{
  "architectures": [
    "SpatialSpectralMAEViT"
  ],
  "attention_radius": 640,
  "attn_drop": 0.1,
  "channel_dim": 24,
  "channel_dropout": [
    0.75,
    0.85
  ],
  "channel_mask_ratio": 0.75,
  "decoder_attention_radius": [
    640
  ],
  "decoder_channel_dim": 32,
  "decoder_depth": 8,
  "decoder_embed_dim": 512,
  "decoder_history_length": [
    4
  ],
  "decoder_num_heads": 16,
  "decoder_out_chans": 155,
  "decoder_out_dims": 1,
  "decoder_spatial_dim": 256,
  "decoder_temporal_embed_dims_per_head": 4,
  "depth": 12,
  "drop_path_rate": 0.1,
  "drop_path_uniform": false,
  "embed_dim": 768,
  "init_values": 1.0,
  "mask_ratio": 0.75,
  "mlp_ratio": 4.0,
  "model_type": "multi_modal_low_rank_vit",
  "norm_pix_loss": false,
  "num_heads": 12,
  "patch_size": 16,
  "pos_chan_embed_residual": true,
  "pretrain": true,
  "proj_drop": 0.1,
  "qk_norm": false,
  "qkv_bias": true,
  "rank": 1,
  "return_dict": false,
  "rope_embed_base": 100.0,
  "spatial_dim": 384,
  "use_perception_field_mask": true,
  "use_rope_embed": true,
  "channel_embed_dims_per_head": 2
}