add model

Llama-3.2-3B-Instruct_chunk1.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0806d9561f1b977f8fb7c990502de9bc2576ac170b096b4b3479ca05c69b5db9
+size 243

Llama-3.2-3B-Instruct_chunk1.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7d9258e6a9d7d75508e04144cce26719dee2fd20b0953014c351af2d53f0f6a
+size 409

Llama-3.2-3B-Instruct_chunk1.mlmodelc/metadata.json

@@ -0,0 +1,105 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Float16",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3072 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[1, 3072, 8, 8]",
+        "name" : "x",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 128 × 64)",
+        "shortDescription" : "",
+        "shape" : "[128, 64]",
+        "name" : "cos",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 128 × 64)",
+        "shortDescription" : "",
+        "shape" : "[128, 64]",
+        "name" : "sin",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 512 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 512, 1, 64]",
+        "name" : "mask",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 7,
+    "mlProgramOperationTypeHistogram" : {
+      "Select" : 2,
+      "Tile" : 2,
+      "Ios16.sub" : 3,
+      "Transpose" : 2,
+      "Ios16.gather" : 3,
+      "ExpandDims" : 3,
+      "Ios16.reshape" : 1,
+      "Ios16.maximum" : 1,
+      "Ios16.less" : 2
+    },
+    "computePrecision" : "Mixed (Float16, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.1.0",
+      "com.github.apple.coremltools.version" : "8.0b1"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Int32",
+        "formattedType" : "MultiArray (Int32 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 64]",
+        "name" : "input_ids",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Int32",
+        "formattedType" : "MultiArray (Int32 1)",
+        "shortDescription" : "",
+        "shape" : "[1]",
+        "name" : "full_sequence_length",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "Llama_3_2_3B_Instruct_2024_11_09_16_14_37_chunk1",
+    "method" : "predict"
+  }
+]

Llama-3.2-3B-Instruct_chunk1.mlmodelc/model.mil

@@ -0,0 +1,50 @@
+program(1.0)
+[buildInfo = dict<tensor<string, []>, tensor<string, []>>({{"coremlc-component-MIL", "3304.5.2"}, {"coremlc-version", "3304.6.2"}, {"coremltools-component-torch", "2.1.0"}, {"coremltools-source-dialect", "TorchScript"}, {"coremltools-version", "8.0b1"}})]
+{
+    func main<ios16>(tensor<int32, [1]> full_sequence_length, tensor<int32, [1, 64]> input_ids) {
+            tensor<int32, [1]> T = const()[name = tensor<string, []>("T"), val = tensor<int32, [1]>([64])];
+            tensor<int32, []> x_1_axis_0 = const()[name = tensor<string, []>("x_1_axis_0"), val = tensor<int32, []>(0)];
+            tensor<int32, []> x_1_batch_dims_0 = const()[name = tensor<string, []>("x_1_batch_dims_0"), val = tensor<int32, []>(0)];
+            tensor<fp16, [128256, 3072]> wte_weight_to_fp16 = const()[name = tensor<string, []>("wte_weight_to_fp16"), val = tensor<fp16, [128256, 3072]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(64)))];
+            tensor<fp16, [1, 64, 3072]> x_1_cast_fp16 = gather(axis = x_1_axis_0, batch_dims = x_1_batch_dims_0, indices = input_ids, x = wte_weight_to_fp16)[name = tensor<string, []>("x_1_cast_fp16")];
+            tensor<int32, [3]> x_perm_0 = const()[name = tensor<string, []>("x_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            tensor<int32, [4]> var_27 = const()[name = tensor<string, []>("op_27"), val = tensor<int32, [4]>([1, 3072, -1, 8])];
+            tensor<fp16, [1, 3072, 64]> x_cast_fp16 = transpose(perm = x_perm_0, x = x_1_cast_fp16)[name = tensor<string, []>("transpose_1")];
+            tensor<fp16, [1, 3072, 8, 8]> x = reshape(shape = var_27, x = x_cast_fp16)[name = tensor<string, []>("op_28_cast_fp16")];
+            tensor<int32, [1]> pos_offset = sub(x = T, y = full_sequence_length)[name = tensor<string, []>("pos_offset")];
+            tensor<int32, [64]> var_36 = const()[name = tensor<string, []>("op_36"), val = tensor<int32, [64]>([0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63])];
+            tensor<int32, [64]> input_pos_1 = sub(x = var_36, y = pos_offset)[name = tensor<string, []>("input_pos_1")];
+            tensor<int32, [64]> var_44 = const()[name = tensor<string, []>("op_44"), val = tensor<int32, [64]>([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])];
+            tensor<int32, [64]> input_pos = maximum(x = input_pos_1, y = var_44)[name = tensor<string, []>("input_pos")];
+            tensor<int32, []> var_55 = const()[name = tensor<string, []>("op_55"), val = tensor<int32, []>(1)];
+            tensor<int32, []> cos_batch_dims_0 = const()[name = tensor<string, []>("cos_batch_dims_0"), val = tensor<int32, []>(0)];
+            tensor<fp16, [128, 512]> var_54_to_fp16 = const()[name = tensor<string, []>("op_54_to_fp16"), val = tensor<fp16, [128, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(788004992)))];
+            tensor<fp16, [128, 64]> cos = gather(axis = var_55, batch_dims = cos_batch_dims_0, indices = input_pos, x = var_54_to_fp16)[name = tensor<string, []>("cos_cast_fp16")];
+            tensor<int32, []> var_66 = const()[name = tensor<string, []>("op_66"), val = tensor<int32, []>(1)];
+            tensor<int32, []> sin_batch_dims_0 = const()[name = tensor<string, []>("sin_batch_dims_0"), val = tensor<int32, []>(0)];
+            tensor<fp16, [128, 512]> var_65_to_fp16 = const()[name = tensor<string, []>("op_65_to_fp16"), val = tensor<fp16, [128, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(788136128)))];
+            tensor<fp16, [128, 64]> sin = gather(axis = var_66, batch_dims = sin_batch_dims_0, indices = input_pos, x = var_65_to_fp16)[name = tensor<string, []>("sin_cast_fp16")];
+            tensor<int32, [64, 1]> var_102 = const()[name = tensor<string, []>("op_102"), val = tensor<int32, [64, 1]>([[0], [1], [2], [3], [4], [5], [6], [7], [8], [9], [10], [11], [12], [13], [14], [15], [16], [17], [18], [19], [20], [21], [22], [23], [24], [25], [26], [27], [28], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47], [48], [49], [50], [51], [52], [53], [54], [55], [56], [57], [58], [59], [60], [61], [62], [63]])];
+            tensor<bool, [64, 1]> var_105 = less(x = var_102, y = pos_offset)[name = tensor<string, []>("op_105")];
+            tensor<int32, [2]> var_105_after_broadcast_reps_0 = const()[name = tensor<string, []>("op_105_after_broadcast_reps_0"), val = tensor<int32, [2]>([1, 512])];
+            tensor<bool, [64, 512]> var_105_after_broadcast = tile(reps = var_105_after_broadcast_reps_0, x = var_105)[name = tensor<string, []>("op_105_after_broadcast")];
+            tensor<fp16, [64, 512]> all_mask_to_fp16 = const()[name = tensor<string, []>("all_mask_to_fp16"), val = tensor<fp16, [64, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(788267264)))];
+            tensor<fp16, [64, 512]> m_1_to_fp16 = const()[name = tensor<string, []>("m_1_to_fp16"), val = tensor<fp16, [64, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(788332864)))];
+            tensor<fp16, [64, 512]> m_3_cast_fp16 = select(a = all_mask_to_fp16, b = m_1_to_fp16, cond = var_105_after_broadcast)[name = tensor<string, []>("m_3_cast_fp16")];
+            tensor<int32, [512]> var_115 = const()[name = tensor<string, []>("op_115"), val = tensor<int32, [512]>([0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 215, 216, 217, 218, 219, 220, 221, 222, 223, 224, 225, 226, 227, 228, 229, 230, 231, 232, 233, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246, 247, 248, 249, 250, 251, 252, 253, 254, 255, 256, 257, 258, 259, 260, 261, 262, 263, 264, 265, 266, 267, 268, 269, 270, 271, 272, 273, 274, 275, 276, 277, 278, 279, 280, 281, 282, 283, 284, 285, 286, 287, 288, 289, 290, 291, 292, 293, 294, 295, 296, 297, 298, 299, 300, 301, 302, 303, 304, 305, 306, 307, 308, 309, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320, 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 333, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354, 355, 356, 357, 358, 359, 360, 361, 362, 363, 364, 365, 366, 367, 368, 369, 370, 371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 382, 383, 384, 385, 386, 387, 388, 389, 390, 391, 392, 393, 394, 395, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, 412, 413, 414, 415, 416, 417, 418, 419, 420, 421, 422, 423, 424, 425, 426, 427, 428, 429, 430, 431, 432, 433, 434, 435, 436, 437, 438, 439, 440, 441, 442, 443, 444, 445, 446, 447, 448, 449, 450, 451, 452, 453, 454, 455, 456, 457, 458, 459, 460, 461, 462, 463, 464, 465, 466, 467, 468, 469, 470, 471, 472, 473, 474, 475, 476, 477, 478, 479, 480, 481, 482, 483, 484, 485, 486, 487, 488, 489, 490, 491, 492, 493, 494, 495, 496, 497, 498, 499, 500, 501, 502, 503, 504, 505, 506, 507, 508, 509, 510, 511])];
+            tensor<int32, []> var_116 = const()[name = tensor<string, []>("op_116"), val = tensor<int32, []>(512)];
+            tensor<int32, [1]> var_118 = sub(x = var_116, y = full_sequence_length)[name = tensor<string, []>("op_118")];
+            tensor<bool, [512]> var_119 = less(x = var_115, y = var_118)[name = tensor<string, []>("op_119")];
+            tensor<int32, [1]> expand_dims_0_axes_0 = const()[name = tensor<string, []>("expand_dims_0_axes_0"), val = tensor<int32, [1]>([0])];
+            tensor<bool, [1, 512]> expand_dims_0 = expand_dims(axes = expand_dims_0_axes_0, x = var_119)[name = tensor<string, []>("expand_dims_0")];
+            tensor<int32, [2]> var_119_after_broadcast_reps_0 = const()[name = tensor<string, []>("op_119_after_broadcast_reps_0"), val = tensor<int32, [2]>([64, 1])];
+            tensor<bool, [64, 512]> var_119_after_broadcast = tile(reps = var_119_after_broadcast_reps_0, x = expand_dims_0)[name = tensor<string, []>("op_119_after_broadcast")];
+            tensor<fp16, [64, 512]> m_cast_fp16 = select(a = all_mask_to_fp16, b = m_3_cast_fp16, cond = var_119_after_broadcast)[name = tensor<string, []>("m_cast_fp16")];
+            tensor<int32, [1]> var_122_axes_0 = const()[name = tensor<string, []>("op_122_axes_0"), val = tensor<int32, [1]>([0])];
+            tensor<fp16, [1, 64, 512]> var_122_cast_fp16 = expand_dims(axes = var_122_axes_0, x = m_cast_fp16)[name = tensor<string, []>("op_122_cast_fp16")];
+            tensor<int32, [1]> mask_axes_0 = const()[name = tensor<string, []>("mask_axes_0"), val = tensor<int32, [1]>([0])];
+            tensor<fp16, [1, 1, 64, 512]> mask_cast_fp16 = expand_dims(axes = mask_axes_0, x = var_122_cast_fp16)[name = tensor<string, []>("mask_cast_fp16")];
+            tensor<int32, [4]> var_129 = const()[name = tensor<string, []>("op_129"), val = tensor<int32, [4]>([0, 3, 1, 2])];
+            tensor<fp16, [1, 512, 1, 64]> mask = transpose(perm = var_129, x = mask_cast_fp16)[name = tensor<string, []>("transpose_0")];
+        } -> (x, cos, sin, mask);
+}

Llama-3.2-3B-Instruct_chunk1.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6f15abcf5514d401e17446e479bffc8f51867d8bec5ad4b84751ed31b378192
+size 788398464

Llama-3.2-3B-Instruct_chunk10.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf21e446e7587de3fd840eae95f3e79729298df568725552f7ef5fd8f954e58c
+size 243

Llama-3.2-3B-Instruct_chunk10.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8129d684aa1ea8b76708a186fe44f7ffc4aa08b4854907105fe41c0825e71875
+size 653

Llama-3.2-3B-Instruct_chunk10.mlmodelc/metadata.json

@@ -0,0 +1,178 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Float16",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3072 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[1, 3072, 8, 8]",
+        "name" : "new_x",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 1 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 1, 1024]",
+        "name" : "new_k_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 64]",
+        "name" : "new_v_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 1 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 1, 1024]",
+        "name" : "new_k_cache_1",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 64]",
+        "name" : "new_v_cache_1",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 7,
+    "mlProgramOperationTypeHistogram" : {
+      "Concat" : 14,
+      "Ios16.mul" : 70,
+      "SliceByIndex" : 88,
+      "Transpose" : 2,
+      "Ios16.einsum" : 96,
+      "Ios16.conv" : 14,
+      "Ios16.add" : 56,
+      "Ios16.realDiv" : 4,
+      "Ios16.softmax" : 48,
+      "Ios16.reduceL2Norm" : 4,
+      "Ios16.reshape" : 14,
+      "Ios16.silu" : 2
+    },
+    "computePrecision" : "Mixed (Float16, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.1.0",
+      "com.github.apple.coremltools.version" : "8.0b1"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3072 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[1, 3072, 8, 8]",
+        "name" : "x",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 128 × 64)",
+        "shortDescription" : "",
+        "shape" : "[128, 64]",
+        "name" : "cos",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 128 × 64)",
+        "shortDescription" : "",
+        "shape" : "[128, 64]",
+        "name" : "sin",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 512 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 512, 1, 64]",
+        "name" : "mask",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 448 × 1 × 1024)?",
+        "shortDescription" : "",
+        "shape" : "[1, 448, 1, 1024]",
+        "name" : "k_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 448)?",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 448]",
+        "name" : "v_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 448 × 1 × 1024)?",
+        "shortDescription" : "",
+        "shape" : "[1, 448, 1, 1024]",
+        "name" : "k_cache_1",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 448)?",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 448]",
+        "name" : "v_cache_1",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "Llama_3_2_3B_Instruct_2024_11_09_16_14_37_chunk10",
+    "method" : "predict"
+  }
+]

Llama-3.2-3B-Instruct_chunk10.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:943564e130d797200225f5eaeef339030c6c3c01691819963fe7ef78303c8545
+size 402679744

Llama-3.2-3B-Instruct_chunk11.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf21e446e7587de3fd840eae95f3e79729298df568725552f7ef5fd8f954e58c
+size 243

Llama-3.2-3B-Instruct_chunk11.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8129d684aa1ea8b76708a186fe44f7ffc4aa08b4854907105fe41c0825e71875
+size 653

Llama-3.2-3B-Instruct_chunk11.mlmodelc/metadata.json

@@ -0,0 +1,178 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Float16",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3072 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[1, 3072, 8, 8]",
+        "name" : "new_x",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 1 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 1, 1024]",
+        "name" : "new_k_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 64]",
+        "name" : "new_v_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 1 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 1, 1024]",
+        "name" : "new_k_cache_1",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 64]",
+        "name" : "new_v_cache_1",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 7,
+    "mlProgramOperationTypeHistogram" : {
+      "Concat" : 14,
+      "Ios16.mul" : 70,
+      "SliceByIndex" : 88,
+      "Transpose" : 2,
+      "Ios16.einsum" : 96,
+      "Ios16.conv" : 14,
+      "Ios16.add" : 56,
+      "Ios16.realDiv" : 4,
+      "Ios16.softmax" : 48,
+      "Ios16.reduceL2Norm" : 4,
+      "Ios16.reshape" : 14,
+      "Ios16.silu" : 2
+    },
+    "computePrecision" : "Mixed (Float16, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.1.0",
+      "com.github.apple.coremltools.version" : "8.0b1"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3072 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[1, 3072, 8, 8]",
+        "name" : "x",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 128 × 64)",
+        "shortDescription" : "",
+        "shape" : "[128, 64]",
+        "name" : "cos",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 128 × 64)",
+        "shortDescription" : "",
+        "shape" : "[128, 64]",
+        "name" : "sin",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 512 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 512, 1, 64]",
+        "name" : "mask",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 448 × 1 × 1024)?",
+        "shortDescription" : "",
+        "shape" : "[1, 448, 1, 1024]",
+        "name" : "k_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 448)?",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 448]",
+        "name" : "v_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 448 × 1 × 1024)?",
+        "shortDescription" : "",
+        "shape" : "[1, 448, 1, 1024]",
+        "name" : "k_cache_1",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 448)?",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 448]",
+        "name" : "v_cache_1",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "Llama_3_2_3B_Instruct_2024_11_09_16_14_37_chunk11",
+    "method" : "predict"
+  }
+]

Llama-3.2-3B-Instruct_chunk11.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d05d3ea64682e5a7113cac2eafb36ecb827788c42f94832abe42470a06e6bd90
+size 402679744

Llama-3.2-3B-Instruct_chunk12.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf21e446e7587de3fd840eae95f3e79729298df568725552f7ef5fd8f954e58c
+size 243

Llama-3.2-3B-Instruct_chunk12.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8129d684aa1ea8b76708a186fe44f7ffc4aa08b4854907105fe41c0825e71875
+size 653

Llama-3.2-3B-Instruct_chunk12.mlmodelc/metadata.json

@@ -0,0 +1,178 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Float16",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3072 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[1, 3072, 8, 8]",
+        "name" : "new_x",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 1 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 1, 1024]",
+        "name" : "new_k_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 64]",
+        "name" : "new_v_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 1 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 1, 1024]",
+        "name" : "new_k_cache_1",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 64]",
+        "name" : "new_v_cache_1",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 7,
+    "mlProgramOperationTypeHistogram" : {
+      "Concat" : 14,
+      "Ios16.mul" : 70,
+      "SliceByIndex" : 88,
+      "Transpose" : 2,
+      "Ios16.einsum" : 96,
+      "Ios16.conv" : 14,
+      "Ios16.add" : 56,
+      "Ios16.realDiv" : 4,
+      "Ios16.softmax" : 48,
+      "Ios16.reduceL2Norm" : 4,
+      "Ios16.reshape" : 14,
+      "Ios16.silu" : 2
+    },
+    "computePrecision" : "Mixed (Float16, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.1.0",
+      "com.github.apple.coremltools.version" : "8.0b1"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3072 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[1, 3072, 8, 8]",
+        "name" : "x",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 128 × 64)",
+        "shortDescription" : "",
+        "shape" : "[128, 64]",
+        "name" : "cos",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 128 × 64)",
+        "shortDescription" : "",
+        "shape" : "[128, 64]",
+        "name" : "sin",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 512 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 512, 1, 64]",
+        "name" : "mask",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 448 × 1 × 1024)?",
+        "shortDescription" : "",
+        "shape" : "[1, 448, 1, 1024]",
+        "name" : "k_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 448)?",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 448]",
+        "name" : "v_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 448 × 1 × 1024)?",
+        "shortDescription" : "",
+        "shape" : "[1, 448, 1, 1024]",
+        "name" : "k_cache_1",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 448)?",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 448]",
+        "name" : "v_cache_1",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "Llama_3_2_3B_Instruct_2024_11_09_16_14_37_chunk12",
+    "method" : "predict"
+  }
+]

Llama-3.2-3B-Instruct_chunk12.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b78ea2d679f5c65ebc0a051180df02861df9dfad72fdbd6d7da795e6effcbd4
+size 402679744

Llama-3.2-3B-Instruct_chunk13.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf21e446e7587de3fd840eae95f3e79729298df568725552f7ef5fd8f954e58c
+size 243

Llama-3.2-3B-Instruct_chunk13.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b45f96f9ba201e16f197a78412041f41d2ac869df9ad95ef03af7662e7d940
+size 653

Llama-3.2-3B-Instruct_chunk13.mlmodelc/metadata.json

@@ -0,0 +1,178 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Float16",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3072 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[1, 3072, 8, 8]",
+        "name" : "new_x",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 1 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 1, 1024]",
+        "name" : "new_k_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 64]",
+        "name" : "new_v_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 1 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 1, 1024]",
+        "name" : "new_k_cache_1",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 64]",
+        "name" : "new_v_cache_1",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 7,
+    "mlProgramOperationTypeHistogram" : {
+      "Concat" : 14,
+      "Ios16.mul" : 70,
+      "SliceByIndex" : 88,
+      "Transpose" : 2,
+      "Ios16.einsum" : 96,
+      "Ios16.conv" : 14,
+      "Ios16.add" : 56,
+      "Ios16.realDiv" : 4,
+      "Ios16.softmax" : 48,
+      "Ios16.reduceL2Norm" : 4,
+      "Ios16.reshape" : 14,
+      "Ios16.silu" : 2
+    },
+    "computePrecision" : "Mixed (Float16, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.1.0",
+      "com.github.apple.coremltools.version" : "8.0b1"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3072 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[1, 3072, 8, 8]",
+        "name" : "x",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 128 × 64)",
+        "shortDescription" : "",
+        "shape" : "[128, 64]",
+        "name" : "cos",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 128 × 64)",
+        "shortDescription" : "",
+        "shape" : "[128, 64]",
+        "name" : "sin",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 512 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 512, 1, 64]",
+        "name" : "mask",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 448 × 1 × 1024)?",
+        "shortDescription" : "",
+        "shape" : "[1, 448, 1, 1024]",
+        "name" : "k_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 448)?",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 448]",
+        "name" : "v_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 448 × 1 × 1024)?",
+        "shortDescription" : "",
+        "shape" : "[1, 448, 1, 1024]",
+        "name" : "k_cache_1",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 448)?",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 448]",
+        "name" : "v_cache_1",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "Llama_3_2_3B_Instruct_2024_11_09_16_14_37_chunk13",
+    "method" : "predict"
+  }
+]

Llama-3.2-3B-Instruct_chunk13.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c010e4d1d6fba27b10c2fc842fe9244994286e621309812a88c461ddeb071342
+size 402679744

Llama-3.2-3B-Instruct_chunk14.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf21e446e7587de3fd840eae95f3e79729298df568725552f7ef5fd8f954e58c
+size 243

Llama-3.2-3B-Instruct_chunk14.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8129d684aa1ea8b76708a186fe44f7ffc4aa08b4854907105fe41c0825e71875
+size 653

Llama-3.2-3B-Instruct_chunk14.mlmodelc/metadata.json

@@ -0,0 +1,178 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Float16",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3072 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[1, 3072, 8, 8]",
+        "name" : "new_x",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 1 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 1, 1024]",
+        "name" : "new_k_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 64]",
+        "name" : "new_v_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 1 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 1, 1024]",
+        "name" : "new_k_cache_1",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 64]",
+        "name" : "new_v_cache_1",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 7,
+    "mlProgramOperationTypeHistogram" : {
+      "Concat" : 14,
+      "Ios16.mul" : 70,
+      "SliceByIndex" : 88,
+      "Transpose" : 2,
+      "Ios16.einsum" : 96,
+      "Ios16.conv" : 14,
+      "Ios16.add" : 56,
+      "Ios16.realDiv" : 4,
+      "Ios16.softmax" : 48,
+      "Ios16.reduceL2Norm" : 4,
+      "Ios16.reshape" : 14,
+      "Ios16.silu" : 2
+    },
+    "computePrecision" : "Mixed (Float16, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.1.0",
+      "com.github.apple.coremltools.version" : "8.0b1"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3072 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[1, 3072, 8, 8]",
+        "name" : "x",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 128 × 64)",
+        "shortDescription" : "",
+        "shape" : "[128, 64]",
+        "name" : "cos",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 128 × 64)",
+        "shortDescription" : "",
+        "shape" : "[128, 64]",
+        "name" : "sin",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 512 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 512, 1, 64]",
+        "name" : "mask",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 448 × 1 × 1024)?",
+        "shortDescription" : "",
+        "shape" : "[1, 448, 1, 1024]",
+        "name" : "k_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 448)?",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 448]",
+        "name" : "v_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 448 × 1 × 1024)?",
+        "shortDescription" : "",
+        "shape" : "[1, 448, 1, 1024]",
+        "name" : "k_cache_1",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 448)?",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 448]",
+        "name" : "v_cache_1",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "Llama_3_2_3B_Instruct_2024_11_09_16_14_37_chunk14",
+    "method" : "predict"
+  }
+]

Llama-3.2-3B-Instruct_chunk14.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f154c6a8553b1baf60e07b7f98801702aa94b24c825db6651c5dea4d28f0c0b6
+size 402679744

Llama-3.2-3B-Instruct_chunk15.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf21e446e7587de3fd840eae95f3e79729298df568725552f7ef5fd8f954e58c
+size 243

Llama-3.2-3B-Instruct_chunk15.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8129d684aa1ea8b76708a186fe44f7ffc4aa08b4854907105fe41c0825e71875
+size 653

Llama-3.2-3B-Instruct_chunk15.mlmodelc/metadata.json

@@ -0,0 +1,178 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Float16",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3072 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[1, 3072, 8, 8]",
+        "name" : "new_x",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 1 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 1, 1024]",
+        "name" : "new_k_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 64]",
+        "name" : "new_v_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 1 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 1, 1024]",
+        "name" : "new_k_cache_1",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 64]",
+        "name" : "new_v_cache_1",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 7,
+    "mlProgramOperationTypeHistogram" : {
+      "Concat" : 14,
+      "Ios16.mul" : 70,
+      "SliceByIndex" : 88,
+      "Transpose" : 2,
+      "Ios16.einsum" : 96,
+      "Ios16.conv" : 14,
+      "Ios16.add" : 56,
+      "Ios16.realDiv" : 4,
+      "Ios16.softmax" : 48,
+      "Ios16.reduceL2Norm" : 4,
+      "Ios16.reshape" : 14,
+      "Ios16.silu" : 2
+    },
+    "computePrecision" : "Mixed (Float16, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.1.0",
+      "com.github.apple.coremltools.version" : "8.0b1"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3072 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[1, 3072, 8, 8]",
+        "name" : "x",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 128 × 64)",
+        "shortDescription" : "",
+        "shape" : "[128, 64]",
+        "name" : "cos",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 128 × 64)",
+        "shortDescription" : "",
+        "shape" : "[128, 64]",
+        "name" : "sin",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 512 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 512, 1, 64]",
+        "name" : "mask",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 448 × 1 × 1024)?",
+        "shortDescription" : "",
+        "shape" : "[1, 448, 1, 1024]",
+        "name" : "k_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 448)?",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 448]",
+        "name" : "v_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 448 × 1 × 1024)?",
+        "shortDescription" : "",
+        "shape" : "[1, 448, 1, 1024]",
+        "name" : "k_cache_1",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 448)?",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 448]",
+        "name" : "v_cache_1",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "Llama_3_2_3B_Instruct_2024_11_09_16_14_37_chunk15",
+    "method" : "predict"
+  }
+]

Llama-3.2-3B-Instruct_chunk15.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb9d6d8288946add36334ed30dca14912099e940d2f8989248bac042f9112d1
+size 402679744

Llama-3.2-3B-Instruct_chunk16.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:099d892d9754805b9d755f8a563efcf8322cc8319dee028d51b62ca558115cb5
+size 243

Llama-3.2-3B-Instruct_chunk16.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:351176279ef47a4a1ba4a1c69135c7c59e5181f28a16fe3d47f04bd2a80c5863
+size 501

Llama-3.2-3B-Instruct_chunk16.mlmodelc/metadata.json

@@ -0,0 +1,134 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Float16",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 16384)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 16384]",
+        "name" : "logits_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 16384)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 16384]",
+        "name" : "logits_1",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 16384)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 16384]",
+        "name" : "logits_2",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 16384)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 16384]",
+        "name" : "logits_3",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 16384)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 16384]",
+        "name" : "logits_4",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 16384)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 16384]",
+        "name" : "logits_5",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 16384)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 16384]",
+        "name" : "logits_6",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 13568)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 13568]",
+        "name" : "logits_7",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 7,
+    "mlProgramOperationTypeHistogram" : {
+      "Concat" : 1,
+      "Ios16.mul" : 2,
+      "Squeeze" : 1,
+      "Transpose" : 1,
+      "Ios16.reshape" : 10,
+      "Ios16.matmul" : 8,
+      "Ios16.realDiv" : 1,
+      "Ios16.reduceL2Norm" : 1
+    },
+    "computePrecision" : "Mixed (Float16, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.1.0",
+      "com.github.apple.coremltools.version" : "8.0b1"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3072 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[1, 3072, 8, 8]",
+        "name" : "x",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "Llama_3_2_3B_Instruct_2024_11_09_16_14_37_chunk16",
+    "method" : "predict"
+  }
+]

Llama-3.2-3B-Instruct_chunk16.mlmodelc/model.mil

@@ -0,0 +1,74 @@
+program(1.0)
+[buildInfo = dict<tensor<string, []>, tensor<string, []>>({{"coremlc-component-MIL", "3304.5.2"}, {"coremlc-version", "3304.6.2"}, {"coremltools-component-torch", "2.1.0"}, {"coremltools-source-dialect", "TorchScript"}, {"coremltools-version", "8.0b1"}})]
+{
+    func main<ios16>(tensor<fp16, [1, 3072, 8, 8]> x) {
+            tensor<bool, []> var_6 = const()[name = tensor<string, []>("op_6"), val = tensor<bool, []>(true)];
+            tensor<int32, []> var_9 = const()[name = tensor<string, []>("op_9"), val = tensor<int32, []>(1)];
+            tensor<bool, []> x_eps_interleave_0 = const()[name = tensor<string, []>("x_eps_interleave_0"), val = tensor<bool, []>(false)];
+            tensor<fp16, [1, 1, 8, 8]> eps_chan_to_fp16 = const()[name = tensor<string, []>("eps_chan_to_fp16"), val = tensor<fp16, [1, 1, 8, 8]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(64)))];
+            tensor<fp16, [1, 3073, 8, 8]> x_eps_cast_fp16 = concat(axis = var_9, interleave = x_eps_interleave_0, values = (x, eps_chan_to_fp16))[name = tensor<string, []>("x_eps_cast_fp16")];
+            tensor<int32, [1]> norm_x_axes_0 = const()[name = tensor<string, []>("norm_x_axes_0"), val = tensor<int32, [1]>([1])];
+            tensor<fp16, [1, 1, 8, 8]> norm_x_cast_fp16 = reduce_l2_norm(axes = norm_x_axes_0, keep_dims = var_6, x = x_eps_cast_fp16)[name = tensor<string, []>("norm_x_cast_fp16")];
+            tensor<fp16, [1, 3072, 8, 8]> x_normed_1_cast_fp16 = real_div(x = x, y = norm_x_cast_fp16)[name = tensor<string, []>("x_normed_1_cast_fp16")];
+            tensor<fp16, []> var_34_to_fp16 = const()[name = tensor<string, []>("op_34_to_fp16"), val = tensor<fp16, []>(0x1.bb8p+5)];
+            tensor<fp16, [1, 3072, 8, 8]> x_normed_3_cast_fp16 = mul(x = x_normed_1_cast_fp16, y = var_34_to_fp16)[name = tensor<string, []>("x_normed_3_cast_fp16")];
+            tensor<fp16, [1, 3072, 1, 1]> ln_f_weight_to_fp16 = const()[name = tensor<string, []>("ln_f_weight_to_fp16"), val = tensor<fp16, [1, 3072, 1, 1]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(256)))];
+            tensor<fp16, [1, 3072, 8, 8]> x_5_cast_fp16 = mul(x = x_normed_3_cast_fp16, y = ln_f_weight_to_fp16)[name = tensor<string, []>("x_5_cast_fp16")];
+            tensor<int32, [4]> var_48 = const()[name = tensor<string, []>("op_48"), val = tensor<int32, [4]>([1, 3072, 1, -1])];
+            tensor<fp16, [1, 3072, 1, 64]> x_cast_fp16 = reshape(shape = var_48, x = x_5_cast_fp16)[name = tensor<string, []>("x_cast_fp16")];
+            tensor<int32, [1]> var_51_axes_0 = const()[name = tensor<string, []>("op_51_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 3072, 64]> var_51_cast_fp16 = squeeze(axes = var_51_axes_0, x = x_cast_fp16)[name = tensor<string, []>("op_51_cast_fp16")];
+            tensor<int32, [3]> var_54_perm_0 = const()[name = tensor<string, []>("op_54_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            tensor<int32, [2]> concat_4 = const()[name = tensor<string, []>("concat_4"), val = tensor<int32, [2]>([64, 3072])];
+            tensor<fp16, [1, 64, 3072]> var_54_cast_fp16 = transpose(perm = var_54_perm_0, x = var_51_cast_fp16)[name = tensor<string, []>("transpose_16")];
+            tensor<fp16, [64, 3072]> reshape_0_cast_fp16 = reshape(shape = concat_4, x = var_54_cast_fp16)[name = tensor<string, []>("reshape_0_cast_fp16")];
+            tensor<bool, []> matmul_0_transpose_x_0 = const()[name = tensor<string, []>("matmul_0_transpose_x_0"), val = tensor<bool, []>(false)];
+            tensor<bool, []> matmul_0_transpose_y_0 = const()[name = tensor<string, []>("matmul_0_transpose_y_0"), val = tensor<bool, []>(false)];
+            tensor<fp16, [3072, 16384]> transpose_1_to_fp16 = const()[name = tensor<string, []>("transpose_1_to_fp16"), val = tensor<fp16, [3072, 16384]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(6464)))];
+            tensor<fp16, [64, 16384]> matmul_0_cast_fp16 = matmul(transpose_x = matmul_0_transpose_x_0, transpose_y = matmul_0_transpose_y_0, x = reshape_0_cast_fp16, y = transpose_1_to_fp16)[name = tensor<string, []>("matmul_0_cast_fp16")];
+            tensor<int32, [3]> concat_8 = const()[name = tensor<string, []>("concat_8"), val = tensor<int32, [3]>([1, 64, 16384])];
+            tensor<fp16, [1, 64, 16384]> logits_0 = reshape(shape = concat_8, x = matmul_0_cast_fp16)[name = tensor<string, []>("reshape_2_cast_fp16")];
+            tensor<bool, []> matmul_1_transpose_x_0 = const()[name = tensor<string, []>("matmul_1_transpose_x_0"), val = tensor<bool, []>(false)];
+            tensor<bool, []> matmul_1_transpose_y_0 = const()[name = tensor<string, []>("matmul_1_transpose_y_0"), val = tensor<bool, []>(false)];
+            tensor<fp16, [3072, 16384]> transpose_3_to_fp16 = const()[name = tensor<string, []>("transpose_3_to_fp16"), val = tensor<fp16, [3072, 16384]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(100669824)))];
+            tensor<fp16, [64, 16384]> matmul_1_cast_fp16 = matmul(transpose_x = matmul_1_transpose_x_0, transpose_y = matmul_1_transpose_y_0, x = reshape_0_cast_fp16, y = transpose_3_to_fp16)[name = tensor<string, []>("matmul_1_cast_fp16")];
+            tensor<int32, [3]> concat_16 = const()[name = tensor<string, []>("concat_16"), val = tensor<int32, [3]>([1, 64, 16384])];
+            tensor<fp16, [1, 64, 16384]> logits_1 = reshape(shape = concat_16, x = matmul_1_cast_fp16)[name = tensor<string, []>("reshape_5_cast_fp16")];
+            tensor<bool, []> matmul_2_transpose_x_0 = const()[name = tensor<string, []>("matmul_2_transpose_x_0"), val = tensor<bool, []>(false)];
+            tensor<bool, []> matmul_2_transpose_y_0 = const()[name = tensor<string, []>("matmul_2_transpose_y_0"), val = tensor<bool, []>(false)];
+            tensor<fp16, [3072, 16384]> transpose_5_to_fp16 = const()[name = tensor<string, []>("transpose_5_to_fp16"), val = tensor<fp16, [3072, 16384]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(201333184)))];
+            tensor<fp16, [64, 16384]> matmul_2_cast_fp16 = matmul(transpose_x = matmul_2_transpose_x_0, transpose_y = matmul_2_transpose_y_0, x = reshape_0_cast_fp16, y = transpose_5_to_fp16)[name = tensor<string, []>("matmul_2_cast_fp16")];
+            tensor<int32, [3]> concat_24 = const()[name = tensor<string, []>("concat_24"), val = tensor<int32, [3]>([1, 64, 16384])];
+            tensor<fp16, [1, 64, 16384]> logits_2 = reshape(shape = concat_24, x = matmul_2_cast_fp16)[name = tensor<string, []>("reshape_8_cast_fp16")];
+            tensor<bool, []> matmul_3_transpose_x_0 = const()[name = tensor<string, []>("matmul_3_transpose_x_0"), val = tensor<bool, []>(false)];
+            tensor<bool, []> matmul_3_transpose_y_0 = const()[name = tensor<string, []>("matmul_3_transpose_y_0"), val = tensor<bool, []>(false)];
+            tensor<fp16, [3072, 16384]> transpose_7_to_fp16 = const()[name = tensor<string, []>("transpose_7_to_fp16"), val = tensor<fp16, [3072, 16384]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(301996544)))];
+            tensor<fp16, [64, 16384]> matmul_3_cast_fp16 = matmul(transpose_x = matmul_3_transpose_x_0, transpose_y = matmul_3_transpose_y_0, x = reshape_0_cast_fp16, y = transpose_7_to_fp16)[name = tensor<string, []>("matmul_3_cast_fp16")];
+            tensor<int32, [3]> concat_32 = const()[name = tensor<string, []>("concat_32"), val = tensor<int32, [3]>([1, 64, 16384])];
+            tensor<fp16, [1, 64, 16384]> logits_3 = reshape(shape = concat_32, x = matmul_3_cast_fp16)[name = tensor<string, []>("reshape_11_cast_fp16")];
+            tensor<bool, []> matmul_4_transpose_x_0 = const()[name = tensor<string, []>("matmul_4_transpose_x_0"), val = tensor<bool, []>(false)];
+            tensor<bool, []> matmul_4_transpose_y_0 = const()[name = tensor<string, []>("matmul_4_transpose_y_0"), val = tensor<bool, []>(false)];
+            tensor<fp16, [3072, 16384]> transpose_9_to_fp16 = const()[name = tensor<string, []>("transpose_9_to_fp16"), val = tensor<fp16, [3072, 16384]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(402659904)))];
+            tensor<fp16, [64, 16384]> matmul_4_cast_fp16 = matmul(transpose_x = matmul_4_transpose_x_0, transpose_y = matmul_4_transpose_y_0, x = reshape_0_cast_fp16, y = transpose_9_to_fp16)[name = tensor<string, []>("matmul_4_cast_fp16")];
+            tensor<int32, [3]> concat_40 = const()[name = tensor<string, []>("concat_40"), val = tensor<int32, [3]>([1, 64, 16384])];
+            tensor<fp16, [1, 64, 16384]> logits_4 = reshape(shape = concat_40, x = matmul_4_cast_fp16)[name = tensor<string, []>("reshape_14_cast_fp16")];
+            tensor<bool, []> matmul_5_transpose_x_0 = const()[name = tensor<string, []>("matmul_5_transpose_x_0"), val = tensor<bool, []>(false)];
+            tensor<bool, []> matmul_5_transpose_y_0 = const()[name = tensor<string, []>("matmul_5_transpose_y_0"), val = tensor<bool, []>(false)];
+            tensor<fp16, [3072, 16384]> transpose_11_to_fp16 = const()[name = tensor<string, []>("transpose_11_to_fp16"), val = tensor<fp16, [3072, 16384]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(503323264)))];
+            tensor<fp16, [64, 16384]> matmul_5_cast_fp16 = matmul(transpose_x = matmul_5_transpose_x_0, transpose_y = matmul_5_transpose_y_0, x = reshape_0_cast_fp16, y = transpose_11_to_fp16)[name = tensor<string, []>("matmul_5_cast_fp16")];
+            tensor<int32, [3]> concat_48 = const()[name = tensor<string, []>("concat_48"), val = tensor<int32, [3]>([1, 64, 16384])];
+            tensor<fp16, [1, 64, 16384]> logits_5 = reshape(shape = concat_48, x = matmul_5_cast_fp16)[name = tensor<string, []>("reshape_17_cast_fp16")];
+            tensor<bool, []> matmul_6_transpose_x_0 = const()[name = tensor<string, []>("matmul_6_transpose_x_0"), val = tensor<bool, []>(false)];
+            tensor<bool, []> matmul_6_transpose_y_0 = const()[name = tensor<string, []>("matmul_6_transpose_y_0"), val = tensor<bool, []>(false)];
+            tensor<fp16, [3072, 16384]> transpose_13_to_fp16 = const()[name = tensor<string, []>("transpose_13_to_fp16"), val = tensor<fp16, [3072, 16384]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(603986624)))];
+            tensor<fp16, [64, 16384]> matmul_6_cast_fp16 = matmul(transpose_x = matmul_6_transpose_x_0, transpose_y = matmul_6_transpose_y_0, x = reshape_0_cast_fp16, y = transpose_13_to_fp16)[name = tensor<string, []>("matmul_6_cast_fp16")];
+            tensor<int32, [3]> concat_56 = const()[name = tensor<string, []>("concat_56"), val = tensor<int32, [3]>([1, 64, 16384])];
+            tensor<fp16, [1, 64, 16384]> logits_6 = reshape(shape = concat_56, x = matmul_6_cast_fp16)[name = tensor<string, []>("reshape_20_cast_fp16")];
+            tensor<bool, []> matmul_7_transpose_x_0 = const()[name = tensor<string, []>("matmul_7_transpose_x_0"), val = tensor<bool, []>(false)];
+            tensor<bool, []> matmul_7_transpose_y_0 = const()[name = tensor<string, []>("matmul_7_transpose_y_0"), val = tensor<bool, []>(false)];
+            tensor<fp16, [3072, 13568]> transpose_15_to_fp16 = const()[name = tensor<string, []>("transpose_15_to_fp16"), val = tensor<fp16, [3072, 13568]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(704649984)))];
+            tensor<fp16, [64, 13568]> matmul_7_cast_fp16 = matmul(transpose_x = matmul_7_transpose_x_0, transpose_y = matmul_7_transpose_y_0, x = reshape_0_cast_fp16, y = transpose_15_to_fp16)[name = tensor<string, []>("matmul_7_cast_fp16")];
+            tensor<int32, [3]> concat_64 = const()[name = tensor<string, []>("concat_64"), val = tensor<int32, [3]>([1, 64, 13568])];
+            tensor<fp16, [1, 64, 13568]> logits_7 = reshape(shape = concat_64, x = matmul_7_cast_fp16)[name = tensor<string, []>("reshape_23_cast_fp16")];
+        } -> (logits_0, logits_1, logits_2, logits_3, logits_4, logits_5, logits_6, logits_7);
+}

Llama-3.2-3B-Instruct_chunk16.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd01e5605ef4a5bebc9bcafc5514e012c4c605231c065a1d634fd9fc66df411
+size 788011840

Llama-3.2-3B-Instruct_chunk2.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf21e446e7587de3fd840eae95f3e79729298df568725552f7ef5fd8f954e58c
+size 243

Llama-3.2-3B-Instruct_chunk2.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b45f96f9ba201e16f197a78412041f41d2ac869df9ad95ef03af7662e7d940
+size 653

Llama-3.2-3B-Instruct_chunk2.mlmodelc/metadata.json

@@ -0,0 +1,178 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Float16",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3072 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[1, 3072, 8, 8]",
+        "name" : "new_x",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 1 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 1, 1024]",
+        "name" : "new_k_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 64]",
+        "name" : "new_v_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 1 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 1, 1024]",
+        "name" : "new_k_cache_1",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 64]",
+        "name" : "new_v_cache_1",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 7,
+    "mlProgramOperationTypeHistogram" : {
+      "Concat" : 14,
+      "Ios16.mul" : 70,
+      "SliceByIndex" : 88,
+      "Transpose" : 2,
+      "Ios16.einsum" : 96,
+      "Ios16.conv" : 14,
+      "Ios16.add" : 56,
+      "Ios16.realDiv" : 4,
+      "Ios16.softmax" : 48,
+      "Ios16.reduceL2Norm" : 4,
+      "Ios16.reshape" : 14,
+      "Ios16.silu" : 2
+    },
+    "computePrecision" : "Mixed (Float16, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.1.0",
+      "com.github.apple.coremltools.version" : "8.0b1"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3072 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[1, 3072, 8, 8]",
+        "name" : "x",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 128 × 64)",
+        "shortDescription" : "",
+        "shape" : "[128, 64]",
+        "name" : "cos",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 128 × 64)",
+        "shortDescription" : "",
+        "shape" : "[128, 64]",
+        "name" : "sin",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 512 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 512, 1, 64]",
+        "name" : "mask",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 448 × 1 × 1024)?",
+        "shortDescription" : "",
+        "shape" : "[1, 448, 1, 1024]",
+        "name" : "k_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 448)?",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 448]",
+        "name" : "v_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 448 × 1 × 1024)?",
+        "shortDescription" : "",
+        "shape" : "[1, 448, 1, 1024]",
+        "name" : "k_cache_1",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 448)?",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 448]",
+        "name" : "v_cache_1",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "Llama_3_2_3B_Instruct_2024_11_09_16_14_37_chunk2",
+    "method" : "predict"
+  }
+]

Llama-3.2-3B-Instruct_chunk2.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d49db7568f50fc8f361e2b4cca2888853752a4784bf7a44b06842bebf37ed2b
+size 402679744

Llama-3.2-3B-Instruct_chunk3.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf21e446e7587de3fd840eae95f3e79729298df568725552f7ef5fd8f954e58c
+size 243

Llama-3.2-3B-Instruct_chunk3.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8129d684aa1ea8b76708a186fe44f7ffc4aa08b4854907105fe41c0825e71875
+size 653

Llama-3.2-3B-Instruct_chunk3.mlmodelc/metadata.json

@@ -0,0 +1,178 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Float16",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3072 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[1, 3072, 8, 8]",
+        "name" : "new_x",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 1 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 1, 1024]",
+        "name" : "new_k_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 64]",
+        "name" : "new_v_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 64 × 1 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 64, 1, 1024]",
+        "name" : "new_k_cache_1",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 64]",
+        "name" : "new_v_cache_1",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 7,
+    "mlProgramOperationTypeHistogram" : {
+      "Concat" : 14,
+      "Ios16.mul" : 70,
+      "SliceByIndex" : 88,
+      "Transpose" : 2,
+      "Ios16.einsum" : 96,
+      "Ios16.conv" : 14,
+      "Ios16.add" : 56,
+      "Ios16.realDiv" : 4,
+      "Ios16.softmax" : 48,
+      "Ios16.reduceL2Norm" : 4,
+      "Ios16.reshape" : 14,
+      "Ios16.silu" : 2
+    },
+    "computePrecision" : "Mixed (Float16, Int32)",
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.1.0",
+      "com.github.apple.coremltools.version" : "8.0b1"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 3072 × 8 × 8)",
+        "shortDescription" : "",
+        "shape" : "[1, 3072, 8, 8]",
+        "name" : "x",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 128 × 64)",
+        "shortDescription" : "",
+        "shape" : "[128, 64]",
+        "name" : "cos",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 128 × 64)",
+        "shortDescription" : "",
+        "shape" : "[128, 64]",
+        "name" : "sin",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 512 × 1 × 64)",
+        "shortDescription" : "",
+        "shape" : "[1, 512, 1, 64]",
+        "name" : "mask",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 448 × 1 × 1024)?",
+        "shortDescription" : "",
+        "shape" : "[1, 448, 1, 1024]",
+        "name" : "k_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 448)?",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 448]",
+        "name" : "v_cache_0",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 448 × 1 × 1024)?",
+        "shortDescription" : "",
+        "shape" : "[1, 448, 1, 1024]",
+        "name" : "k_cache_1",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "1",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1024 × 1 × 448)?",
+        "shortDescription" : "",
+        "shape" : "[1, 1024, 1, 448]",
+        "name" : "v_cache_1",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "Llama_3_2_3B_Instruct_2024_11_09_16_14_37_chunk3",
+    "method" : "predict"
+  }
+]

Llama-3.2-3B-Instruct_chunk3.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:934f835704cd4576365155fea7f05c7308ec2dc8b0c69d6d800fdc6e646ea0ce
+size 402679744