Add vision_video.mlmodelc (Gemma 4 video encoder, 64 tokens/frame)

vision_video.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc1238423fab6eb9d256112410618e6a238e91bb268c5826c05db291b4294f59
+size 243

vision_video.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:964fb81d893883036b585f83a962a2db6ce39eaf23c7b418868e6c928c5d0a27
+size 418

vision_video.mlmodelc/metadata.json

@@ -0,0 +1,102 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Float16",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16)",
+        "shortDescription" : "",
+        "shape" : "[]",
+        "name" : "image_features",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 9,
+    "mlProgramOperationTypeHistogram" : {
+      "Ios18.expandDims" : 135,
+      "Ios18.mul" : 423,
+      "Ios18.cos" : 2,
+      "Ios18.softmax" : 16,
+      "Ios18.matmul" : 36,
+      "Ios18.floorDiv" : 2,
+      "Ios16.reduceMean" : 113,
+      "Ios18.logicalNot" : 2,
+      "Ios18.equal" : 2,
+      "Ios18.sin" : 2,
+      "Split" : 96,
+      "Select" : 3,
+      "Ios18.greaterEqual" : 1,
+      "Ios16.reduceMax" : 1,
+      "Ios16.reduceMin" : 2,
+      "Ios18.add" : 229,
+      "Ios16.reduceSum" : 1,
+      "Tile" : 1,
+      "Ios18.reshape" : 64,
+      "Ios18.maximum" : 1,
+      "Ios18.linear" : 114,
+      "Ios18.concat" : 100,
+      "Ios18.transpose" : 67,
+      "OneHot" : 2,
+      "Ios18.sub" : 2,
+      "Ios18.cast" : 16,
+      "Ios18.pow" : 226,
+      "Ios18.clip" : 176,
+      "Ios18.gelu" : 16,
+      "Ios18.gatherNd" : 1,
+      "Ios18.sliceByIndex" : 133,
+      "NonZero" : 1
+    },
+    "computePrecision" : "Mixed (Float16, Int16, Int32)",
+    "isUpdatable" : "0",
+    "stateSchema" : [
+
+    ],
+    "availability" : {
+      "macOS" : "15.0",
+      "tvOS" : "18.0",
+      "visionOS" : "2.0",
+      "watchOS" : "11.0",
+      "iOS" : "18.0",
+      "macCatalyst" : "18.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.conversion_date" : "2026-04-15",
+      "com.github.apple.coremltools.source" : "torch==2.7.0",
+      "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 × 630 × 768)",
+        "shortDescription" : "",
+        "shape" : "[1, 630, 768]",
+        "name" : "pixel_values",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Int32",
+        "formattedType" : "MultiArray (Int32 1 × 630 × 2)",
+        "shortDescription" : "",
+        "shape" : "[1, 630, 2]",
+        "name" : "pixel_position_ids",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "vision_video",
+    "method" : "predict"
+  }
+]

vision_video.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a58aad4747e2c5269fbcae1b80ac3342bada076223052e2f093d344ccce4309
+size 338081024