{
  "_attn_implementation_autoset": false,
  "architectures": [
    "MllamaVisionModel"
  ],
  "attention_heads": 16,
  "dtype": "float32",
  "hidden_act": "gelu",
  "hidden_size": 1280,
  "image_size": 448,
  "initializer_range": 0.02,
  "intermediate_layers_indices": [
    3,
    7,
    15,
    23,
    30
  ],
  "intermediate_size": 5120,
  "max_num_tiles": 4,
  "model_type": "mllama_vision_model",
  "norm_eps": 1e-05,
  "num_channels": 3,
  "num_global_layers": 8,
  "num_hidden_layers": 32,
  "patch_size": 14,
  "supported_aspect_ratios": [
    [
      1,
      1
    ],
    [
      1,
      2
    ],
    [
      1,
      3
    ],
    [
      1,
      4
    ],
    [
      2,
      1
    ],
    [
      2,
      2
    ],
    [
      3,
      1
    ],
    [
      4,
      1
    ]
  ],
  "transformers_version": "4.57.6",
  "vision_output_dim": 7680
}