| [ | |
| { | |
| "shortDescription" : "CLIP ViT-B\/32 model trained with DataComp-1B (Text Encoder Model)", | |
| "metadataOutputVersion" : "3.0", | |
| "outputSchema" : [ | |
| { | |
| "hasShapeFlexibility" : "0", | |
| "isOptional" : "0", | |
| "dataType" : "Float32", | |
| "formattedType" : "MultiArray (Float32 1 × 512)", | |
| "shortDescription" : "--", | |
| "shape" : "[1, 512]", | |
| "name" : "var_1317", | |
| "type" : "MultiArray" | |
| } | |
| ], | |
| "version" : "1.0.0", | |
| "modelParameters" : [ | |
| ], | |
| "author" : "InspiratioNULL 2026", | |
| "specificationVersion" : 6, | |
| "storagePrecision" : "Float16", | |
| "license" : "MIT", | |
| "mlProgramOperationTypeHistogram" : { | |
| "Linear" : 49, | |
| "SliceByIndex" : 36, | |
| "LayerNorm" : 25, | |
| "Transpose" : 84, | |
| "Matmul" : 24, | |
| "Gelu" : 12, | |
| "Stack" : 1, | |
| "Softmax" : 12, | |
| "Squeeze" : 12, | |
| "Reshape" : 108, | |
| "Mul" : 12, | |
| "Add" : 37, | |
| "ExpandDims" : 12, | |
| "ReduceArgmax" : 1, | |
| "Gather" : 1, | |
| "GatherNd" : 1, | |
| "Cast" : 1 | |
| }, | |
| "computePrecision" : "Mixed (Float16, Float32, Int32)", | |
| "stateSchema" : [ | |
| ], | |
| "isUpdatable" : "0", | |
| "availability" : { | |
| "macOS" : "12.0", | |
| "tvOS" : "15.0", | |
| "visionOS" : "1.0", | |
| "watchOS" : "8.0", | |
| "iOS" : "15.0", | |
| "macCatalyst" : "15.0" | |
| }, | |
| "modelType" : { | |
| "name" : "MLModelType_mlProgram" | |
| }, | |
| "inputSchema" : [ | |
| { | |
| "hasShapeFlexibility" : "0", | |
| "isOptional" : "0", | |
| "dataType" : "Int32", | |
| "formattedType" : "MultiArray (Int32 1 × 77)", | |
| "shortDescription" : "--", | |
| "shape" : "[1, 77]", | |
| "name" : "text", | |
| "type" : "MultiArray" | |
| } | |
| ], | |
| "userDefinedMetadata" : { | |
| "com.github.apple.coremltools.conversion_date" : "2026-01-15", | |
| "com.github.apple.coremltools.source" : "torch==2.9.1", | |
| "com.github.apple.coremltools.version" : "9.0", | |
| "com.github.apple.coremltools.source_dialect" : "TorchScript" | |
| }, | |
| "generatedClassName" : "CLIP_TextEncoder", | |
| "method" : "predict" | |
| } | |
| ] |