model_type": "mpixel",
  "norm_pix_loss": true,
  "num_attention_heads": 16,
  "num_channels": 3,
  "num_hidden_layers": 24,
  "patch_embedding_init": null,
  "patch_size": 16,
  "pooler_add_layer_norm": true,
  "pooling_mode": "mean",
  "qkv_bias": true,
  "reference_compile": false,
  "rope_theta": 160000.0,
  "transformers_version": "4.57.3"
}