Upload folder using huggingface_hub

custom/custom_FFN_PF_lut4_chunk_01of01.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d61b88bebdd3ab1149a9256fa255a0cb8ca68e157679e0ac5c03ac840414073
+size 2432838

custom/custom_FFN_PF_lut4_chunk_01of01.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed75455d7ca4f4ee07de2767873017c7ba682877d26bfbf39ebca8f7470aa94
+size 775086336

custom/custom_FFN_PF_lut4_chunk_01of01.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "8AF6FC31-EB32-469F-B437-3E7EC4A85979": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "C5BD2776-CFCF-4969-879D-2770E575745B": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "C5BD2776-CFCF-4969-879D-2770E575745B"
+}

custom/custom_embeddings.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d1ef532bcbe96c8e5a561c733e96aec0cef0240c6c0daa1828ed1aa8fe33439
+size 550

custom/custom_embeddings.mlmodelc/model.mil

@@ -0,0 +1,16 @@
+program(1.3)
+[buildInfo = dict<string, string>({{"coremlc-component-MIL", "3510.2.1"}, {"coremlc-version", "3500.32.1"}, {"coremltools-component-torch", "2.7.1"}, {"coremltools-source-dialect", "TorchScript"}, {"coremltools-version", "9.0"}})]
+{
+    func main<ios18>(tensor<int32, [1, 1]> input_ids) {
+            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, [120818, 2048]> embed_tokens_weight_to_fp16 = const()[name = string("embed_tokens_weight_to_fp16"), val = tensor<fp16, [120818, 2048]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(64)))];
+            int32 greater_equal_0_y_0 = const()[name = string("greater_equal_0_y_0"), val = int32(0)];
+            tensor<bool, [1, 1]> greater_equal_0 = greater_equal(x = input_ids, y = greater_equal_0_y_0)[name = string("greater_equal_0")];
+            int32 slice_by_index_0 = const()[name = string("slice_by_index_0"), val = int32(120818)];
+            tensor<int32, [1, 1]> add_0 = add(x = input_ids, y = slice_by_index_0)[name = string("add_0")];
+            tensor<int32, [1, 1]> select_0 = select(a = input_ids, b = add_0, cond = greater_equal_0)[name = string("select_0")];
+            int32 hidden_states_cast_fp16_axis_0 = const()[name = string("hidden_states_cast_fp16_axis_0"), val = int32(0)];
+            tensor<fp16, [1, 1, 2048]> hidden_states = gather(axis = hidden_states_cast_fp16_axis_0, batch_dims = hidden_states_batch_dims_0, indices = select_0, validate_indices = hidden_states_validate_indices_0, x = embed_tokens_weight_to_fp16)[name = string("hidden_states_cast_fp16")];
+        } -> (hidden_states);
+}

custom/custom_embeddings.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97f05fcb658b26724981c787e0747aa9bed31541629f63774212e3e71538530
+size 494870656

custom/custom_lm_head_lut6.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e41d277f42c917c2c6a54ff4e044a7c666648d830daed3576fe63d878d7aed32
+size 1106

custom/custom_lm_head_lut6.mlmodelc/model.mil

@@ -0,0 +1,186 @@
+program(1.3)
+[buildInfo = dict<string, string>({{"coremlc-component-MIL", "3510.2.1"}, {"coremlc-version", "3500.32.1"}})]
+{
+    func main<ios18>(tensor<fp16, [1, 1, 2048]> hidden_states) {
+            tensor<int32, [3]> var_5 = const()[name = string("op_5"), val = tensor<int32, [3]>([0, 2, 1])];
+            tensor<int32, [1]> input_axes_0 = const()[name = string("input_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 2048, 1]> var_6_cast_fp16 = transpose(perm = var_5, x = hidden_states)[name = string("transpose_16")];
+            tensor<fp16, [1, 2048, 1, 1]> input_cast_fp16 = expand_dims(axes = input_axes_0, x = var_6_cast_fp16)[name = string("input_cast_fp16")];
+            string var_29_pad_type_0 = const()[name = string("op_29_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_29_strides_0 = const()[name = string("op_29_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_29_pad_0 = const()[name = string("op_29_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_29_dilations_0 = const()[name = string("op_29_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_29_groups_0 = const()[name = string("op_29_groups_0"), val = int32(1)];
+            tensor<fp16, [7552, 2048, 1, 1]> op_9_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [7552, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(64))), lut = tensor<fp16, [944, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(11600000))))[name = string("op_9_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 7552, 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, 7552, 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, [7552, 2048, 1, 1]> op_35_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [7552, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(11720896))), lut = tensor<fp16, [944, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(23320832))))[name = string("op_35_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 7552, 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, 7552, 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, [7551, 2048, 1, 1]> var_61_promoted_to_fp16 = const()[name = string("op_61_promoted_to_fp16"), val = tensor<fp16, [7551, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(23441728)))];
+            tensor<fp16, [1, 7551, 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 = var_61_promoted_to_fp16, 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, 7551, 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, [7551, 2048, 1, 1]> var_87_promoted_to_fp16 = const()[name = string("op_87_promoted_to_fp16"), val = tensor<fp16, [7551, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(54370688)))];
+            tensor<fp16, [1, 7551, 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 = var_87_promoted_to_fp16, 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, 7551, 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, [7551, 2048, 1, 1]> var_113_promoted_to_fp16 = const()[name = string("op_113_promoted_to_fp16"), val = tensor<fp16, [7551, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(85299648)))];
+            tensor<fp16, [1, 7551, 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 = var_113_promoted_to_fp16, 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, 7551, 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, [7551, 2048, 1, 1]> var_139_promoted_to_fp16 = const()[name = string("op_139_promoted_to_fp16"), val = tensor<fp16, [7551, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(116228608)))];
+            tensor<fp16, [1, 7551, 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 = var_139_promoted_to_fp16, 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, 7551, 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, [7551, 2048, 1, 1]> var_165_promoted_to_fp16 = const()[name = string("op_165_promoted_to_fp16"), val = tensor<fp16, [7551, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(147157568)))];
+            tensor<fp16, [1, 7551, 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 = var_165_promoted_to_fp16, 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, 7551, 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, [7551, 2048, 1, 1]> var_191_promoted_to_fp16 = const()[name = string("op_191_promoted_to_fp16"), val = tensor<fp16, [7551, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(178086528)))];
+            tensor<fp16, [1, 7551, 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 = var_191_promoted_to_fp16, 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, 7551, 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, [7551, 2048, 1, 1]> var_217_promoted_to_fp16 = const()[name = string("op_217_promoted_to_fp16"), val = tensor<fp16, [7551, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(209015488)))];
+            tensor<fp16, [1, 7551, 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 = var_217_promoted_to_fp16, 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, 7551, 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, [7551, 2048, 1, 1]> var_243_promoted_to_fp16 = const()[name = string("op_243_promoted_to_fp16"), val = tensor<fp16, [7551, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(239944448)))];
+            tensor<fp16, [1, 7551, 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 = var_243_promoted_to_fp16, 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, 7551, 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, [7551, 2048, 1, 1]> var_269_promoted_to_fp16 = const()[name = string("op_269_promoted_to_fp16"), val = tensor<fp16, [7551, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(270873408)))];
+            tensor<fp16, [1, 7551, 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 = var_269_promoted_to_fp16, 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, 7551, 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, [7551, 2048, 1, 1]> var_295_promoted_to_fp16 = const()[name = string("op_295_promoted_to_fp16"), val = tensor<fp16, [7551, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(301802368)))];
+            tensor<fp16, [1, 7551, 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 = var_295_promoted_to_fp16, 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, 7551, 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, [7551, 2048, 1, 1]> var_321_promoted_to_fp16 = const()[name = string("op_321_promoted_to_fp16"), val = tensor<fp16, [7551, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(332731328)))];
+            tensor<fp16, [1, 7551, 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 = var_321_promoted_to_fp16, 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, 7551, 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, [7551, 2048, 1, 1]> var_347_promoted_to_fp16 = const()[name = string("op_347_promoted_to_fp16"), val = tensor<fp16, [7551, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(363660288)))];
+            tensor<fp16, [1, 7551, 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 = var_347_promoted_to_fp16, 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, 7551, 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, [7551, 2048, 1, 1]> var_373_promoted_to_fp16 = const()[name = string("op_373_promoted_to_fp16"), val = tensor<fp16, [7551, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(394589248)))];
+            tensor<fp16, [1, 7551, 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 = var_373_promoted_to_fp16, 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, 7551, 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, [7551, 2048, 1, 1]> var_399_promoted_to_fp16 = const()[name = string("op_399_promoted_to_fp16"), val = tensor<fp16, [7551, 2048, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(425518208)))];
+            tensor<fp16, [1, 7551, 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 = var_399_promoted_to_fp16, 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, 7551, 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, 7552]> logits1 = transpose(perm = var_34_perm_0, x = var_31_cast_fp16)[name = string("transpose_0")];
+            tensor<fp16, [1, 1, 7552]> logits2 = transpose(perm = var_60_perm_0, x = var_57_cast_fp16)[name = string("transpose_1")];
+            tensor<fp16, [1, 1, 7551]> logits3 = transpose(perm = var_86_perm_0, x = var_83_cast_fp16)[name = string("transpose_2")];
+            tensor<fp16, [1, 1, 7551]> logits4 = transpose(perm = var_112_perm_0, x = var_109_cast_fp16)[name = string("transpose_3")];
+            tensor<fp16, [1, 1, 7551]> logits5 = transpose(perm = var_138_perm_0, x = var_135_cast_fp16)[name = string("transpose_4")];
+            tensor<fp16, [1, 1, 7551]> logits6 = transpose(perm = var_164_perm_0, x = var_161_cast_fp16)[name = string("transpose_5")];
+            tensor<fp16, [1, 1, 7551]> logits7 = transpose(perm = var_190_perm_0, x = var_187_cast_fp16)[name = string("transpose_6")];
+            tensor<fp16, [1, 1, 7551]> logits8 = transpose(perm = var_216_perm_0, x = var_213_cast_fp16)[name = string("transpose_7")];
+            tensor<fp16, [1, 1, 7551]> logits9 = transpose(perm = var_242_perm_0, x = var_239_cast_fp16)[name = string("transpose_8")];
+            tensor<fp16, [1, 1, 7551]> logits10 = transpose(perm = var_268_perm_0, x = var_265_cast_fp16)[name = string("transpose_9")];
+            tensor<fp16, [1, 1, 7551]> logits11 = transpose(perm = var_294_perm_0, x = var_291_cast_fp16)[name = string("transpose_10")];
+            tensor<fp16, [1, 1, 7551]> logits12 = transpose(perm = var_320_perm_0, x = var_317_cast_fp16)[name = string("transpose_11")];
+            tensor<fp16, [1, 1, 7551]> logits13 = transpose(perm = var_346_perm_0, x = var_343_cast_fp16)[name = string("transpose_12")];
+            tensor<fp16, [1, 1, 7551]> logits14 = transpose(perm = var_372_perm_0, x = var_369_cast_fp16)[name = string("transpose_13")];
+            tensor<fp16, [1, 1, 7551]> logits15 = transpose(perm = var_398_perm_0, x = var_395_cast_fp16)[name = string("transpose_14")];
+            tensor<fp16, [1, 1, 7551]> 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);
+}

custom/custom_lm_head_lut6.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c7d4c7ad77b553491145ff32870ec94fc1a471ca8ca3ea5dc7e87fa1641f692
+size 456447168