[ { "metadataOutputVersion" : "3.0", "storagePrecision" : "Float16", "outputSchema" : [ { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 1 × 1920)", "shortDescription" : "", "shape" : "[1, 1, 1920]", "name" : "var_1445", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 512 × 16)", "shortDescription" : "", "shape" : "[1, 512, 16]", "name" : "y_end_1", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 2 × 1 × 8 × 256 × 64)", "shortDescription" : "", "shape" : "[2, 1, 8, 256, 64]", "name" : "new_cache_1_internal_tensor_assign_2", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "var_402", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "new_end_offset_1", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 2 × 1 × 8 × 256 × 64)", "shortDescription" : "", "shape" : "[2, 1, 8, 256, 64]", "name" : "new_cache_internal_tensor_assign_2", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "var_825", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "new_end_offset", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 512 × 6)", "shortDescription" : "", "shape" : "[1, 512, 6]", "name" : "var_998", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "var_1006", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 256 × 6)", "shortDescription" : "", "shape" : "[1, 256, 6]", "name" : "var_1048", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 256 × 2)", "shortDescription" : "", "shape" : "[1, 256, 2]", "name" : "var_1105", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "var_1113", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "var_1134", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 128 × 5)", "shortDescription" : "", "shape" : "[1, 128, 5]", "name" : "var_1178", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 128 × 2)", "shortDescription" : "", "shape" : "[1, 128, 2]", "name" : "var_1235", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "var_1243", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "var_1264", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 64 × 4)", "shortDescription" : "", "shape" : "[1, 64, 4]", "name" : "var_1308", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 64 × 2)", "shortDescription" : "", "shape" : "[1, 64, 2]", "name" : "var_1365", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "var_1373", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "var_1394", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 64 × 2)", "shortDescription" : "", "shape" : "[1, 64, 2]", "name" : "var_1450", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "var_1458", "type" : "MultiArray" } ], "modelParameters" : [ ], "specificationVersion" : 7, "mlProgramOperationTypeHistogram" : { "Transpose" : 10, "Ios16.elu" : 10, "Ios16.scatterAlongAxis" : 4, "Ios16.softmax" : 2, "Ios16.sin" : 2, "Identity" : 3, "Ios16.linear" : 8, "Ios16.add" : 29, "Concat" : 9, "Ios16.convTranspose" : 4, "Tile" : 12, "Select" : 9, "Ios16.greaterEqual" : 6, "Ios16.logicalAnd" : 4, "Ios16.fillLike" : 2, "Ios16.greater" : 5, "Ios16.lessEqual" : 2, "ExpandDims" : 8, "Ios16.sub" : 21, "Ios16.cast" : 4, "Ios16.reshape" : 37, "Ios16.less" : 2, "Ios16.matmul" : 4, "Ios16.layerNorm" : 4, "SliceByIndex" : 43, "Stack" : 4, "Ios16.scatter" : 4, "Ios16.floor" : 4, "Ios16.gelu" : 2, "Ios16.mul" : 34, "Ios16.cos" : 2, "Ios16.conv" : 8 }, "computePrecision" : "Mixed (Float16, Int32)", "isUpdatable" : "0", "stateSchema" : [ ], "availability" : { "macOS" : "13.0", "tvOS" : "16.0", "visionOS" : "1.0", "watchOS" : "9.0", "iOS" : "16.0", "macCatalyst" : "16.0" }, "modelType" : { "name" : "MLModelType_mlProgram" }, "userDefinedMetadata" : { "com.github.apple.coremltools.conversion_date" : "2026-01-28", "com.github.apple.coremltools.source" : "torch==2.10.0", "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 × 512 × 1)", "shortDescription" : "", "shape" : "[1, 512, 1]", "name" : "latent", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 512 × 16)", "shortDescription" : "", "shape" : "[1, 512, 16]", "name" : "upsample_partial", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 2 × 1 × 8 × 256 × 64)", "shortDescription" : "", "shape" : "[2, 1, 8, 256, 64]", "name" : "attn0_cache", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "attn0_offset", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "attn0_end_offset", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 2 × 1 × 8 × 256 × 64)", "shortDescription" : "", "shape" : "[2, 1, 8, 256, 64]", "name" : "attn1_cache", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "attn1_offset", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "attn1_end_offset", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 512 × 6)", "shortDescription" : "", "shape" : "[1, 512, 6]", "name" : "conv0_prev", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "conv0_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 256 × 6)", "shortDescription" : "", "shape" : "[1, 256, 6]", "name" : "convtr0_partial", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 256 × 2)", "shortDescription" : "", "shape" : "[1, 256, 2]", "name" : "res0_conv0_prev", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "res0_conv0_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "res0_conv1_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 128 × 5)", "shortDescription" : "", "shape" : "[1, 128, 5]", "name" : "convtr1_partial", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 128 × 2)", "shortDescription" : "", "shape" : "[1, 128, 2]", "name" : "res1_conv0_prev", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "res1_conv0_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "res1_conv1_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 64 × 4)", "shortDescription" : "", "shape" : "[1, 64, 4]", "name" : "convtr2_partial", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 64 × 2)", "shortDescription" : "", "shape" : "[1, 64, 2]", "name" : "res2_conv0_prev", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "res2_conv0_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "res2_conv1_first", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1 × 64 × 2)", "shortDescription" : "", "shape" : "[1, 64, 2]", "name" : "conv_final_prev", "type" : "MultiArray" }, { "hasShapeFlexibility" : "0", "isOptional" : "0", "dataType" : "Float16", "formattedType" : "MultiArray (Float16 1)", "shortDescription" : "", "shape" : "[1]", "name" : "conv_final_first", "type" : "MultiArray" } ], "generatedClassName" : "mimi_decoder_v3", "method" : "predict" } ]