[ { "metadataOutputVersion" : "3.0", "storagePrecision" : "Float32", "outputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 1 × 1920)", "shortDescription" : "", "shape" : "[1, 1, 1920]", "name" : "var_724", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 512 × 16)", "shortDescription" : "", "shape" : "[1, 512, 16]", "name" : "var_77", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 2 × 1 × 256 × 8 × 64)", "shortDescription" : "", "shape" : "[2, 1, 256, 8, 64]", "name" : "var_210", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "var_741", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 2 × 1 × 256 × 8 × 64)", "shortDescription" : "", "shape" : "[2, 1, 256, 8, 64]", "name" : "var_400", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "var_744", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 512 × 6)", "shortDescription" : "", "shape" : "[1, 512, 6]", "name" : "var_542", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "conv0_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 256 × 6)", "shortDescription" : "", "shape" : "[1, 256, 6]", "name" : "var_565", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 256 × 2)", "shortDescription" : "", "shape" : "[1, 256, 2]", "name" : "var_585", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "res0_conv0_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 128 × 0)", "shortDescription" : "", "shape" : "[1, 128, 0]", "name" : "res0_conv1_prev", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "res0_conv1_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 128 × 5)", "shortDescription" : "", "shape" : "[1, 128, 5]", "name" : "var_621", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 128 × 2)", "shortDescription" : "", "shape" : "[1, 128, 2]", "name" : "var_641", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "res1_conv0_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 64 × 0)", "shortDescription" : "", "shape" : "[1, 64, 0]", "name" : "res1_conv1_prev", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "res1_conv1_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 64 × 4)", "shortDescription" : "", "shape" : "[1, 64, 4]", "name" : "var_677", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 64 × 2)", "shortDescription" : "", "shape" : "[1, 64, 2]", "name" : "var_697", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "res2_conv0_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 32 × 0)", "shortDescription" : "", "shape" : "[1, 32, 0]", "name" : "res2_conv1_prev", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "res2_conv1_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 64 × 2)", "shortDescription" : "", "shape" : "[1, 64, 2]", "name" : "var_725", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "conv_final_first", "type" : "MultiArray" } ], "modelParameters" : [ ], "specificationVersion" : 8, "mlProgramOperationTypeHistogram" : { "Ios17.notEqual" : 4, "Tile" : 2, "Ios17.lessEqual" : 2, "Ios17.layerNorm" : 4, "Stack" : 6, "Ios17.greaterEqual" : 4, "Ios17.scatterAlongAxis" : 4, "Ios17.sub" : 17, "Identity" : 11, "Ios17.elu" : 10, "Ios17.logicalNot" : 2, "Ios17.sliceByIndex" : 35, "Ios17.concat" : 9, "Ios17.convTranspose" : 4, "Ios17.floorDiv" : 4, "Ios17.expandDims" : 7, "Ios17.less" : 2, "Ios17.mul" : 29, "Ios17.transpose" : 10, "Ios17.matmul" : 4, "Ios16.gelu" : 2, "Ios17.conv" : 9, "Ios17.reshape" : 22, "Split" : 2, "Ios17.squeeze" : 6, "Ios17.cast" : 6, "Ios17.sin" : 2, "Ios17.linear" : 8, "Select" : 6, "Ios16.softmax" : 2, "Ios17.add" : 28, "Ios17.cos" : 2, "Ios17.logicalAnd" : 6 }, "computePrecision" : "Mixed (Float32, Int32)", "isUpdatable" : "0", "stateSchema" : [ ], "availability" : { "macOS" : "14.0", "tvOS" : "17.0", "visionOS" : "1.0", "watchOS" : "10.0", "iOS" : "17.0", "macCatalyst" : "17.0" }, "modelType" : { "name" : "MLModelType_mlProgram" }, "userDefinedMetadata" : { "com.github.apple.coremltools.conversion_date" : "2026-04-24", "com.github.apple.coremltools.source" : "torch==2.9.1", "com.github.apple.coremltools.version" : "9.0", "com.github.apple.coremltools.source_dialect" : "TorchScript" }, "inputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 32)", "shortDescription" : "", "shape" : "[1, 32]", "name" : "latent", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 512 × 16)", "shortDescription" : "", "shape" : "[1, 512, 16]", "name" : "upsample_partial", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 2 × 1 × 256 × 8 × 64)", "shortDescription" : "", "shape" : "[2, 1, 256, 8, 64]", "name" : "attn0_cache", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "attn0_offset", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 2 × 1 × 256 × 8 × 64)", "shortDescription" : "", "shape" : "[2, 1, 256, 8, 64]", "name" : "attn1_cache", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "attn1_offset", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 512 × 6)", "shortDescription" : "", "shape" : "[1, 512, 6]", "name" : "conv0_prev", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "conv0_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 256 × 6)", "shortDescription" : "", "shape" : "[1, 256, 6]", "name" : "convtr0_partial", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 256 × 2)", "shortDescription" : "", "shape" : "[1, 256, 2]", "name" : "res0_conv0_prev", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "res0_conv0_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 128 × 0)", "shortDescription" : "", "shape" : "[1, 128, 0]", "name" : "res0_conv1_prev", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "res0_conv1_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 128 × 5)", "shortDescription" : "", "shape" : "[1, 128, 5]", "name" : "convtr1_partial", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 128 × 2)", "shortDescription" : "", "shape" : "[1, 128, 2]", "name" : "res1_conv0_prev", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "res1_conv0_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 64 × 0)", "shortDescription" : "", "shape" : "[1, 64, 0]", "name" : "res1_conv1_prev", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "res1_conv1_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 64 × 4)", "shortDescription" : "", "shape" : "[1, 64, 4]", "name" : "convtr2_partial", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 64 × 2)", "shortDescription" : "", "shape" : "[1, 64, 2]", "name" : "res2_conv0_prev", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "res2_conv0_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 32 × 0)", "shortDescription" : "", "shape" : "[1, 32, 0]", "name" : "res2_conv1_prev", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "res2_conv1_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1 × 64 × 2)", "shortDescription" : "", "shape" : "[1, 64, 2]", "name" : "conv_final_prev", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float32", "formattedType" : "MultiArray (Float32 1)", "shortDescription" : "", "shape" : "[1]", "name" : "conv_final_first", "type" : "MultiArray" } ], "generatedClassName" : "mimi_decoder", "method" : "predict" } ]