| [ |
| { |
| "metadataOutputVersion" : "3.0", |
| "userDefinedMetadata" : { |
| "com.github.apple.coremltools.version" : "9.0", |
| "com.github.apple.coremltools.source_dialect" : "TorchScript", |
| "com.anemll.context_length" : "4096", |
| "com.github.apple.coremltools.source" : "torch==2.5.0", |
| "com.anemll.lut_bits" : "6", |
| "com.anemll.num_chunks" : "1", |
| "com.anemll.batch_size" : "64", |
| "com.anemll.info" : "Converted with Anemll v0.3.5", |
| "com.anemll.chunk_no" : "1" |
| }, |
| "availability" : { |
| "macOS" : "15.0", |
| "tvOS" : "18.0", |
| "visionOS" : "2.0", |
| "watchOS" : "11.0", |
| "iOS" : "18.0", |
| "macCatalyst" : "18.0" |
| }, |
| "inputSchema" : [ |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 1 × 1152)", |
| "shortDescription" : "", |
| "shape" : "[1, 1, 1152]", |
| "name" : "hidden_states", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Int32", |
| "formattedType" : "MultiArray (Int32 1)", |
| "shortDescription" : "", |
| "shape" : "[1]", |
| "name" : "position_ids", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 4096)", |
| "shortDescription" : "", |
| "shape" : "[1, 1, 1, 4096]", |
| "name" : "causal_mask", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Int32", |
| "formattedType" : "MultiArray (Int32 1)", |
| "shortDescription" : "", |
| "shape" : "[1]", |
| "name" : "current_pos", |
| "type" : "MultiArray" |
| } |
| ], |
| "outputSchema" : [ |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 1 × 1152)", |
| "shortDescription" : "", |
| "shape" : "[1, 1, 1152]", |
| "name" : "output_hidden_states", |
| "type" : "MultiArray" |
| } |
| ], |
| "modelParameters" : [ |
|
|
| ], |
| "storagePrecision" : "Mixed (Float16, Palettized (11 bits), Palettized (13 bits), Palettized (14 bits), Palettized (16 bits), UInt6)", |
| "method" : "predict", |
| "functions" : [ |
| { |
| "inputSchema" : [ |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 1 × 1152)", |
| "shortDescription" : "", |
| "shape" : "[1, 1, 1152]", |
| "name" : "hidden_states", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Int32", |
| "formattedType" : "MultiArray (Int32 1)", |
| "shortDescription" : "", |
| "shape" : "[1]", |
| "name" : "position_ids", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 4096)", |
| "shortDescription" : "", |
| "shape" : "[1, 1, 1, 4096]", |
| "name" : "causal_mask", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Int32", |
| "formattedType" : "MultiArray (Int32 1)", |
| "shortDescription" : "", |
| "shape" : "[1]", |
| "name" : "current_pos", |
| "type" : "MultiArray" |
| } |
| ], |
| "computePrecision" : "Mixed (Float16, Int16, Int32, UInt16)", |
| "storagePrecision" : "Mixed (Float16, Palettized (11 bits), Palettized (13 bits), Palettized (14 bits), Palettized (16 bits), UInt6)", |
| "stateSchema" : [ |
| { |
| "dataType" : "Float16", |
| "isOptional" : "0", |
| "formattedType" : "State (Float16 44 × 1 × 512 × 256)", |
| "shortDescription" : "", |
| "shape" : "[44, 1, 512, 256]", |
| "name" : "model_model_kv_cache_local", |
| "type" : "State" |
| }, |
| { |
| "dataType" : "Float16", |
| "isOptional" : "0", |
| "formattedType" : "State (Float16 8 × 1 × 4096 × 256)", |
| "shortDescription" : "", |
| "shape" : "[8, 1, 4096, 256]", |
| "name" : "model_model_kv_cache_global", |
| "type" : "State" |
| } |
| ], |
| "outputSchema" : [ |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 1 × 1152)", |
| "shortDescription" : "", |
| "shape" : "[1, 1, 1152]", |
| "name" : "output_hidden_states", |
| "type" : "MultiArray" |
| } |
| ], |
| "name" : "infer", |
| "mlProgramOperationTypeHistogram" : { |
| "Ios18.expandDims" : 52, |
| "Ios18.softmax" : 26, |
| "Ios18.mul" : 524, |
| "Ios18.matmul" : 52, |
| "Identity" : 1, |
| "Ios18.greaterEqual" : 2, |
| "Select" : 2, |
| "Ios18.readState" : 54, |
| "Tile" : 52, |
| "Ios18.gather" : 4, |
| "Ios18.add" : 135, |
| "Ios18.layerNorm" : 157, |
| "Ios18.sliceUpdate" : 52, |
| "Ios18.writeState" : 52, |
| "Ios18.reshape" : 109, |
| "Ios18.constexprLutToDense" : 182, |
| "Ios18.conv" : 182, |
| "Ios18.concat" : 297, |
| "Ios18.transpose" : 156, |
| "Ios18.cast" : 5, |
| "Ios18.gelu" : 26, |
| "Ios18.sliceByIndex" : 322, |
| "Ios18.squeeze" : 26 |
| } |
| }, |
| { |
| "inputSchema" : [ |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 1 × 1152)", |
| "shortDescription" : "", |
| "shape" : "[1, 1, 1152]", |
| "name" : "hidden_states", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Int32", |
| "formattedType" : "MultiArray (Int32 1)", |
| "shortDescription" : "", |
| "shape" : "[1]", |
| "name" : "position_ids", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 4096)", |
| "shortDescription" : "", |
| "shape" : "[1, 1, 1, 4096]", |
| "name" : "causal_mask", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Int32", |
| "formattedType" : "MultiArray (Int32 1)", |
| "shortDescription" : "", |
| "shape" : "[1]", |
| "name" : "current_pos", |
| "type" : "MultiArray" |
| } |
| ], |
| "computePrecision" : "Mixed (Float16, Int16, Int32, UInt16)", |
| "storagePrecision" : "Mixed (Float16, Palettized (11 bits), Palettized (13 bits), Palettized (14 bits), Palettized (16 bits), UInt6)", |
| "stateSchema" : [ |
| { |
| "dataType" : "Float16", |
| "isOptional" : "0", |
| "formattedType" : "State (Float16 44 × 1 × 512 × 256)", |
| "shortDescription" : "", |
| "shape" : "[44, 1, 512, 256]", |
| "name" : "model_model_kv_cache_local", |
| "type" : "State" |
| }, |
| { |
| "dataType" : "Float16", |
| "isOptional" : "0", |
| "formattedType" : "State (Float16 8 × 1 × 4096 × 256)", |
| "shortDescription" : "", |
| "shape" : "[8, 1, 4096, 256]", |
| "name" : "model_model_kv_cache_global", |
| "type" : "State" |
| } |
| ], |
| "outputSchema" : [ |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 1 × 1152)", |
| "shortDescription" : "", |
| "shape" : "[1, 1, 1152]", |
| "name" : "output_hidden_states", |
| "type" : "MultiArray" |
| } |
| ], |
| "name" : "infer_rotate", |
| "mlProgramOperationTypeHistogram" : { |
| "Ios18.expandDims" : 52, |
| "Ios18.softmax" : 26, |
| "Ios18.mul" : 524, |
| "Ios18.matmul" : 52, |
| "Identity" : 1, |
| "Ios18.greaterEqual" : 2, |
| "Select" : 2, |
| "Ios18.readState" : 54, |
| "Tile" : 52, |
| "Ios18.gather" : 4, |
| "Ios18.add" : 135, |
| "Ios18.layerNorm" : 157, |
| "Ios18.sliceUpdate" : 52, |
| "Ios18.writeState" : 52, |
| "Ios18.reshape" : 109, |
| "Ios18.constexprLutToDense" : 182, |
| "Ios18.conv" : 182, |
| "Ios18.concat" : 269, |
| "Ios18.transpose" : 156, |
| "Ios18.cast" : 5, |
| "Ios18.gelu" : 26, |
| "Ios18.sliceByIndex" : 410, |
| "Ios18.squeeze" : 26 |
| } |
| }, |
| { |
| "inputSchema" : [ |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 64 × 1152)", |
| "shortDescription" : "", |
| "shape" : "[1, 64, 1152]", |
| "name" : "hidden_states", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Int32", |
| "formattedType" : "MultiArray (Int32 64)", |
| "shortDescription" : "", |
| "shape" : "[64]", |
| "name" : "position_ids", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 1 × 64 × 4096)", |
| "shortDescription" : "", |
| "shape" : "[1, 1, 64, 4096]", |
| "name" : "causal_mask", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Int32", |
| "formattedType" : "MultiArray (Int32 1)", |
| "shortDescription" : "", |
| "shape" : "[1]", |
| "name" : "current_pos", |
| "type" : "MultiArray" |
| } |
| ], |
| "computePrecision" : "Mixed (Float16, Int16, Int32, UInt16)", |
| "storagePrecision" : "Mixed (Float16, Palettized (11 bits), Palettized (13 bits), Palettized (14 bits), Palettized (16 bits), UInt6)", |
| "stateSchema" : [ |
| { |
| "dataType" : "Float16", |
| "isOptional" : "0", |
| "formattedType" : "State (Float16 44 × 1 × 512 × 256)", |
| "shortDescription" : "", |
| "shape" : "[44, 1, 512, 256]", |
| "name" : "model_model_kv_cache_local", |
| "type" : "State" |
| }, |
| { |
| "dataType" : "Float16", |
| "isOptional" : "0", |
| "formattedType" : "State (Float16 8 × 1 × 4096 × 256)", |
| "shortDescription" : "", |
| "shape" : "[8, 1, 4096, 256]", |
| "name" : "model_model_kv_cache_global", |
| "type" : "State" |
| } |
| ], |
| "outputSchema" : [ |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 1 × 1152)", |
| "shortDescription" : "", |
| "shape" : "[1, 1, 1152]", |
| "name" : "output_hidden_states", |
| "type" : "MultiArray" |
| } |
| ], |
| "name" : "prefill", |
| "mlProgramOperationTypeHistogram" : { |
| "Ios18.expandDims" : 52, |
| "Ios18.softmax" : 26, |
| "Ios18.mul" : 522, |
| "Ios18.matmul" : 52, |
| "Ios18.greaterEqual" : 2, |
| "Select" : 2, |
| "Ios18.readState" : 54, |
| "Tile" : 52, |
| "Ios18.gather" : 4, |
| "Ios18.add" : 135, |
| "Ios18.layerNorm" : 156, |
| "Ios18.sliceUpdate" : 52, |
| "Ios18.writeState" : 52, |
| "Ios18.reshape" : 187, |
| "Ios18.constexprLutToDense" : 182, |
| "Ios18.conv" : 182, |
| "Ios18.concat" : 296, |
| "Ios18.transpose" : 238, |
| "Ios18.cast" : 5, |
| "Ios18.gelu" : 26, |
| "Ios18.sliceByIndex" : 322, |
| "Ios18.squeeze" : 26 |
| } |
| }, |
| { |
| "inputSchema" : [ |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 64 × 1152)", |
| "shortDescription" : "", |
| "shape" : "[1, 64, 1152]", |
| "name" : "hidden_states", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Int32", |
| "formattedType" : "MultiArray (Int32 64)", |
| "shortDescription" : "", |
| "shape" : "[64]", |
| "name" : "position_ids", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 1 × 64 × 4096)", |
| "shortDescription" : "", |
| "shape" : "[1, 1, 64, 4096]", |
| "name" : "causal_mask", |
| "type" : "MultiArray" |
| }, |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Int32", |
| "formattedType" : "MultiArray (Int32 1)", |
| "shortDescription" : "", |
| "shape" : "[1]", |
| "name" : "current_pos", |
| "type" : "MultiArray" |
| } |
| ], |
| "computePrecision" : "Mixed (Float16, Int16, Int32, UInt16)", |
| "storagePrecision" : "Mixed (Float16, Palettized (11 bits), Palettized (13 bits), Palettized (14 bits), Palettized (16 bits), UInt6)", |
| "stateSchema" : [ |
| { |
| "dataType" : "Float16", |
| "isOptional" : "0", |
| "formattedType" : "State (Float16 44 × 1 × 512 × 256)", |
| "shortDescription" : "", |
| "shape" : "[44, 1, 512, 256]", |
| "name" : "model_model_kv_cache_local", |
| "type" : "State" |
| }, |
| { |
| "dataType" : "Float16", |
| "isOptional" : "0", |
| "formattedType" : "State (Float16 8 × 1 × 4096 × 256)", |
| "shortDescription" : "", |
| "shape" : "[8, 1, 4096, 256]", |
| "name" : "model_model_kv_cache_global", |
| "type" : "State" |
| } |
| ], |
| "outputSchema" : [ |
| { |
| "hasShapeFlexibility" : "0", |
| "isOptional" : "0", |
| "dataType" : "Float16", |
| "formattedType" : "MultiArray (Float16 1 × 1 × 1152)", |
| "shortDescription" : "", |
| "shape" : "[1, 1, 1152]", |
| "name" : "output_hidden_states", |
| "type" : "MultiArray" |
| } |
| ], |
| "name" : "prefill_rotate", |
| "mlProgramOperationTypeHistogram" : { |
| "Ios18.expandDims" : 52, |
| "Ios18.softmax" : 26, |
| "Ios18.mul" : 522, |
| "Ios18.matmul" : 52, |
| "Ios18.greaterEqual" : 2, |
| "Select" : 2, |
| "Ios18.readState" : 54, |
| "Tile" : 52, |
| "Ios18.gather" : 4, |
| "Ios18.add" : 135, |
| "Ios18.layerNorm" : 156, |
| "Ios18.sliceUpdate" : 52, |
| "Ios18.writeState" : 52, |
| "Ios18.reshape" : 187, |
| "Ios18.constexprLutToDense" : 182, |
| "Ios18.conv" : 182, |
| "Ios18.concat" : 268, |
| "Ios18.transpose" : 238, |
| "Ios18.cast" : 5, |
| "Ios18.gelu" : 26, |
| "Ios18.sliceByIndex" : 410, |
| "Ios18.squeeze" : 26 |
| } |
| } |
| ], |
| "version" : "0.3.5", |
| "isUpdatable" : "0", |
| "defaultFunctionName" : "infer", |
| "specificationVersion" : 9, |
| "stateSchema" : [ |
| { |
| "dataType" : "Float16", |
| "isOptional" : "0", |
| "formattedType" : "State (Float16 44 × 1 × 512 × 256)", |
| "shortDescription" : "", |
| "shape" : "[44, 1, 512, 256]", |
| "name" : "model_model_kv_cache_local", |
| "type" : "State" |
| }, |
| { |
| "dataType" : "Float16", |
| "isOptional" : "0", |
| "formattedType" : "State (Float16 8 × 1 × 4096 × 256)", |
| "shortDescription" : "", |
| "shape" : "[8, 1, 4096, 256]", |
| "name" : "model_model_kv_cache_global", |
| "type" : "State" |
| } |
| ], |
| "computePrecision" : "Mixed (Float16, Int16, Int32, UInt16)", |
| "mlProgramOperationTypeHistogram" : { |
| "Ios18.expandDims" : 52, |
| "Ios18.softmax" : 26, |
| "Ios18.mul" : 524, |
| "Ios18.matmul" : 52, |
| "Identity" : 1, |
| "Ios18.greaterEqual" : 2, |
| "Select" : 2, |
| "Ios18.readState" : 54, |
| "Tile" : 52, |
| "Ios18.gather" : 4, |
| "Ios18.add" : 135, |
| "Ios18.layerNorm" : 157, |
| "Ios18.sliceUpdate" : 52, |
| "Ios18.writeState" : 52, |
| "Ios18.reshape" : 109, |
| "Ios18.constexprLutToDense" : 182, |
| "Ios18.conv" : 182, |
| "Ios18.concat" : 297, |
| "Ios18.transpose" : 156, |
| "Ios18.cast" : 5, |
| "Ios18.gelu" : 26, |
| "Ios18.sliceByIndex" : 322, |
| "Ios18.squeeze" : 26 |
| }, |
| "shortDescription" : "Anemll Model: Multifunction FFN+Prefill", |
| "generatedClassName" : "gemma3_FFN_PF_lut6_chunk_01of01", |
| "author" : "Converted with Anemll v0.3.5", |
| "modelType" : { |
| "name" : "MLModelType_mlProgram" |
| } |
| } |
| ] |
