Upload folder using huggingface_hub

meta.yaml

@@ -14,7 +14,7 @@ model_info:
   parameters:
     context_length: 512
     batch_size: 64
-    lut_embeddings: 6
+    lut_embeddings: None
     lut_ffn: 6
     lut_lmhead: 6
     num_chunks: 1

qwen_embeddings.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:310d49eb41b891c1cfc6a9a7dbe1d62e5a33e9136343e46852bb15d61754e43f
+size 243

qwen_embeddings.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:626e4ce3bf37e13a0b48524ccabe18155e9b7fed0c972dd10d4db61a5d0880c6
+size 527

qwen_embeddings.mlmodelc/metadata.json

@@ -0,0 +1,69 @@
+[
+  {
+    "shortDescription" : "Anemll Model (Embeddings) converted to CoreML",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16)",
+        "shortDescription" : "",
+        "shape" : "[]",
+        "name" : "hidden_states",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "0.3.3",
+    "modelParameters" : [
+
+    ],
+    "author" : "Converted with Anemll v0.3.3",
+    "specificationVersion" : 9,
+    "storagePrecision" : "Mixed (Float16, Palettized (21 bits), UInt6)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios18.constexprLutToDense" : 1,
+      "Ios18.gather" : 1
+    },
+    "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" : [
+      {
+        "shortDescription" : "",
+        "dataType" : "Int32",
+        "hasShapeFlexibility" : "1",
+        "isOptional" : "0",
+        "shapeFlexibility" : "1 × 1 | 1 × 64",
+        "formattedType" : "MultiArray (Int32 1 × 1)",
+        "type" : "MultiArray",
+        "shape" : "[1, 1]",
+        "name" : "input_ids",
+        "enumeratedShapes" : "[[1, 1], [1, 64]]"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.anemll.context_length" : "512",
+      "com.github.apple.coremltools.version" : "8.3.0",
+      "com.anemll.lut_bits" : "6",
+      "com.github.apple.coremltools.source" : "torch==2.5.0",
+      "com.anemll.info" : "Converted with Anemll v0.3.3",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript"
+    },
+    "generatedClassName" : "qwen_embeddings",
+    "method" : "predict"
+  }
+]

qwen_embeddings.mlmodelc/model.mil

@@ -0,0 +1,11 @@
+program(1.3)
+[buildInfo = dict<string, string>({{"coremlc-component-MIL", "3500.11.1"}, {"coremlc-version", "3500.21.1"}})]
+{
+    func main<ios18>(tensor<int32, [1, ?]> input_ids) [FlexibleShapeInformation = tuple<tuple<string, dict<string, tensor<int32, [?]>>>, tuple<string, dict<string, dict<string, tensor<int32, [?]>>>>>((("DefaultShapes", {{"input_ids", [1, 1]}}), ("EnumeratedShapes", {{"79ae981e", {{"input_ids", [1, 1]}}}, {"ed9b58c8", {{"input_ids", [1, 64]}}}})))] {
+            int32 hidden_states_axis_0 = const()[name = string("hidden_states_axis_0"), val = int32(0)];
+            int32 hidden_states_batch_dims_0 = const()[name = string("hidden_states_batch_dims_0"), val = int32(0)];
+            bool hidden_states_validate_indices_0 = const()[name = string("hidden_states_validate_indices_0"), val = bool(false)];
+            tensor<fp16, [151936, 1024]> embed_tokens_weight_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [151936, 1024]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(64))), lut = tensor<fp16, [18992, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(116686976))))[name = string("embed_tokens_weight_to_fp16_palettized")];
+            tensor<fp16, [1, ?, 1024]> hidden_states = gather(axis = hidden_states_axis_0, batch_dims = hidden_states_batch_dims_0, indices = input_ids, validate_indices = hidden_states_validate_indices_0, x = embed_tokens_weight_to_fp16_palettized)[name = string("hidden_states_cast_fp16")];
+        } -> (hidden_states);
+}

qwen_embeddings.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aa93c5a92574caf627576b16b8bb7b7f5bacfdf5a5eb1951916bd64b3456ff3
+size 119118016

qwen_lm_head.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e05343a44f7fc2c4b9afbeeb300d09a6c1186c7be10912da68dfa83b14735c85
+size 243

qwen_lm_head.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097eaf8ad6e5423e442dae8722977a3f5aab61660be17053b7a32c53c95152fd
+size 897

qwen_lm_head.mlmodelc/metadata.json

@@ -0,0 +1,220 @@
+[
+  {
+    "shortDescription" : "Anemll Model (LM Head) converted to CoreML",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits1",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits2",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits3",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits4",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits5",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits6",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits7",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits8",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits9",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits10",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits11",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits12",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits13",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits14",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits15",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits16",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "0.3.3",
+    "modelParameters" : [
+
+    ],
+    "author" : "Converted with Anemll v0.3.3",
+    "specificationVersion" : 9,
+    "storagePrecision" : "Mixed (Float16, Palettized (17 bits), UInt6)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios18.transpose" : 17,
+      "Ios18.constexprLutToDense" : 16,
+      "Ios18.expandDims" : 1,
+      "Ios18.conv" : 16,
+      "Ios18.squeeze" : 16
+    },
+    "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 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1024]",
+        "name" : "hidden_states",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.version" : "8.3.0",
+      "com.anemll.lut_bits" : "6",
+      "com.github.apple.coremltools.source" : "torch==2.5.0",
+      "com.anemll.info" : "Converted with Anemll v0.3.3",
+      "com.anemll.context_length" : "512"
+    },
+    "generatedClassName" : "qwen_lm_head_lut6",
+    "method" : "predict"
+  }
+]

qwen_lm_head.mlmodelc/model.mil

@@ -0,0 +1,186 @@
+program(1.3)
+[buildInfo = dict<string, string>({{"coremlc-component-MIL", "3500.11.1"}, {"coremlc-version", "3500.21.1"}})]
+{
+    func main<ios18>(tensor<fp16, [1, 1, 1024]> 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, 1024, 1]> var_6_cast_fp16 = transpose(perm = var_5, x = hidden_states)[name = string("transpose_16")];
+            tensor<fp16, [1, 1024, 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, [9496, 1024, 1, 1]> op_9_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(64))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(7293056))))[name = string("op_9_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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, 9496, 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, [9496, 1024, 1, 1]> op_35_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(7445056))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(14738048))))[name = string("op_35_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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, 9496, 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, [9496, 1024, 1, 1]> op_61_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(14890048))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(22183040))))[name = string("op_61_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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, 9496, 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, [9496, 1024, 1, 1]> op_87_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(22335040))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(29628032))))[name = string("op_87_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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, 9496, 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, [9496, 1024, 1, 1]> op_113_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(29780032))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(37073024))))[name = string("op_113_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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, 9496, 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, [9496, 1024, 1, 1]> op_139_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(37225024))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(44518016))))[name = string("op_139_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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, 9496, 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, [9496, 1024, 1, 1]> op_165_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(44670016))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(51963008))))[name = string("op_165_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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, 9496, 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, [9496, 1024, 1, 1]> op_191_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(52115008))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(59408000))))[name = string("op_191_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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, 9496, 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])];
+            string var_237_pad_type_0 = const()[name = string("op_237_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_237_strides_0 = const()[name = string("op_237_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_237_pad_0 = const()[name = string("op_237_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_237_dilations_0 = const()[name = string("op_237_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_237_groups_0 = const()[name = string("op_237_groups_0"), val = int32(1)];
+            tensor<fp16, [9496, 1024, 1, 1]> op_217_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(59560000))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(66852992))))[name = string("op_217_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 1, 1]> var_237_cast_fp16 = conv(dilations = var_237_dilations_0, groups = var_237_groups_0, pad = var_237_pad_0, pad_type = var_237_pad_type_0, strides = var_237_strides_0, weight = op_217_promoted_to_fp16_palettized, x = input_cast_fp16)[name = string("op_237_cast_fp16")];
+            tensor<int32, [1]> var_239_axes_0 = const()[name = string("op_239_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 9496, 1]> var_239_cast_fp16 = squeeze(axes = var_239_axes_0, x = var_237_cast_fp16)[name = string("op_239_cast_fp16")];
+            tensor<int32, [3]> var_242_perm_0 = const()[name = string("op_242_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_263_pad_type_0 = const()[name = string("op_263_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_263_strides_0 = const()[name = string("op_263_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_263_pad_0 = const()[name = string("op_263_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_263_dilations_0 = const()[name = string("op_263_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_263_groups_0 = const()[name = string("op_263_groups_0"), val = int32(1)];
+            tensor<fp16, [9496, 1024, 1, 1]> op_243_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(67004992))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(74297984))))[name = string("op_243_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 1, 1]> var_263_cast_fp16 = conv(dilations = var_263_dilations_0, groups = var_263_groups_0, pad = var_263_pad_0, pad_type = var_263_pad_type_0, strides = var_263_strides_0, weight = op_243_promoted_to_fp16_palettized, x = input_cast_fp16)[name = string("op_263_cast_fp16")];
+            tensor<int32, [1]> var_265_axes_0 = const()[name = string("op_265_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 9496, 1]> var_265_cast_fp16 = squeeze(axes = var_265_axes_0, x = var_263_cast_fp16)[name = string("op_265_cast_fp16")];
+            tensor<int32, [3]> var_268_perm_0 = const()[name = string("op_268_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_289_pad_type_0 = const()[name = string("op_289_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_289_strides_0 = const()[name = string("op_289_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_289_pad_0 = const()[name = string("op_289_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_289_dilations_0 = const()[name = string("op_289_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_289_groups_0 = const()[name = string("op_289_groups_0"), val = int32(1)];
+            tensor<fp16, [9496, 1024, 1, 1]> op_269_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(74449984))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(81742976))))[name = string("op_269_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 1, 1]> var_289_cast_fp16 = conv(dilations = var_289_dilations_0, groups = var_289_groups_0, pad = var_289_pad_0, pad_type = var_289_pad_type_0, strides = var_289_strides_0, weight = op_269_promoted_to_fp16_palettized, x = input_cast_fp16)[name = string("op_289_cast_fp16")];
+            tensor<int32, [1]> var_291_axes_0 = const()[name = string("op_291_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 9496, 1]> var_291_cast_fp16 = squeeze(axes = var_291_axes_0, x = var_289_cast_fp16)[name = string("op_291_cast_fp16")];
+            tensor<int32, [3]> var_294_perm_0 = const()[name = string("op_294_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_315_pad_type_0 = const()[name = string("op_315_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_315_strides_0 = const()[name = string("op_315_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_315_pad_0 = const()[name = string("op_315_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_315_dilations_0 = const()[name = string("op_315_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_315_groups_0 = const()[name = string("op_315_groups_0"), val = int32(1)];
+            tensor<fp16, [9496, 1024, 1, 1]> op_295_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(81894976))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(89187968))))[name = string("op_295_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 1, 1]> var_315_cast_fp16 = conv(dilations = var_315_dilations_0, groups = var_315_groups_0, pad = var_315_pad_0, pad_type = var_315_pad_type_0, strides = var_315_strides_0, weight = op_295_promoted_to_fp16_palettized, x = input_cast_fp16)[name = string("op_315_cast_fp16")];
+            tensor<int32, [1]> var_317_axes_0 = const()[name = string("op_317_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 9496, 1]> var_317_cast_fp16 = squeeze(axes = var_317_axes_0, x = var_315_cast_fp16)[name = string("op_317_cast_fp16")];
+            tensor<int32, [3]> var_320_perm_0 = const()[name = string("op_320_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_341_pad_type_0 = const()[name = string("op_341_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_341_strides_0 = const()[name = string("op_341_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_341_pad_0 = const()[name = string("op_341_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_341_dilations_0 = const()[name = string("op_341_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_341_groups_0 = const()[name = string("op_341_groups_0"), val = int32(1)];
+            tensor<fp16, [9496, 1024, 1, 1]> op_321_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(89339968))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(96632960))))[name = string("op_321_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 1, 1]> var_341_cast_fp16 = conv(dilations = var_341_dilations_0, groups = var_341_groups_0, pad = var_341_pad_0, pad_type = var_341_pad_type_0, strides = var_341_strides_0, weight = op_321_promoted_to_fp16_palettized, x = input_cast_fp16)[name = string("op_341_cast_fp16")];
+            tensor<int32, [1]> var_343_axes_0 = const()[name = string("op_343_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 9496, 1]> var_343_cast_fp16 = squeeze(axes = var_343_axes_0, x = var_341_cast_fp16)[name = string("op_343_cast_fp16")];
+            tensor<int32, [3]> var_346_perm_0 = const()[name = string("op_346_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_367_pad_type_0 = const()[name = string("op_367_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_367_strides_0 = const()[name = string("op_367_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_367_pad_0 = const()[name = string("op_367_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_367_dilations_0 = const()[name = string("op_367_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_367_groups_0 = const()[name = string("op_367_groups_0"), val = int32(1)];
+            tensor<fp16, [9496, 1024, 1, 1]> op_347_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(96784960))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(104077952))))[name = string("op_347_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 1, 1]> var_367_cast_fp16 = conv(dilations = var_367_dilations_0, groups = var_367_groups_0, pad = var_367_pad_0, pad_type = var_367_pad_type_0, strides = var_367_strides_0, weight = op_347_promoted_to_fp16_palettized, x = input_cast_fp16)[name = string("op_367_cast_fp16")];
+            tensor<int32, [1]> var_369_axes_0 = const()[name = string("op_369_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 9496, 1]> var_369_cast_fp16 = squeeze(axes = var_369_axes_0, x = var_367_cast_fp16)[name = string("op_369_cast_fp16")];
+            tensor<int32, [3]> var_372_perm_0 = const()[name = string("op_372_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_393_pad_type_0 = const()[name = string("op_393_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_393_strides_0 = const()[name = string("op_393_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_393_pad_0 = const()[name = string("op_393_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_393_dilations_0 = const()[name = string("op_393_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_393_groups_0 = const()[name = string("op_393_groups_0"), val = int32(1)];
+            tensor<fp16, [9496, 1024, 1, 1]> op_373_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(104229952))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(111522944))))[name = string("op_373_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 1, 1]> var_393_cast_fp16 = conv(dilations = var_393_dilations_0, groups = var_393_groups_0, pad = var_393_pad_0, pad_type = var_393_pad_type_0, strides = var_393_strides_0, weight = op_373_promoted_to_fp16_palettized, x = input_cast_fp16)[name = string("op_393_cast_fp16")];
+            tensor<int32, [1]> var_395_axes_0 = const()[name = string("op_395_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 9496, 1]> var_395_cast_fp16 = squeeze(axes = var_395_axes_0, x = var_393_cast_fp16)[name = string("op_395_cast_fp16")];
+            tensor<int32, [3]> var_398_perm_0 = const()[name = string("op_398_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_419_pad_type_0 = const()[name = string("op_419_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_419_strides_0 = const()[name = string("op_419_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_419_pad_0 = const()[name = string("op_419_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_419_dilations_0 = const()[name = string("op_419_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_419_groups_0 = const()[name = string("op_419_groups_0"), val = int32(1)];
+            tensor<fp16, [9496, 1024, 1, 1]> op_399_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(111674944))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(118967936))))[name = string("op_399_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 1, 1]> var_419_cast_fp16 = conv(dilations = var_419_dilations_0, groups = var_419_groups_0, pad = var_419_pad_0, pad_type = var_419_pad_type_0, strides = var_419_strides_0, weight = op_399_promoted_to_fp16_palettized, x = input_cast_fp16)[name = string("op_419_cast_fp16")];
+            tensor<int32, [1]> var_421_axes_0 = const()[name = string("op_421_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 9496, 1]> var_421_cast_fp16 = squeeze(axes = var_421_axes_0, x = var_419_cast_fp16)[name = string("op_421_cast_fp16")];
+            tensor<int32, [3]> var_424_perm_0 = const()[name = string("op_424_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            tensor<fp16, [1, 1, 9496]> logits1 = transpose(perm = var_34_perm_0, x = var_31_cast_fp16)[name = string("transpose_0")];
+            tensor<fp16, [1, 1, 9496]> logits2 = transpose(perm = var_60_perm_0, x = var_57_cast_fp16)[name = string("transpose_1")];
+            tensor<fp16, [1, 1, 9496]> logits3 = transpose(perm = var_86_perm_0, x = var_83_cast_fp16)[name = string("transpose_2")];
+            tensor<fp16, [1, 1, 9496]> logits4 = transpose(perm = var_112_perm_0, x = var_109_cast_fp16)[name = string("transpose_3")];
+            tensor<fp16, [1, 1, 9496]> logits5 = transpose(perm = var_138_perm_0, x = var_135_cast_fp16)[name = string("transpose_4")];
+            tensor<fp16, [1, 1, 9496]> logits6 = transpose(perm = var_164_perm_0, x = var_161_cast_fp16)[name = string("transpose_5")];
+            tensor<fp16, [1, 1, 9496]> logits7 = transpose(perm = var_190_perm_0, x = var_187_cast_fp16)[name = string("transpose_6")];
+            tensor<fp16, [1, 1, 9496]> logits8 = transpose(perm = var_216_perm_0, x = var_213_cast_fp16)[name = string("transpose_7")];
+            tensor<fp16, [1, 1, 9496]> logits9 = transpose(perm = var_242_perm_0, x = var_239_cast_fp16)[name = string("transpose_8")];
+            tensor<fp16, [1, 1, 9496]> logits10 = transpose(perm = var_268_perm_0, x = var_265_cast_fp16)[name = string("transpose_9")];
+            tensor<fp16, [1, 1, 9496]> logits11 = transpose(perm = var_294_perm_0, x = var_291_cast_fp16)[name = string("transpose_10")];
+            tensor<fp16, [1, 1, 9496]> logits12 = transpose(perm = var_320_perm_0, x = var_317_cast_fp16)[name = string("transpose_11")];
+            tensor<fp16, [1, 1, 9496]> logits13 = transpose(perm = var_346_perm_0, x = var_343_cast_fp16)[name = string("transpose_12")];
+            tensor<fp16, [1, 1, 9496]> logits14 = transpose(perm = var_372_perm_0, x = var_369_cast_fp16)[name = string("transpose_13")];
+            tensor<fp16, [1, 1, 9496]> logits15 = transpose(perm = var_398_perm_0, x = var_395_cast_fp16)[name = string("transpose_14")];
+            tensor<fp16, [1, 1, 9496]> logits16 = transpose(perm = var_424_perm_0, x = var_421_cast_fp16)[name = string("transpose_15")];
+        } -> (logits1, logits2, logits3, logits4, logits5, logits6, logits7, logits8, logits9, logits10, logits11, logits12, logits13, logits14, logits15, logits16);
+}

qwen_lm_head.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8707b04445d6c46e5b15b263bb51e7329841877d4517808b26760117d42b22ac
+size 119119936