Remove old lut6 models and .mlpackage files

Cleanup to reduce download size and prevent memory issues:
- Removed lut6 .mlmodelc files (replaced by lut8)
- Removed all .mlpackage files (only .mlmodelc needed for inference)
- Removed meta_progress.yaml (not needed)

llama_FFN_PF_lut6_chunk_01of01.mlmodelc/analytics/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e53b9306ddaf9d32f54326b70d13396584a1cd78c5a4bcf99b4b3cdc4011e2a7
-size 243

llama_FFN_PF_lut6_chunk_01of01.mlmodelc/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9421991cfae970be73591364d1b1d6b7b41cdd5f508b597bee227cf92c8dd386
-size 981

llama_FFN_PF_lut6_chunk_01of01.mlmodelc/metadata.json

@@ -1,333 +0,0 @@
-[
-  {
-    "metadataOutputVersion" : "3.0",
-    "userDefinedMetadata" : {
-      "com.anemll.chunk_no" : "1",
-      "com.github.apple.coremltools.source" : "torch==2.5.0",
-      "com.anemll.context_length" : "2048",
-      "com.github.apple.coremltools.version" : "9.0",
-      "com.github.apple.coremltools.source_dialect" : "TorchScript",
-      "com.anemll.num_chunks" : "1",
-      "com.anemll.info" : "Converted with Anemll v0.1.1",
-      "com.anemll.batch_size" : "64",
-      "com.anemll.lut_bits" : "6"
-    },
-    "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 × 2048)",
-        "shortDescription" : "",
-        "shape" : "[1, 1, 2048]",
-        "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 × 2048)",
-        "shortDescription" : "",
-        "shape" : "[1, 1, 1, 2048]",
-        "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 × 2048)",
-        "shortDescription" : "",
-        "shape" : "[1, 1, 2048]",
-        "name" : "output_hidden_states",
-        "type" : "MultiArray"
-      }
-    ],
-    "modelParameters" : [
-
-    ],
-    "storagePrecision" : "Mixed (Float16, Palettized (14 bits), Palettized (16 bits), UInt6)",
-    "method" : "predict",
-    "functions" : [
-      {
-        "inputSchema" : [
-          {
-            "hasShapeFlexibility" : "0",
-            "isOptional" : "0",
-            "dataType" : "Float16",
-            "formattedType" : "MultiArray (Float16 1 × 1 × 2048)",
-            "shortDescription" : "",
-            "shape" : "[1, 1, 2048]",
-            "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 × 2048)",
-            "shortDescription" : "",
-            "shape" : "[1, 1, 1, 2048]",
-            "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 (14 bits), Palettized (16 bits), UInt6)",
-        "stateSchema" : [
-          {
-            "dataType" : "Float16",
-            "isOptional" : "0",
-            "formattedType" : "State (Float16 48 × 16 × 2048 × 128)",
-            "shortDescription" : "",
-            "shape" : "[48, 16, 2048, 128]",
-            "name" : "model_model_kv_cache_0",
-            "type" : "State"
-          }
-        ],
-        "outputSchema" : [
-          {
-            "hasShapeFlexibility" : "0",
-            "isOptional" : "0",
-            "dataType" : "Float16",
-            "formattedType" : "MultiArray (Float16 1 × 1 × 2048)",
-            "shortDescription" : "",
-            "shape" : "[1, 1, 2048]",
-            "name" : "output_hidden_states",
-            "type" : "MultiArray"
-          }
-        ],
-        "name" : "infer",
-        "mlProgramOperationTypeHistogram" : {
-          "Ios18.expandDims" : 96,
-          "Ios18.mul" : 338,
-          "Ios18.matmul" : 48,
-          "Identity" : 1,
-          "Ios18.exp" : 24,
-          "Ios18.realDiv" : 24,
-          "Ios18.greaterEqual" : 2,
-          "Select" : 2,
-          "Ios18.readState" : 49,
-          "Ios16.reduceMax" : 24,
-          "Ios18.gather" : 2,
-          "Ios18.add" : 123,
-          "Ios18.layerNorm" : 49,
-          "Ios18.sliceUpdate" : 48,
-          "Ios18.writeState" : 48,
-          "Ios18.reshape" : 146,
-          "Ios16.reduceSum" : 24,
-          "Ios18.constexprLutToDense" : 168,
-          "Ios18.conv" : 144,
-          "Ios18.concat" : 193,
-          "Ios18.transpose" : 96,
-          "Ios18.sub" : 72,
-          "Ios18.cast" : 5,
-          "Ios18.linear" : 24,
-          "Ios18.silu" : 24,
-          "Ios18.sliceByIndex" : 195,
-          "Ios18.squeeze" : 72
-        }
-      },
-      {
-        "inputSchema" : [
-          {
-            "hasShapeFlexibility" : "0",
-            "isOptional" : "0",
-            "dataType" : "Float16",
-            "formattedType" : "MultiArray (Float16 1 × 64 × 2048)",
-            "shortDescription" : "",
-            "shape" : "[1, 64, 2048]",
-            "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 × 2048)",
-            "shortDescription" : "",
-            "shape" : "[1, 1, 64, 2048]",
-            "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 (14 bits), Palettized (16 bits), UInt6)",
-        "stateSchema" : [
-          {
-            "dataType" : "Float16",
-            "isOptional" : "0",
-            "formattedType" : "State (Float16 48 × 16 × 2048 × 128)",
-            "shortDescription" : "",
-            "shape" : "[48, 16, 2048, 128]",
-            "name" : "model_model_kv_cache_0",
-            "type" : "State"
-          }
-        ],
-        "outputSchema" : [
-          {
-            "hasShapeFlexibility" : "0",
-            "isOptional" : "0",
-            "dataType" : "Float16",
-            "formattedType" : "MultiArray (Float16 1 × 1 × 2048)",
-            "shortDescription" : "",
-            "shape" : "[1, 1, 2048]",
-            "name" : "output_hidden_states",
-            "type" : "MultiArray"
-          }
-        ],
-        "name" : "prefill",
-        "mlProgramOperationTypeHistogram" : {
-          "Ios18.expandDims" : 95,
-          "Ios18.mul" : 333,
-          "Ios18.matmul" : 48,
-          "Ios18.exp" : 24,
-          "Ios18.realDiv" : 24,
-          "Ios18.greaterEqual" : 2,
-          "Select" : 2,
-          "Ios18.readState" : 49,
-          "Ios16.reduceMax" : 24,
-          "Ios18.gather" : 2,
-          "Ios18.add" : 122,
-          "Ios18.layerNorm" : 47,
-          "Ios18.sliceUpdate" : 48,
-          "Ios18.writeState" : 48,
-          "Ios18.reshape" : 194,
-          "Ios16.reduceSum" : 24,
-          "Ios18.constexprLutToDense" : 165,
-          "Ios18.conv" : 141,
-          "Ios18.concat" : 191,
-          "Ios18.transpose" : 168,
-          "Ios18.sub" : 72,
-          "Ios18.cast" : 5,
-          "Ios18.linear" : 24,
-          "Ios18.silu" : 23,
-          "Ios18.sliceByIndex" : 194,
-          "Ios18.squeeze" : 71
-        }
-      }
-    ],
-    "version" : "0.1.1",
-    "isUpdatable" : "0",
-    "defaultFunctionName" : "infer",
-    "specificationVersion" : 9,
-    "stateSchema" : [
-      {
-        "dataType" : "Float16",
-        "isOptional" : "0",
-        "formattedType" : "State (Float16 48 × 16 × 2048 × 128)",
-        "shortDescription" : "",
-        "shape" : "[48, 16, 2048, 128]",
-        "name" : "model_model_kv_cache_0",
-        "type" : "State"
-      }
-    ],
-    "computePrecision" : "Mixed (Float16, Int16, Int32, UInt16)",
-    "mlProgramOperationTypeHistogram" : {
-      "Ios18.expandDims" : 96,
-      "Ios18.mul" : 338,
-      "Ios18.matmul" : 48,
-      "Identity" : 1,
-      "Ios18.exp" : 24,
-      "Ios18.realDiv" : 24,
-      "Ios18.greaterEqual" : 2,
-      "Select" : 2,
-      "Ios18.readState" : 49,
-      "Ios16.reduceMax" : 24,
-      "Ios18.gather" : 2,
-      "Ios18.add" : 123,
-      "Ios18.layerNorm" : 49,
-      "Ios18.sliceUpdate" : 48,
-      "Ios18.writeState" : 48,
-      "Ios18.reshape" : 146,
-      "Ios16.reduceSum" : 24,
-      "Ios18.constexprLutToDense" : 168,
-      "Ios18.conv" : 144,
-      "Ios18.concat" : 193,
-      "Ios18.transpose" : 96,
-      "Ios18.sub" : 72,
-      "Ios18.cast" : 5,
-      "Ios18.linear" : 24,
-      "Ios18.silu" : 24,
-      "Ios18.sliceByIndex" : 195,
-      "Ios18.squeeze" : 72
-    },
-    "shortDescription" : "Anemll Model: Multifunction FFN+Prefill",
-    "generatedClassName" : "llama_FFN_PF_lut6_chunk_01of01",
-    "author" : "Converted with Anemll v0.1.1",
-    "modelType" : {
-      "name" : "MLModelType_mlProgram"
-    }
-  }
-]

llama_FFN_PF_lut6_chunk_01of01.mlmodelc/weights/weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b0659bdab44ee574404cb208e209af0f6c56eabd9256114562844c1964c23355
-size 921174336

llama_FFN_PF_lut6_chunk_01of01.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:abc54c5b07b17c136e4ab1ceea4abd524f7e1fc6e4b705648911a6302b0f32e6
-size 1614653

llama_FFN_PF_lut6_chunk_01of01.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b0659bdab44ee574404cb208e209af0f6c56eabd9256114562844c1964c23355
-size 921174336

llama_FFN_PF_lut6_chunk_01of01.mlpackage/Manifest.json

@@ -1,18 +0,0 @@
-{
-    "fileFormatVersion": "1.0.0",
-    "itemInfoEntries": {
-        "364C6207-AD1B-4B33-A195-BF5B841ABF74": {
-            "author": "com.apple.CoreML",
-            "description": "CoreML Model Weights",
-            "name": "weights",
-            "path": "com.apple.CoreML/weights"
-        },
-        "B22A275C-8BF9-4736-B0C1-DA2C81FDEF1D": {
-            "author": "com.apple.CoreML",
-            "description": "CoreML Model Specification",
-            "name": "model.mlmodel",
-            "path": "com.apple.CoreML/model.mlmodel"
-        }
-    },
-    "rootModelIdentifier": "B22A275C-8BF9-4736-B0C1-DA2C81FDEF1D"
-}

llama_FFN_lut6_chunk_01of01.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:14d4c5586b55eb3202a31ee84dacd16a76a58dbc0a97aee400a75ba19bd9a9c8
-size 799512

llama_FFN_lut6_chunk_01of01.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b0659bdab44ee574404cb208e209af0f6c56eabd9256114562844c1964c23355
-size 921174336

llama_FFN_lut6_chunk_01of01.mlpackage/Manifest.json

@@ -1,18 +0,0 @@
-{
-    "fileFormatVersion": "1.0.0",
-    "itemInfoEntries": {
-        "53F9A283-E453-4A93-ABBB-513F65C9575B": {
-            "author": "com.apple.CoreML",
-            "description": "CoreML Model Weights",
-            "name": "weights",
-            "path": "com.apple.CoreML/weights"
-        },
-        "DDDD6E01-E6E6-411A-83B9-93FBB2D79385": {
-            "author": "com.apple.CoreML",
-            "description": "CoreML Model Specification",
-            "name": "model.mlmodel",
-            "path": "com.apple.CoreML/model.mlmodel"
-        }
-    },
-    "rootModelIdentifier": "DDDD6E01-E6E6-411A-83B9-93FBB2D79385"
-}

llama_embeddings.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e9d75ab28c2cde20f1ad2517130b3d465c2bcad497502fd9922ee9f474096ede
-size 3061

llama_embeddings.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:852a384d0c577ec63eb8faf2f7d7afa24aaca03b1d3e373fb5bb46fc07af283b
-size 132120704

llama_embeddings.mlpackage/Manifest.json

@@ -1,18 +0,0 @@
-{
-    "fileFormatVersion": "1.0.0",
-    "itemInfoEntries": {
-        "85625E63-BF8B-467B-957B-DF5327D861BA": {
-            "author": "com.apple.CoreML",
-            "description": "CoreML Model Weights",
-            "name": "weights",
-            "path": "com.apple.CoreML/weights"
-        },
-        "ED954E18-4E2C-435F-98E4-D9B190F21DF3": {
-            "author": "com.apple.CoreML",
-            "description": "CoreML Model Specification",
-            "name": "model.mlmodel",
-            "path": "com.apple.CoreML/model.mlmodel"
-        }
-    },
-    "rootModelIdentifier": "ED954E18-4E2C-435F-98E4-D9B190F21DF3"
-}

llama_lm_head_lut6.mlmodelc/analytics/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3c882753e4853952ee503752cc3509b7343777c48e1fa6189b67a093ada772c7
-size 243

llama_lm_head_lut6.mlmodelc/coremldata.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4a088381332bc8837634b408eb51f8acc6c63381326aa92211a406ee56c1ba97
-size 859

llama_lm_head_lut6.mlmodelc/metadata.json

@@ -1,143 +0,0 @@
-[
-  {
-    "shortDescription" : "Anemll Model (LM Head) converted to CoreML",
-    "metadataOutputVersion" : "3.0",
-    "outputSchema" : [
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 1 × 4032)",
-        "shortDescription" : "",
-        "shape" : "[1, 1, 4032]",
-        "name" : "logits1",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 1 × 4032)",
-        "shortDescription" : "",
-        "shape" : "[1, 1, 4032]",
-        "name" : "logits2",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 1 × 4032)",
-        "shortDescription" : "",
-        "shape" : "[1, 1, 4032]",
-        "name" : "logits3",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 1 × 4032)",
-        "shortDescription" : "",
-        "shape" : "[1, 1, 4032]",
-        "name" : "logits4",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 1 × 4032)",
-        "shortDescription" : "",
-        "shape" : "[1, 1, 4032]",
-        "name" : "logits5",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 1 × 4032)",
-        "shortDescription" : "",
-        "shape" : "[1, 1, 4032]",
-        "name" : "logits6",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 1 × 4032)",
-        "shortDescription" : "",
-        "shape" : "[1, 1, 4032]",
-        "name" : "logits7",
-        "type" : "MultiArray"
-      },
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 1 × 4032)",
-        "shortDescription" : "",
-        "shape" : "[1, 1, 4032]",
-        "name" : "logits8",
-        "type" : "MultiArray"
-      }
-    ],
-    "version" : "0.1.1",
-    "modelParameters" : [
-
-    ],
-    "author" : "Converted with Anemll v0.1.1",
-    "specificationVersion" : 9,
-    "storagePrecision" : "Mixed (Float16, Palettized (15 bits), UInt6)",
-    "mlProgramOperationTypeHistogram" : {
-      "Ios18.transpose" : 9,
-      "Ios18.constexprLutToDense" : 8,
-      "Ios18.expandDims" : 1,
-      "Ios18.conv" : 8,
-      "Ios18.squeeze" : 8
-    },
-    "computePrecision" : "Mixed (Float16, Int32)",
-    "stateSchema" : [
-
-    ],
-    "isUpdatable" : "0",
-    "availability" : {
-      "macOS" : "15.0",
-      "tvOS" : "18.0",
-      "visionOS" : "2.0",
-      "watchOS" : "11.0",
-      "iOS" : "18.0",
-      "macCatalyst" : "18.0"
-    },
-    "modelType" : {
-      "name" : "MLModelType_mlProgram"
-    },
-    "inputSchema" : [
-      {
-        "hasShapeFlexibility" : "0",
-        "isOptional" : "0",
-        "dataType" : "Float16",
-        "formattedType" : "MultiArray (Float16 1 × 1 × 2048)",
-        "shortDescription" : "",
-        "shape" : "[1, 1, 2048]",
-        "name" : "hidden_states",
-        "type" : "MultiArray"
-      }
-    ],
-    "userDefinedMetadata" : {
-      "com.github.apple.coremltools.version" : "9.0",
-      "com.github.apple.coremltools.source_dialect" : "TorchScript",
-      "com.github.apple.coremltools.conversion_date" : "2026-03-17",
-      "com.anemll.context_length" : "2048",
-      "com.anemll.lm_head_chunk_sizes" : "4032,4032,4032,4032,4032,4032,4032,4032",
-      "com.github.apple.coremltools.source" : "torch==2.5.0",
-      "com.anemll.vocab_size" : "32256",
-      "com.anemll.info" : "Converted with Anemll v0.1.1",
-      "com.anemll.lut_bits" : "6"
-    },
-    "generatedClassName" : "llama_lm_head_lut6",
-    "method" : "predict"
-  }
-]

llama_lm_head_lut6.mlmodelc/model.mil

@@ -1,98 +0,0 @@
-program(1.3)
-[buildInfo = dict<string, string>({{"coremlc-component-MIL", "3510.2.1"}, {"coremlc-version", "3500.32.1"}})]
-{
-    func main<ios18>(tensor<fp16, [1, 1, 2048]> hidden_states) {
-            tensor<int32, [3]> var_5 = const()[name = string("op_5"), val = tensor<int32, [3]>([0, 2, 1])];
-            tensor<int32, [1]> input_axes_0 = const()[name = string("input_axes_0"), val = tensor<int32, [1]>([2])];
-            tensor<fp16, [1, 2048, 1]> var_6_cast_fp16 = transpose(perm = var_5, x = hidden_states)[name = string("transpose_8")];
-            tensor<fp16, [1, 2048, 1, 1]> input_cast_fp16 = expand_dims(axes = input_axes_0, x = var_6_cast_fp16)[name = string("input_cast_fp16")];
-            string var_29_pad_type_0 = const()[name = string("op_29_pad_type_0"), val = string("valid")];
-            tensor<int32, [2]> var_29_strides_0 = const()[name = string("op_29_strides_0"), val = tensor<int32, [2]>([1, 1])];
-            tensor<int32, [4]> var_29_pad_0 = const()[name = string("op_29_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
-            tensor<int32, [2]> var_29_dilations_0 = const()[name = string("op_29_dilations_0"), val = tensor<int32, [2]>([1, 1])];
-            int32 var_29_groups_0 = const()[name = string("op_29_groups_0"), val = int32(1)];
-            tensor<fp16, [4032, 2048, 1, 1]> op_9_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [4032, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(64))), lut = tensor<fp16, [504, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(6193280))))[name = string("op_9_promoted_to_fp16_palettized")];
-            tensor<fp16, [1, 4032, 1, 1]> var_29_cast_fp16 = conv(dilations = var_29_dilations_0, groups = var_29_groups_0, pad = var_29_pad_0, pad_type = var_29_pad_type_0, strides = var_29_strides_0, weight = op_9_promoted_to_fp16_palettized, x = input_cast_fp16)[name = string("op_29_cast_fp16")];
-            tensor<int32, [1]> var_31_axes_0 = const()[name = string("op_31_axes_0"), val = tensor<int32, [1]>([2])];
-            tensor<fp16, [1, 4032, 1]> var_31_cast_fp16 = squeeze(axes = var_31_axes_0, x = var_29_cast_fp16)[name = string("op_31_cast_fp16")];
-            tensor<int32, [3]> var_34_perm_0 = const()[name = string("op_34_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
-            string var_55_pad_type_0 = const()[name = string("op_55_pad_type_0"), val = string("valid")];
-            tensor<int32, [2]> var_55_strides_0 = const()[name = string("op_55_strides_0"), val = tensor<int32, [2]>([1, 1])];
-            tensor<int32, [4]> var_55_pad_0 = const()[name = string("op_55_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
-            tensor<int32, [2]> var_55_dilations_0 = const()[name = string("op_55_dilations_0"), val = tensor<int32, [2]>([1, 1])];
-            int32 var_55_groups_0 = const()[name = string("op_55_groups_0"), val = int32(1)];
-            tensor<fp16, [4032, 2048, 1, 1]> op_35_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [4032, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(6257856))), lut = tensor<fp16, [504, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(12451072))))[name = string("op_35_promoted_to_fp16_palettized")];
-            tensor<fp16, [1, 4032, 1, 1]> var_55_cast_fp16 = conv(dilations = var_55_dilations_0, groups = var_55_groups_0, pad = var_55_pad_0, pad_type = var_55_pad_type_0, strides = var_55_strides_0, weight = op_35_promoted_to_fp16_palettized, x = input_cast_fp16)[name = string("op_55_cast_fp16")];
-            tensor<int32, [1]> var_57_axes_0 = const()[name = string("op_57_axes_0"), val = tensor<int32, [1]>([2])];
-            tensor<fp16, [1, 4032, 1]> var_57_cast_fp16 = squeeze(axes = var_57_axes_0, x = var_55_cast_fp16)[name = string("op_57_cast_fp16")];
-            tensor<int32, [3]> var_60_perm_0 = const()[name = string("op_60_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
-            string var_81_pad_type_0 = const()[name = string("op_81_pad_type_0"), val = string("valid")];
-            tensor<int32, [2]> var_81_strides_0 = const()[name = string("op_81_strides_0"), val = tensor<int32, [2]>([1, 1])];
-            tensor<int32, [4]> var_81_pad_0 = const()[name = string("op_81_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
-            tensor<int32, [2]> var_81_dilations_0 = const()[name = string("op_81_dilations_0"), val = tensor<int32, [2]>([1, 1])];
-            int32 var_81_groups_0 = const()[name = string("op_81_groups_0"), val = int32(1)];
-            tensor<fp16, [4032, 2048, 1, 1]> op_61_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [4032, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(12515648))), lut = tensor<fp16, [504, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(18708864))))[name = string("op_61_promoted_to_fp16_palettized")];
-            tensor<fp16, [1, 4032, 1, 1]> var_81_cast_fp16 = conv(dilations = var_81_dilations_0, groups = var_81_groups_0, pad = var_81_pad_0, pad_type = var_81_pad_type_0, strides = var_81_strides_0, weight = op_61_promoted_to_fp16_palettized, x = input_cast_fp16)[name = string("op_81_cast_fp16")];
-            tensor<int32, [1]> var_83_axes_0 = const()[name = string("op_83_axes_0"), val = tensor<int32, [1]>([2])];
-            tensor<fp16, [1, 4032, 1]> var_83_cast_fp16 = squeeze(axes = var_83_axes_0, x = var_81_cast_fp16)[name = string("op_83_cast_fp16")];
-            tensor<int32, [3]> var_86_perm_0 = const()[name = string("op_86_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
-            string var_107_pad_type_0 = const()[name = string("op_107_pad_type_0"), val = string("valid")];
-            tensor<int32, [2]> var_107_strides_0 = const()[name = string("op_107_strides_0"), val = tensor<int32, [2]>([1, 1])];
-            tensor<int32, [4]> var_107_pad_0 = const()[name = string("op_107_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
-            tensor<int32, [2]> var_107_dilations_0 = const()[name = string("op_107_dilations_0"), val = tensor<int32, [2]>([1, 1])];
-            int32 var_107_groups_0 = const()[name = string("op_107_groups_0"), val = int32(1)];
-            tensor<fp16, [4032, 2048, 1, 1]> op_87_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [4032, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(18773440))), lut = tensor<fp16, [504, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(24966656))))[name = string("op_87_promoted_to_fp16_palettized")];
-            tensor<fp16, [1, 4032, 1, 1]> var_107_cast_fp16 = conv(dilations = var_107_dilations_0, groups = var_107_groups_0, pad = var_107_pad_0, pad_type = var_107_pad_type_0, strides = var_107_strides_0, weight = op_87_promoted_to_fp16_palettized, x = input_cast_fp16)[name = string("op_107_cast_fp16")];
-            tensor<int32, [1]> var_109_axes_0 = const()[name = string("op_109_axes_0"), val = tensor<int32, [1]>([2])];
-            tensor<fp16, [1, 4032, 1]> var_109_cast_fp16 = squeeze(axes = var_109_axes_0, x = var_107_cast_fp16)[name = string("op_109_cast_fp16")];
-            tensor<int32, [3]> var_112_perm_0 = const()[name = string("op_112_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
-            string var_133_pad_type_0 = const()[name = string("op_133_pad_type_0"), val = string("valid")];
-            tensor<int32, [2]> var_133_strides_0 = const()[name = string("op_133_strides_0"), val = tensor<int32, [2]>([1, 1])];
-            tensor<int32, [4]> var_133_pad_0 = const()[name = string("op_133_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
-            tensor<int32, [2]> var_133_dilations_0 = const()[name = string("op_133_dilations_0"), val = tensor<int32, [2]>([1, 1])];
-            int32 var_133_groups_0 = const()[name = string("op_133_groups_0"), val = int32(1)];
-            tensor<fp16, [4032, 2048, 1, 1]> op_113_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [4032, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(25031232))), lut = tensor<fp16, [504, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(31224448))))[name = string("op_113_promoted_to_fp16_palettized")];
-            tensor<fp16, [1, 4032, 1, 1]> var_133_cast_fp16 = conv(dilations = var_133_dilations_0, groups = var_133_groups_0, pad = var_133_pad_0, pad_type = var_133_pad_type_0, strides = var_133_strides_0, weight = op_113_promoted_to_fp16_palettized, x = input_cast_fp16)[name = string("op_133_cast_fp16")];
-            tensor<int32, [1]> var_135_axes_0 = const()[name = string("op_135_axes_0"), val = tensor<int32, [1]>([2])];
-            tensor<fp16, [1, 4032, 1]> var_135_cast_fp16 = squeeze(axes = var_135_axes_0, x = var_133_cast_fp16)[name = string("op_135_cast_fp16")];
-            tensor<int32, [3]> var_138_perm_0 = const()[name = string("op_138_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
-            string var_159_pad_type_0 = const()[name = string("op_159_pad_type_0"), val = string("valid")];
-            tensor<int32, [2]> var_159_strides_0 = const()[name = string("op_159_strides_0"), val = tensor<int32, [2]>([1, 1])];
-            tensor<int32, [4]> var_159_pad_0 = const()[name = string("op_159_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
-            tensor<int32, [2]> var_159_dilations_0 = const()[name = string("op_159_dilations_0"), val = tensor<int32, [2]>([1, 1])];
-            int32 var_159_groups_0 = const()[name = string("op_159_groups_0"), val = int32(1)];
-            tensor<fp16, [4032, 2048, 1, 1]> op_139_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [4032, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(31289024))), lut = tensor<fp16, [504, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(37482240))))[name = string("op_139_promoted_to_fp16_palettized")];
-            tensor<fp16, [1, 4032, 1, 1]> var_159_cast_fp16 = conv(dilations = var_159_dilations_0, groups = var_159_groups_0, pad = var_159_pad_0, pad_type = var_159_pad_type_0, strides = var_159_strides_0, weight = op_139_promoted_to_fp16_palettized, x = input_cast_fp16)[name = string("op_159_cast_fp16")];
-            tensor<int32, [1]> var_161_axes_0 = const()[name = string("op_161_axes_0"), val = tensor<int32, [1]>([2])];
-            tensor<fp16, [1, 4032, 1]> var_161_cast_fp16 = squeeze(axes = var_161_axes_0, x = var_159_cast_fp16)[name = string("op_161_cast_fp16")];
-            tensor<int32, [3]> var_164_perm_0 = const()[name = string("op_164_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
-            string var_185_pad_type_0 = const()[name = string("op_185_pad_type_0"), val = string("valid")];
-            tensor<int32, [2]> var_185_strides_0 = const()[name = string("op_185_strides_0"), val = tensor<int32, [2]>([1, 1])];
-            tensor<int32, [4]> var_185_pad_0 = const()[name = string("op_185_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
-            tensor<int32, [2]> var_185_dilations_0 = const()[name = string("op_185_dilations_0"), val = tensor<int32, [2]>([1, 1])];
-            int32 var_185_groups_0 = const()[name = string("op_185_groups_0"), val = int32(1)];
-            tensor<fp16, [4032, 2048, 1, 1]> op_165_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [4032, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(37546816))), lut = tensor<fp16, [504, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(43740032))))[name = string("op_165_promoted_to_fp16_palettized")];
-            tensor<fp16, [1, 4032, 1, 1]> var_185_cast_fp16 = conv(dilations = var_185_dilations_0, groups = var_185_groups_0, pad = var_185_pad_0, pad_type = var_185_pad_type_0, strides = var_185_strides_0, weight = op_165_promoted_to_fp16_palettized, x = input_cast_fp16)[name = string("op_185_cast_fp16")];
-            tensor<int32, [1]> var_187_axes_0 = const()[name = string("op_187_axes_0"), val = tensor<int32, [1]>([2])];
-            tensor<fp16, [1, 4032, 1]> var_187_cast_fp16 = squeeze(axes = var_187_axes_0, x = var_185_cast_fp16)[name = string("op_187_cast_fp16")];
-            tensor<int32, [3]> var_190_perm_0 = const()[name = string("op_190_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
-            string var_211_pad_type_0 = const()[name = string("op_211_pad_type_0"), val = string("valid")];
-            tensor<int32, [2]> var_211_strides_0 = const()[name = string("op_211_strides_0"), val = tensor<int32, [2]>([1, 1])];
-            tensor<int32, [4]> var_211_pad_0 = const()[name = string("op_211_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
-            tensor<int32, [2]> var_211_dilations_0 = const()[name = string("op_211_dilations_0"), val = tensor<int32, [2]>([1, 1])];
-            int32 var_211_groups_0 = const()[name = string("op_211_groups_0"), val = int32(1)];
-            tensor<fp16, [4032, 2048, 1, 1]> op_191_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [4032, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(43804608))), lut = tensor<fp16, [504, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(49997824))))[name = string("op_191_promoted_to_fp16_palettized")];
-            tensor<fp16, [1, 4032, 1, 1]> var_211_cast_fp16 = conv(dilations = var_211_dilations_0, groups = var_211_groups_0, pad = var_211_pad_0, pad_type = var_211_pad_type_0, strides = var_211_strides_0, weight = op_191_promoted_to_fp16_palettized, x = input_cast_fp16)[name = string("op_211_cast_fp16")];
-            tensor<int32, [1]> var_213_axes_0 = const()[name = string("op_213_axes_0"), val = tensor<int32, [1]>([2])];
-            tensor<fp16, [1, 4032, 1]> var_213_cast_fp16 = squeeze(axes = var_213_axes_0, x = var_211_cast_fp16)[name = string("op_213_cast_fp16")];
-            tensor<int32, [3]> var_216_perm_0 = const()[name = string("op_216_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
-            tensor<fp16, [1, 1, 4032]> logits1 = transpose(perm = var_34_perm_0, x = var_31_cast_fp16)[name = string("transpose_0")];
-            tensor<fp16, [1, 1, 4032]> logits2 = transpose(perm = var_60_perm_0, x = var_57_cast_fp16)[name = string("transpose_1")];
-            tensor<fp16, [1, 1, 4032]> logits3 = transpose(perm = var_86_perm_0, x = var_83_cast_fp16)[name = string("transpose_2")];
-            tensor<fp16, [1, 1, 4032]> logits4 = transpose(perm = var_112_perm_0, x = var_109_cast_fp16)[name = string("transpose_3")];
-            tensor<fp16, [1, 1, 4032]> logits5 = transpose(perm = var_138_perm_0, x = var_135_cast_fp16)[name = string("transpose_4")];
-            tensor<fp16, [1, 1, 4032]> logits6 = transpose(perm = var_164_perm_0, x = var_161_cast_fp16)[name = string("transpose_5")];
-            tensor<fp16, [1, 1, 4032]> logits7 = transpose(perm = var_190_perm_0, x = var_187_cast_fp16)[name = string("transpose_6")];
-            tensor<fp16, [1, 1, 4032]> logits8 = transpose(perm = var_216_perm_0, x = var_213_cast_fp16)[name = string("transpose_7")];
-        } -> (logits1, logits2, logits3, logits4, logits5, logits6, logits7, logits8);
-}

llama_lm_head_lut6.mlmodelc/weights/weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b8194981a11603b43da42a4d396dc17c54f1c5c637b990c78b38b9bf542b9acf
-size 50062400

llama_lm_head_lut6.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b666cbadf27c962fab9d7e421586a134120b334107382eac2f20a88cb474813b
-size 15426

llama_lm_head_lut6.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b8194981a11603b43da42a4d396dc17c54f1c5c637b990c78b38b9bf542b9acf
-size 50062400

llama_lm_head_lut6.mlpackage/Manifest.json

@@ -1,18 +0,0 @@
-{
-    "fileFormatVersion": "1.0.0",
-    "itemInfoEntries": {
-        "14014917-4E03-4FF7-A25C-7D37CE6A58AA": {
-            "author": "com.apple.CoreML",
-            "description": "CoreML Model Weights",
-            "name": "weights",
-            "path": "com.apple.CoreML/weights"
-        },
-        "9357E2E6-C079-4015-B45E-2FD97B2DAE46": {
-            "author": "com.apple.CoreML",
-            "description": "CoreML Model Specification",
-            "name": "model.mlmodel",
-            "path": "com.apple.CoreML/model.mlmodel"
-        }
-    },
-    "rootModelIdentifier": "9357E2E6-C079-4015-B45E-2FD97B2DAE46"
-}

llama_prefill_lut6_chunk_01of01.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:923df0f8f9f36dd15f611332ef4d5ac432f47e801ca5db1ccee3e7a3301ad4e9
-size 815469

llama_prefill_lut6_chunk_01of01.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dfff805ee70f63a0bc87249cfc794d7b652460c385a05877276bed63d5e21f75
-size 895594304

llama_prefill_lut6_chunk_01of01.mlpackage/Manifest.json

@@ -1,18 +0,0 @@
-{
-    "fileFormatVersion": "1.0.0",
-    "itemInfoEntries": {
-        "46B7EB73-4FFD-4A6A-85A6-70EE30E0419E": {
-            "author": "com.apple.CoreML",
-            "description": "CoreML Model Weights",
-            "name": "weights",
-            "path": "com.apple.CoreML/weights"
-        },
-        "8BA31F55-D521-48BF-B65B-543B036F89D5": {
-            "author": "com.apple.CoreML",
-            "description": "CoreML Model Specification",
-            "name": "model.mlmodel",
-            "path": "com.apple.CoreML/model.mlmodel"
-        }
-    },
-    "rootModelIdentifier": "8BA31F55-D521-48BF-B65B-543B036F89D5"
-}

meta_progress.yaml

@@ -1,51 +0,0 @@
-# Conversion in progress - this file is for monitoring only
-# Final meta.yaml will be created at step 7
-conversion:
-  status: in_progress
-  start_time: 2026-03-17T16:30:31Z
-  model_path: /tmp/ios_models/downloads/Prem-1B-SQL
-  output_dir: /tmp/ios_models/Prem-1B-SQL-ctx2048
-  context_length: 2048
-  batch_size: 64
-  num_chunks: 1
-  prefix: llama
-  architecture: llama
-  lut_part1: none
-  lut_part2: 6
-  lut_part3: 6
-  fp16_scale: none
-  argmax: false
-  split_rotate: false
-steps:
-  - name: embeddings
-    part: 1
-    status: pending
-  - name: lm_head
-    part: 3
-    status: pending
-  - name: ffn
-    part: 2
-    status: pending
-  - name: prefill
-    part: 2_prefill
-    status: pending
-  - name: ffn_rotate
-    part: 2_rotate
-    status: pending
-    gemma3_only: true
-  - name: prefill_rotate
-    part: 2_prefill_rotate
-    status: pending
-    gemma3_only: true
-  - name: combine
-    part: 5
-    status: pending
-  - name: compile
-    part: 6
-    status: pending
-  - name: tokenizer
-    part: 7
-    status: pending
-  - name: test
-    part: 8
-    status: pending