[
  {
    "metadataOutputVersion" : "3.0",
    "storagePrecision" : "Float16",
    "outputSchema" : [
      {
        "hasShapeFlexibility" : "0",
        "isOptional" : "0",
        "dataType" : "Float16",
        "formattedType" : "MultiArray (Float16 1 × 256 × 1536)",
        "shortDescription" : "",
        "shape" : "[1, 256, 1536]",
        "name" : "image_features",
        "type" : "MultiArray"
      }
    ],
    "modelParameters" : [

    ],
    "specificationVersion" : 9,
    "mlProgramOperationTypeHistogram" : {
      "Ios18.expandDims" : 134,
      "Ios18.mul" : 423,
      "Ios18.cos" : 2,
      "Ios18.softmax" : 16,
      "Ios18.matmul" : 36,
      "Ios18.floorDiv" : 2,
      "Ios16.reduceMean" : 112,
      "Ios18.logicalNot" : 1,
      "Ios18.equal" : 1,
      "Ios18.sin" : 2,
      "Split" : 97,
      "Select" : 2,
      "Ios16.reduceMax" : 1,
      "Ios16.reduceMin" : 1,
      "Ios18.add" : 227,
      "Ios16.reduceSum" : 1,
      "Tile" : 1,
      "Ios18.layerNorm" : 1,
      "Ios18.reshape" : 64,
      "Ios18.maximum" : 1,
      "Ios18.linear" : 114,
      "Ios18.concat" : 101,
      "Ios18.transpose" : 67,
      "OneHot" : 2,
      "Ios18.sub" : 2,
      "Ios18.cast" : 10,
      "Ios18.pow" : 224,
      "Ios18.clip" : 176,
      "Ios18.gelu" : 16,
      "Ios18.sliceByIndex" : 133
    },
    "computePrecision" : "Mixed (Float16, Int32)",
    "isUpdatable" : "0",
    "stateSchema" : [

    ],
    "availability" : {
      "macOS" : "15.0",
      "tvOS" : "18.0",
      "visionOS" : "2.0",
      "watchOS" : "11.0",
      "iOS" : "18.0",
      "macCatalyst" : "18.0"
    },
    "modelType" : {
      "name" : "MLModelType_mlProgram"
    },
    "userDefinedMetadata" : {
      "com.github.apple.coremltools.conversion_date" : "2026-04-24",
      "com.github.apple.coremltools.source" : "torch==2.9.0",
      "com.github.apple.coremltools.version" : "9.0",
      "com.github.apple.coremltools.source_dialect" : "TorchScript"
    },
    "inputSchema" : [
      {
        "hasShapeFlexibility" : "0",
        "isOptional" : "0",
        "dataType" : "Float16",
        "formattedType" : "MultiArray (Float16 1 × 2304 × 768)",
        "shortDescription" : "",
        "shape" : "[1, 2304, 768]",
        "name" : "pixel_values",
        "type" : "MultiArray"
      },
      {
        "hasShapeFlexibility" : "0",
        "isOptional" : "0",
        "dataType" : "Int32",
        "formattedType" : "MultiArray (Int32 1 × 2304 × 2)",
        "shortDescription" : "",
        "shape" : "[1, 2304, 2]",
        "name" : "pixel_position_ids",
        "type" : "MultiArray"
      }
    ],
    "generatedClassName" : "vision_ane",
    "method" : "predict"
  }
]