{
  "architectures": [
    "MllamaVisionModel"
  ],
  "attention_heads": 4,
  "dropout": 0.1,
  "dtype": "float32",
  "hidden_act": "gelu",
  "hidden_size": 16,
  "image_size": 30,
  "initializer_range": 0.02,
  "intermediate_layers_indices": [
    0
  ],
  "intermediate_size": 37,
  "max_num_tiles": 4,
  "model_type": "mllama_vision_model",
  "norm_eps": 1e-05,
  "num_channels": 3,
  "num_global_layers": 2,
  "num_hidden_layers": 2,
  "patch_size": 2,
  "projection_dim": 32,
  "supported_aspect_ratios": [
    [
      1,
      1
    ],
    [
      1,
      2
    ],
    [
      1,
      3
    ],
    [
      1,
      4
    ],
    [
      2,
      1
    ],
    [
      2,
      2
    ],
    [
      3,
      1
    ],
    [
      4,
      1
    ]
  ],
  "transformers_version": "5.16.0.dev0",
  "vision_output_dim": 32
}