{
  "architectures": [
    "PIXBAForPreTraining"
  ],
  "attention_probs_dropout_prob": 0.1,
  "bias": false,
  "cache_dir": null,
  "conv_bias": true,
  "d_conv": 4,
  "d_model": 768,
  "d_state": 16,
  "decoder_hidden_size": 512,
  "decoder_intermediate_size": 2048,
  "decoder_num_attention_heads": 16,
  "decoder_num_hidden_layers": 8,
  "device": null,
  "dt_init": "random",
  "dt_init_floor": 0.0001,
  "dt_max": 0.1,
  "dt_min": 0.001,
  "dt_rank": "auto",
  "dt_scale": 1.0,
  "dtype": null,
  "expand": 2,
  "fused_add_norm": true,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "image_size": [
    16,
    8464
  ],
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-12,
  "mask_ratio": 0.25,
  "model_type": "pixel",
  "norm_pix_loss": true,
  "num_attention_heads": 12,
  "num_channels": 3,
  "num_decoder_layers": 2,
  "num_encoder_layers": 4,
  "num_hidden_layers": 12,
  "num_patches": 529,
  "pad_vocab_size_multiple": 8,
  "patch_size": 16,
  "qkv_bias": true,
  "residual_in_fp32": true,
  "revision": "main",
  "rms_norm": true,
  "ssm_cfg": {},
  "torch_dtype": "float32",
  "transformers_version": "4.17.0",
  "use_auth_token": "redacted",
  "use_fast_path": true,
  "vocab_size": 50277
}