program(1.0)
[buildInfo = dict<tensor<string, []>, tensor<string, []>>({{"coremlc-component-MIL", "3520.4.1"}, {"coremlc-version", "3520.5.1"}, {"coremltools-component-torch", "2.11.0"}, {"coremltools-source-dialect", "TorchScript"}, {"coremltools-version", "8.3.0"}})]
{
    func main<ios17>(tensor<fp32, [1, 512, 768]> embedding, tensor<fp32, [1, 256]> features, tensor<fp32, [1]> sigma, tensor<fp32, [1, 1, 256]> x_noisy) {
            tensor<int32, [3]> var_25 = const()[name = tensor<string, []>("op_25"), val = tensor<int32, [3]>([-1, 1, 1])];
            tensor<string, []> sigma_to_fp16_dtype_0 = const()[name = tensor<string, []>("sigma_to_fp16_dtype_0"), val = tensor<string, []>("fp16")];
            tensor<fp16, [1]> sigma_to_fp16 = cast(dtype = sigma_to_fp16_dtype_0, x = sigma)[name = tensor<string, []>("cast_27")];
            tensor<fp16, [1, 1, 1]> s_cast_fp16 = reshape(shape = var_25, x = sigma_to_fp16)[name = tensor<string, []>("s_cast_fp16")];
            tensor<fp16, [1, 1, 1]> var_27_cast_fp16 = mul(x = s_cast_fp16, y = s_cast_fp16)[name = tensor<string, []>("op_27_cast_fp16")];
            tensor<fp16, []> var_29_to_fp16 = const()[name = tensor<string, []>("op_29_to_fp16"), val = tensor<fp16, []>(0x1.47cp-5)];
            tensor<fp16, [1, 1, 1]> var_30_cast_fp16 = add(x = var_27_cast_fp16, y = var_29_to_fp16)[name = tensor<string, []>("op_30_cast_fp16")];
            tensor<fp32, []> var_31_epsilon_0 = const()[name = tensor<string, []>("op_31_epsilon_0"), val = tensor<fp32, []>(0x1.a36e2ep-14)];
            tensor<fp16, [1, 1, 1]> var_31_cast_fp16 = inverse(epsilon = var_31_epsilon_0, x = var_30_cast_fp16)[name = tensor<string, []>("op_31_cast_fp16")];
            tensor<fp16, []> var_32_to_fp16 = const()[name = tensor<string, []>("op_32_to_fp16"), val = tensor<fp16, []>(0x1.47cp-5)];
            tensor<fp16, [1, 1, 1]> c_skip_cast_fp16 = mul(x = var_31_cast_fp16, y = var_32_to_fp16)[name = tensor<string, []>("c_skip_cast_fp16")];
            tensor<fp16, []> var_34_to_fp16 = const()[name = tensor<string, []>("op_34_to_fp16"), val = tensor<fp16, []>(0x1.998p-3)];
            tensor<fp16, [1, 1, 1]> var_35_cast_fp16 = mul(x = s_cast_fp16, y = var_34_to_fp16)[name = tensor<string, []>("op_35_cast_fp16")];
            tensor<fp16, [1, 1, 1]> var_40_cast_fp16 = sqrt(x = var_30_cast_fp16)[name = tensor<string, []>("op_40_cast_fp16")];
            tensor<fp16, [1, 1, 1]> c_out_cast_fp16 = real_div(x = var_35_cast_fp16, y = var_40_cast_fp16)[name = tensor<string, []>("c_out_cast_fp16")];
            tensor<fp32, []> var_47_epsilon_0 = const()[name = tensor<string, []>("op_47_epsilon_0"), val = tensor<fp32, []>(0x1.a36e2ep-14)];
            tensor<fp16, [1, 1, 1]> var_47_cast_fp16 = inverse(epsilon = var_47_epsilon_0, x = var_40_cast_fp16)[name = tensor<string, []>("op_47_cast_fp16")];
            tensor<fp32, []> var_50_epsilon_0 = const()[name = tensor<string, []>("op_50_epsilon_0"), val = tensor<fp32, []>(0x1p-149)];
            tensor<fp16, [1]> var_50_cast_fp16 = log(epsilon = var_50_epsilon_0, x = sigma_to_fp16)[name = tensor<string, []>("op_50_cast_fp16")];
            tensor<fp16, []> var_51_to_fp16 = const()[name = tensor<string, []>("op_51_to_fp16"), val = tensor<fp16, []>(0x1p-2)];
            tensor<fp16, [1]> x_1_cast_fp16 = mul(x = var_50_cast_fp16, y = var_51_to_fp16)[name = tensor<string, []>("x_1_cast_fp16")];
            tensor<string, []> x_noisy_to_fp16_dtype_0 = const()[name = tensor<string, []>("x_noisy_to_fp16_dtype_0"), val = tensor<string, []>("fp16")];
            tensor<fp16, [1, 1, 256]> x_noisy_to_fp16 = cast(dtype = x_noisy_to_fp16_dtype_0, x = x_noisy)[name = tensor<string, []>("cast_26")];
            tensor<fp16, [1, 1, 256]> x_11_cast_fp16 = mul(x = var_47_cast_fp16, y = x_noisy_to_fp16)[name = tensor<string, []>("x_11_cast_fp16")];
            tensor<int32, []> var_55 = const()[name = tensor<string, []>("op_55"), val = tensor<int32, []>(-1)];
            tensor<int32, [2]> var_67 = const()[name = tensor<string, []>("op_67"), val = tensor<int32, [2]>([1, 1])];
            tensor<fp16, [1, 1]> x_5_cast_fp16 = reshape(shape = var_67, x = x_1_cast_fp16)[name = tensor<string, []>("x_5_cast_fp16")];
            tensor<fp16, [1, 128]> var_75_to_fp16 = const()[name = tensor<string, []>("op_75_to_fp16"), val = tensor<fp16, [1, 128]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(64)))];
            tensor<fp16, [1, 128]> var_76_cast_fp16 = mul(x = x_5_cast_fp16, y = var_75_to_fp16)[name = tensor<string, []>("op_76_cast_fp16")];
            tensor<fp16, []> var_77_promoted_to_fp16 = const()[name = tensor<string, []>("op_77_promoted_to_fp16"), val = tensor<fp16, []>(0x1p+1)];
            tensor<fp16, [1, 128]> var_78_cast_fp16 = mul(x = var_76_cast_fp16, y = var_77_promoted_to_fp16)[name = tensor<string, []>("op_78_cast_fp16")];
            tensor<fp16, []> var_79_to_fp16 = const()[name = tensor<string, []>("op_79_to_fp16"), val = tensor<fp16, []>(0x1.92p+1)];
            tensor<fp16, [1, 128]> freqs_cast_fp16 = mul(x = var_78_cast_fp16, y = var_79_to_fp16)[name = tensor<string, []>("freqs_cast_fp16")];
            tensor<fp16, [1, 128]> var_81_cast_fp16 = sin(x = freqs_cast_fp16)[name = tensor<string, []>("op_81_cast_fp16")];
            tensor<fp16, [1, 128]> var_82_cast_fp16 = cos(x = freqs_cast_fp16)[name = tensor<string, []>("op_82_cast_fp16")];
            tensor<bool, []> input_1_interleave_0 = const()[name = tensor<string, []>("input_1_interleave_0"), val = tensor<bool, []>(false)];
            tensor<fp16, [1, 257]> input_1_cast_fp16 = concat(axis = var_55, interleave = input_1_interleave_0, values = (x_5_cast_fp16, var_81_cast_fp16, var_82_cast_fp16))[name = tensor<string, []>("input_1_cast_fp16")];
            tensor<fp16, [1024, 257]> transformer_to_time_0_1_weight_to_fp16 = const()[name = tensor<string, []>("transformer_to_time_0_1_weight_to_fp16"), val = tensor<fp16, [1024, 257]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(384)))];
            tensor<fp16, [1024]> transformer_to_time_0_1_bias_to_fp16 = const()[name = tensor<string, []>("transformer_to_time_0_1_bias_to_fp16"), val = tensor<fp16, [1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(526784)))];
            tensor<fp16, [1, 1024]> linear_0_cast_fp16 = linear(bias = transformer_to_time_0_1_bias_to_fp16, weight = transformer_to_time_0_1_weight_to_fp16, x = input_1_cast_fp16)[name = tensor<string, []>("linear_0_cast_fp16")];
            tensor<string, []> var_88_mode_0 = const()[name = tensor<string, []>("op_88_mode_0"), val = tensor<string, []>("EXACT")];
            tensor<fp16, [1, 1024]> var_88_cast_fp16 = gelu(mode = var_88_mode_0, x = linear_0_cast_fp16)[name = tensor<string, []>("op_88_cast_fp16")];
            tensor<string, []> features_to_fp16_dtype_0 = const()[name = tensor<string, []>("features_to_fp16_dtype_0"), val = tensor<string, []>("fp16")];
            tensor<fp16, [1024, 256]> transformer_to_features_0_weight_to_fp16 = const()[name = tensor<string, []>("transformer_to_features_0_weight_to_fp16"), val = tensor<fp16, [1024, 256]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(528896)))];
            tensor<fp16, [1024]> transformer_to_features_0_bias_to_fp16 = const()[name = tensor<string, []>("transformer_to_features_0_bias_to_fp16"), val = tensor<fp16, [1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(1053248)))];
            tensor<fp16, [1, 256]> features_to_fp16 = cast(dtype = features_to_fp16_dtype_0, x = features)[name = tensor<string, []>("cast_25")];
            tensor<fp16, [1, 1024]> linear_1_cast_fp16 = linear(bias = transformer_to_features_0_bias_to_fp16, weight = transformer_to_features_0_weight_to_fp16, x = features_to_fp16)[name = tensor<string, []>("linear_1_cast_fp16")];
            tensor<string, []> var_94_mode_0 = const()[name = tensor<string, []>("op_94_mode_0"), val = tensor<string, []>("EXACT")];
            tensor<fp16, [1, 1024]> var_94_cast_fp16 = gelu(mode = var_94_mode_0, x = linear_1_cast_fp16)[name = tensor<string, []>("op_94_cast_fp16")];
            tensor<int32, []> x_7_axis_0 = const()[name = tensor<string, []>("x_7_axis_0"), val = tensor<int32, []>(0)];
            tensor<fp16, [2, 1, 1024]> x_7_cast_fp16 = stack(axis = x_7_axis_0, values = (var_88_cast_fp16, var_94_cast_fp16))[name = tensor<string, []>("x_7_cast_fp16")];
            tensor<int32, [3]> var_101 = const()[name = tensor<string, []>("op_101"), val = tensor<int32, [3]>([1, 2, 0])];
            tensor<int32, [1]> input_7_axes_0 = const()[name = tensor<string, []>("input_7_axes_0"), val = tensor<int32, [1]>([2])];
            tensor<bool, []> input_7_keep_dims_0 = const()[name = tensor<string, []>("input_7_keep_dims_0"), val = tensor<bool, []>(false)];
            tensor<fp16, [1, 1024, 2]> x_9_cast_fp16 = transpose(perm = var_101, x = x_7_cast_fp16)[name = tensor<string, []>("transpose_41")];
            tensor<fp16, [1, 1024]> input_7_cast_fp16 = reduce_sum(axes = input_7_axes_0, keep_dims = input_7_keep_dims_0, x = x_9_cast_fp16)[name = tensor<string, []>("input_7_cast_fp16")];
            tensor<fp16, [1024, 1024]> transformer_to_mapping_0_weight_to_fp16 = const()[name = tensor<string, []>("transformer_to_mapping_0_weight_to_fp16"), val = tensor<fp16, [1024, 1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(1055360)))];
            tensor<fp16, [1024]> transformer_to_mapping_0_bias_to_fp16 = const()[name = tensor<string, []>("transformer_to_mapping_0_bias_to_fp16"), val = tensor<fp16, [1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(3152576)))];
            tensor<fp16, [1, 1024]> linear_2_cast_fp16 = linear(bias = transformer_to_mapping_0_bias_to_fp16, weight = transformer_to_mapping_0_weight_to_fp16, x = input_7_cast_fp16)[name = tensor<string, []>("linear_2_cast_fp16")];
            tensor<string, []> input_11_mode_0 = const()[name = tensor<string, []>("input_11_mode_0"), val = tensor<string, []>("EXACT")];
            tensor<fp16, [1, 1024]> input_11_cast_fp16 = gelu(mode = input_11_mode_0, x = linear_2_cast_fp16)[name = tensor<string, []>("input_11_cast_fp16")];
            tensor<fp16, [1024, 1024]> transformer_to_mapping_2_weight_to_fp16 = const()[name = tensor<string, []>("transformer_to_mapping_2_weight_to_fp16"), val = tensor<fp16, [1024, 1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(3154688)))];
            tensor<fp16, [1024]> transformer_to_mapping_2_bias_to_fp16 = const()[name = tensor<string, []>("transformer_to_mapping_2_bias_to_fp16"), val = tensor<fp16, [1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(5251904)))];
            tensor<fp16, [1, 1024]> linear_3_cast_fp16 = linear(bias = transformer_to_mapping_2_bias_to_fp16, weight = transformer_to_mapping_2_weight_to_fp16, x = input_11_cast_fp16)[name = tensor<string, []>("linear_3_cast_fp16")];
            tensor<string, []> mapping_1_mode_0 = const()[name = tensor<string, []>("mapping_1_mode_0"), val = tensor<string, []>("EXACT")];
            tensor<fp16, [1, 1024]> mapping_1_cast_fp16 = gelu(mode = mapping_1_mode_0, x = linear_3_cast_fp16)[name = tensor<string, []>("mapping_1_cast_fp16")];
            tensor<int32, [3]> var_127_reps_0 = const()[name = tensor<string, []>("op_127_reps_0"), val = tensor<int32, [3]>([1, 512, 1])];
            tensor<fp16, [1, 512, 256]> var_127_cast_fp16 = tile(reps = var_127_reps_0, x = x_11_cast_fp16)[name = tensor<string, []>("op_127_cast_fp16")];
            tensor<int32, []> var_129 = const()[name = tensor<string, []>("op_129"), val = tensor<int32, []>(-1)];
            tensor<bool, []> x_13_interleave_0 = const()[name = tensor<string, []>("x_13_interleave_0"), val = tensor<bool, []>(false)];
            tensor<string, []> embedding_to_fp16_dtype_0 = const()[name = tensor<string, []>("embedding_to_fp16_dtype_0"), val = tensor<string, []>("fp16")];
            tensor<fp16, [1, 512, 768]> embedding_to_fp16 = cast(dtype = embedding_to_fp16_dtype_0, x = embedding)[name = tensor<string, []>("cast_24")];
            tensor<fp16, [1, 512, 1024]> x_13_cast_fp16 = concat(axis = var_129, interleave = x_13_interleave_0, values = (var_127_cast_fp16, embedding_to_fp16))[name = tensor<string, []>("x_13_cast_fp16")];
            tensor<int32, [1]> var_132_axes_0 = const()[name = tensor<string, []>("op_132_axes_0"), val = tensor<int32, [1]>([1])];
            tensor<fp16, [1, 1, 1024]> var_132_cast_fp16 = expand_dims(axes = var_132_axes_0, x = mapping_1_cast_fp16)[name = tensor<string, []>("op_132_cast_fp16")];
            tensor<int32, [3]> mapping_reps_0 = const()[name = tensor<string, []>("mapping_reps_0"), val = tensor<int32, [3]>([1, 512, 1])];
            tensor<fp16, [1, 512, 1024]> mapping_cast_fp16 = tile(reps = mapping_reps_0, x = var_132_cast_fp16)[name = tensor<string, []>("mapping_cast_fp16")];
            tensor<fp16, [1, 512, 1024]> x_15_cast_fp16 = add(x = x_13_cast_fp16, y = mapping_cast_fp16)[name = tensor<string, []>("x_15_cast_fp16")];
            tensor<int32, []> var_153 = const()[name = tensor<string, []>("op_153"), val = tensor<int32, []>(-1)];
            tensor<fp16, [2048, 256]> transformer_blocks_0_attention_norm_fc_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_0_attention_norm_fc_weight_to_fp16"), val = tensor<fp16, [2048, 256]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(5254016)))];
            tensor<fp16, [2048]> transformer_blocks_0_attention_norm_fc_bias_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_0_attention_norm_fc_bias_to_fp16"), val = tensor<fp16, [2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(6302656)))];
            tensor<fp16, [1, 2048]> linear_4_cast_fp16 = linear(bias = transformer_blocks_0_attention_norm_fc_bias_to_fp16, weight = transformer_blocks_0_attention_norm_fc_weight_to_fp16, x = features_to_fp16)[name = tensor<string, []>("linear_4_cast_fp16")];
            tensor<int32, [3]> var_172 = const()[name = tensor<string, []>("op_172"), val = tensor<int32, [3]>([1, 2048, 1])];
            tensor<fp16, [1, 2048, 1]> h_3_cast_fp16 = reshape(shape = var_172, x = linear_4_cast_fp16)[name = tensor<string, []>("h_3_cast_fp16")];
            tensor<int32, [2]> var_174_split_sizes_0 = const()[name = tensor<string, []>("op_174_split_sizes_0"), val = tensor<int32, [2]>([1024, 1024])];
            tensor<int32, []> var_174_axis_0 = const()[name = tensor<string, []>("op_174_axis_0"), val = tensor<int32, []>(1)];
            tensor<fp16, [1, 1024, 1]> var_174_cast_fp16_0, tensor<fp16, [1, 1024, 1]> var_174_cast_fp16_1 = split(axis = var_174_axis_0, split_sizes = var_174_split_sizes_0, x = h_3_cast_fp16)[name = tensor<string, []>("op_174_cast_fp16")];
            tensor<int32, [3]> gamma_3_perm_0 = const()[name = tensor<string, []>("gamma_3_perm_0"), val = tensor<int32, [3]>([0, -1, 1])];
            tensor<int32, [3]> beta_3_perm_0 = const()[name = tensor<string, []>("beta_3_perm_0"), val = tensor<int32, [3]>([0, -1, 1])];
            tensor<int32, [1]> x_19_axes_0 = const()[name = tensor<string, []>("x_19_axes_0"), val = tensor<int32, [1]>([-1])];
            tensor<fp16, []> var_146_to_fp16 = const()[name = tensor<string, []>("op_146_to_fp16"), val = tensor<fp16, []>(0x1.5p-17)];
            tensor<fp16, [1, 512, 1024]> x_19_cast_fp16 = layer_norm(axes = x_19_axes_0, epsilon = var_146_to_fp16, x = x_15_cast_fp16)[name = tensor<string, []>("x_19_cast_fp16")];
            tensor<fp16, []> var_180_promoted_to_fp16 = const()[name = tensor<string, []>("op_180_promoted_to_fp16"), val = tensor<fp16, []>(0x1p+0)];
            tensor<fp16, [1, 1, 1024]> gamma_3_cast_fp16 = transpose(perm = gamma_3_perm_0, x = var_174_cast_fp16_0)[name = tensor<string, []>("transpose_40")];
            tensor<fp16, [1, 1, 1024]> var_181_cast_fp16 = add(x = gamma_3_cast_fp16, y = var_180_promoted_to_fp16)[name = tensor<string, []>("op_181_cast_fp16")];
            tensor<fp16, [1, 512, 1024]> var_182_cast_fp16 = mul(x = var_181_cast_fp16, y = x_19_cast_fp16)[name = tensor<string, []>("op_182_cast_fp16")];
            tensor<fp16, [1, 1, 1024]> beta_3_cast_fp16 = transpose(perm = beta_3_perm_0, x = var_174_cast_fp16_1)[name = tensor<string, []>("transpose_39")];
            tensor<fp16, [1, 512, 1024]> x_21_cast_fp16 = add(x = var_182_cast_fp16, y = beta_3_cast_fp16)[name = tensor<string, []>("x_21_cast_fp16")];
            tensor<fp16, [2048, 256]> transformer_blocks_0_attention_norm_context_fc_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_0_attention_norm_context_fc_weight_to_fp16"), val = tensor<fp16, [2048, 256]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(6306816)))];
            tensor<fp16, [2048]> transformer_blocks_0_attention_norm_context_fc_bias_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_0_attention_norm_context_fc_bias_to_fp16"), val = tensor<fp16, [2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(7355456)))];
            tensor<fp16, [1, 2048]> linear_5_cast_fp16 = linear(bias = transformer_blocks_0_attention_norm_context_fc_bias_to_fp16, weight = transformer_blocks_0_attention_norm_context_fc_weight_to_fp16, x = features_to_fp16)[name = tensor<string, []>("linear_5_cast_fp16")];
            tensor<int32, [3]> var_194 = const()[name = tensor<string, []>("op_194"), val = tensor<int32, [3]>([1, 2048, 1])];
            tensor<fp16, [1, 2048, 1]> h_7_cast_fp16 = reshape(shape = var_194, x = linear_5_cast_fp16)[name = tensor<string, []>("h_7_cast_fp16")];
            tensor<int32, [2]> var_196_split_sizes_0 = const()[name = tensor<string, []>("op_196_split_sizes_0"), val = tensor<int32, [2]>([1024, 1024])];
            tensor<int32, []> var_196_axis_0 = const()[name = tensor<string, []>("op_196_axis_0"), val = tensor<int32, []>(1)];
            tensor<fp16, [1, 1024, 1]> var_196_cast_fp16_0, tensor<fp16, [1, 1024, 1]> var_196_cast_fp16_1 = split(axis = var_196_axis_0, split_sizes = var_196_split_sizes_0, x = h_7_cast_fp16)[name = tensor<string, []>("op_196_cast_fp16")];
            tensor<int32, [3]> gamma_7_perm_0 = const()[name = tensor<string, []>("gamma_7_perm_0"), val = tensor<int32, [3]>([0, -1, 1])];
            tensor<int32, [3]> beta_7_perm_0 = const()[name = tensor<string, []>("beta_7_perm_0"), val = tensor<int32, [3]>([0, -1, 1])];
            tensor<fp16, []> var_202_promoted_to_fp16 = const()[name = tensor<string, []>("op_202_promoted_to_fp16"), val = tensor<fp16, []>(0x1p+0)];
            tensor<fp16, [1, 1, 1024]> gamma_7_cast_fp16 = transpose(perm = gamma_7_perm_0, x = var_196_cast_fp16_0)[name = tensor<string, []>("transpose_38")];
            tensor<fp16, [1, 1, 1024]> var_203_cast_fp16 = add(x = gamma_7_cast_fp16, y = var_202_promoted_to_fp16)[name = tensor<string, []>("op_203_cast_fp16")];
            tensor<fp16, [1, 512, 1024]> var_204_cast_fp16 = mul(x = var_203_cast_fp16, y = x_19_cast_fp16)[name = tensor<string, []>("op_204_cast_fp16")];
            tensor<fp16, [1, 1, 1024]> beta_7_cast_fp16 = transpose(perm = beta_7_perm_0, x = var_196_cast_fp16_1)[name = tensor<string, []>("transpose_37")];
            tensor<fp16, [1, 512, 1024]> x_27_cast_fp16 = add(x = var_204_cast_fp16, y = beta_7_cast_fp16)[name = tensor<string, []>("x_27_cast_fp16")];
            tensor<fp16, [512, 1024]> transformer_blocks_0_attention_to_q_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_0_attention_to_q_weight_to_fp16"), val = tensor<fp16, [512, 1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(7359616)))];
            tensor<fp16, [512]> linear_6_bias_0_to_fp16 = const()[name = tensor<string, []>("linear_6_bias_0_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(8408256)))];
            tensor<fp16, [1, 512, 512]> linear_6_cast_fp16 = linear(bias = linear_6_bias_0_to_fp16, weight = transformer_blocks_0_attention_to_q_weight_to_fp16, x = x_21_cast_fp16)[name = tensor<string, []>("linear_6_cast_fp16")];
            tensor<fp16, [1024, 1024]> transformer_blocks_0_attention_to_kv_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_0_attention_to_kv_weight_to_fp16"), val = tensor<fp16, [1024, 1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(8409344)))];
            tensor<fp16, [1024]> linear_7_bias_0_to_fp16 = const()[name = tensor<string, []>("linear_7_bias_0_to_fp16"), val = tensor<fp16, [1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(10506560)))];
            tensor<fp16, [1, 512, 1024]> linear_7_cast_fp16 = linear(bias = linear_7_bias_0_to_fp16, weight = transformer_blocks_0_attention_to_kv_weight_to_fp16, x = x_27_cast_fp16)[name = tensor<string, []>("linear_7_cast_fp16")];
            tensor<int32, [2]> var_212_split_sizes_0 = const()[name = tensor<string, []>("op_212_split_sizes_0"), val = tensor<int32, [2]>([512, 512])];
            tensor<int32, []> var_212_axis_0 = const()[name = tensor<string, []>("op_212_axis_0"), val = tensor<int32, []>(-1)];
            tensor<fp16, [1, 512, 512]> var_212_cast_fp16_0, tensor<fp16, [1, 512, 512]> var_212_cast_fp16_1 = split(axis = var_212_axis_0, split_sizes = var_212_split_sizes_0, x = linear_7_cast_fp16)[name = tensor<string, []>("op_212_cast_fp16")];
            tensor<int32, [4]> var_221 = const()[name = tensor<string, []>("op_221"), val = tensor<int32, [4]>([1, 512, 8, 64])];
            tensor<fp16, [1, 512, 8, 64]> x_31_cast_fp16 = reshape(shape = var_221, x = linear_6_cast_fp16)[name = tensor<string, []>("x_31_cast_fp16")];
            tensor<int32, [4]> var_231 = const()[name = tensor<string, []>("op_231"), val = tensor<int32, [4]>([1, 512, 8, 64])];
            tensor<fp16, [1, 512, 8, 64]> x_35_cast_fp16 = reshape(shape = var_231, x = var_212_cast_fp16_0)[name = tensor<string, []>("x_35_cast_fp16")];
            tensor<int32, [4]> var_241 = const()[name = tensor<string, []>("op_241"), val = tensor<int32, [4]>([1, 512, 8, 64])];
            tensor<fp16, [1, 512, 8, 64]> x_39_cast_fp16 = reshape(shape = var_241, x = var_212_cast_fp16_1)[name = tensor<string, []>("x_39_cast_fp16")];
            tensor<int32, [4]> var_243 = const()[name = tensor<string, []>("op_243"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<bool, []> sim_1_transpose_x_0 = const()[name = tensor<string, []>("sim_1_transpose_x_0"), val = tensor<bool, []>(false)];
            tensor<bool, []> sim_1_transpose_y_0 = const()[name = tensor<string, []>("sim_1_transpose_y_0"), val = tensor<bool, []>(false)];
            tensor<int32, [4]> transpose_9_perm_0 = const()[name = tensor<string, []>("transpose_9_perm_0"), val = tensor<int32, [4]>([0, 2, -3, -1])];
            tensor<int32, [4]> transpose_10_perm_0 = const()[name = tensor<string, []>("transpose_10_perm_0"), val = tensor<int32, [4]>([0, 2, -1, -3])];
            tensor<fp16, [1, 8, 64, 512]> transpose_10 = transpose(perm = transpose_10_perm_0, x = x_35_cast_fp16)[name = tensor<string, []>("transpose_34")];
            tensor<fp16, [1, 8, 512, 64]> transpose_9 = transpose(perm = transpose_9_perm_0, x = x_31_cast_fp16)[name = tensor<string, []>("transpose_35")];
            tensor<fp16, [1, 8, 512, 512]> sim_1_cast_fp16 = matmul(transpose_x = sim_1_transpose_x_0, transpose_y = sim_1_transpose_y_0, x = transpose_9, y = transpose_10)[name = tensor<string, []>("sim_1_cast_fp16")];
            tensor<fp16, []> var_247_to_fp16 = const()[name = tensor<string, []>("op_247_to_fp16"), val = tensor<fp16, []>(0x1p-3)];
            tensor<fp16, [1, 8, 512, 512]> sim_3_cast_fp16 = mul(x = sim_1_cast_fp16, y = var_247_to_fp16)[name = tensor<string, []>("sim_3_cast_fp16")];
            tensor<fp16, [1, 8, 512, 512]> attn_1_cast_fp16 = softmax(axis = var_153, x = sim_3_cast_fp16)[name = tensor<string, []>("attn_1_cast_fp16")];
            tensor<bool, []> x_41_transpose_x_0 = const()[name = tensor<string, []>("x_41_transpose_x_0"), val = tensor<bool, []>(false)];
            tensor<bool, []> x_41_transpose_y_0 = const()[name = tensor<string, []>("x_41_transpose_y_0"), val = tensor<bool, []>(false)];
            tensor<fp16, [1, 8, 512, 64]> v_1_cast_fp16 = transpose(perm = var_243, x = x_39_cast_fp16)[name = tensor<string, []>("transpose_36")];
            tensor<fp16, [1, 8, 512, 64]> x_41_cast_fp16 = matmul(transpose_x = x_41_transpose_x_0, transpose_y = x_41_transpose_y_0, x = attn_1_cast_fp16, y = v_1_cast_fp16)[name = tensor<string, []>("x_41_cast_fp16")];
            tensor<int32, [4]> var_269 = const()[name = tensor<string, []>("op_269"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<int32, [3]> var_271 = const()[name = tensor<string, []>("op_271"), val = tensor<int32, [3]>([1, 512, 512])];
            tensor<fp16, [1, 512, 8, 64]> x_43_cast_fp16 = transpose(perm = var_269, x = x_41_cast_fp16)[name = tensor<string, []>("transpose_33")];
            tensor<fp16, [1, 512, 512]> input_23_cast_fp16 = reshape(shape = var_271, x = x_43_cast_fp16)[name = tensor<string, []>("input_23_cast_fp16")];
            tensor<fp16, [1024, 512]> transformer_blocks_0_attention_attention_to_out_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_0_attention_attention_to_out_weight_to_fp16"), val = tensor<fp16, [1024, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(10508672)))];
            tensor<fp16, [1024]> transformer_blocks_0_attention_attention_to_out_bias_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_0_attention_attention_to_out_bias_to_fp16"), val = tensor<fp16, [1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(11557312)))];
            tensor<fp16, [1, 512, 1024]> linear_8_cast_fp16 = linear(bias = transformer_blocks_0_attention_attention_to_out_bias_to_fp16, weight = transformer_blocks_0_attention_attention_to_out_weight_to_fp16, x = input_23_cast_fp16)[name = tensor<string, []>("linear_8_cast_fp16")];
            tensor<fp16, [1, 512, 1024]> input_25_cast_fp16 = add(x = linear_8_cast_fp16, y = x_15_cast_fp16)[name = tensor<string, []>("input_25_cast_fp16")];
            tensor<fp16, [2048, 1024]> transformer_blocks_0_feed_forward_0_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_0_feed_forward_0_weight_to_fp16"), val = tensor<fp16, [2048, 1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(11559424)))];
            tensor<fp16, [2048]> transformer_blocks_0_feed_forward_0_bias_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_0_feed_forward_0_bias_to_fp16"), val = tensor<fp16, [2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(15753792)))];
            tensor<fp16, [1, 512, 2048]> linear_9_cast_fp16 = linear(bias = transformer_blocks_0_feed_forward_0_bias_to_fp16, weight = transformer_blocks_0_feed_forward_0_weight_to_fp16, x = input_25_cast_fp16)[name = tensor<string, []>("linear_9_cast_fp16")];
            tensor<string, []> input_29_mode_0 = const()[name = tensor<string, []>("input_29_mode_0"), val = tensor<string, []>("EXACT")];
            tensor<fp16, [1, 512, 2048]> input_29_cast_fp16 = gelu(mode = input_29_mode_0, x = linear_9_cast_fp16)[name = tensor<string, []>("input_29_cast_fp16")];
            tensor<fp16, [1024, 2048]> transformer_blocks_0_feed_forward_2_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_0_feed_forward_2_weight_to_fp16"), val = tensor<fp16, [1024, 2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(15757952)))];
            tensor<fp16, [1024]> transformer_blocks_0_feed_forward_2_bias_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_0_feed_forward_2_bias_to_fp16"), val = tensor<fp16, [1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(19952320)))];
            tensor<fp16, [1, 512, 1024]> linear_10_cast_fp16 = linear(bias = transformer_blocks_0_feed_forward_2_bias_to_fp16, weight = transformer_blocks_0_feed_forward_2_weight_to_fp16, x = input_29_cast_fp16)[name = tensor<string, []>("linear_10_cast_fp16")];
            tensor<fp16, [1, 512, 1024]> x_45_cast_fp16 = add(x = linear_10_cast_fp16, y = input_25_cast_fp16)[name = tensor<string, []>("x_45_cast_fp16")];
            tensor<fp16, [1, 512, 1024]> x_47_cast_fp16 = add(x = x_45_cast_fp16, y = mapping_cast_fp16)[name = tensor<string, []>("x_47_cast_fp16")];
            tensor<int32, []> var_298 = const()[name = tensor<string, []>("op_298"), val = tensor<int32, []>(-1)];
            tensor<fp16, [2048, 256]> transformer_blocks_1_attention_norm_fc_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_1_attention_norm_fc_weight_to_fp16"), val = tensor<fp16, [2048, 256]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(19954432)))];
            tensor<fp16, [2048]> transformer_blocks_1_attention_norm_fc_bias_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_1_attention_norm_fc_bias_to_fp16"), val = tensor<fp16, [2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(21003072)))];
            tensor<fp16, [1, 2048]> linear_11_cast_fp16 = linear(bias = transformer_blocks_1_attention_norm_fc_bias_to_fp16, weight = transformer_blocks_1_attention_norm_fc_weight_to_fp16, x = features_to_fp16)[name = tensor<string, []>("linear_11_cast_fp16")];
            tensor<int32, [3]> var_317 = const()[name = tensor<string, []>("op_317"), val = tensor<int32, [3]>([1, 2048, 1])];
            tensor<fp16, [1, 2048, 1]> h_11_cast_fp16 = reshape(shape = var_317, x = linear_11_cast_fp16)[name = tensor<string, []>("h_11_cast_fp16")];
            tensor<int32, [2]> var_319_split_sizes_0 = const()[name = tensor<string, []>("op_319_split_sizes_0"), val = tensor<int32, [2]>([1024, 1024])];
            tensor<int32, []> var_319_axis_0 = const()[name = tensor<string, []>("op_319_axis_0"), val = tensor<int32, []>(1)];
            tensor<fp16, [1, 1024, 1]> var_319_cast_fp16_0, tensor<fp16, [1, 1024, 1]> var_319_cast_fp16_1 = split(axis = var_319_axis_0, split_sizes = var_319_split_sizes_0, x = h_11_cast_fp16)[name = tensor<string, []>("op_319_cast_fp16")];
            tensor<int32, [3]> gamma_11_perm_0 = const()[name = tensor<string, []>("gamma_11_perm_0"), val = tensor<int32, [3]>([0, -1, 1])];
            tensor<int32, [3]> beta_11_perm_0 = const()[name = tensor<string, []>("beta_11_perm_0"), val = tensor<int32, [3]>([0, -1, 1])];
            tensor<int32, [1]> x_51_axes_0 = const()[name = tensor<string, []>("x_51_axes_0"), val = tensor<int32, [1]>([-1])];
            tensor<fp16, []> var_291_to_fp16 = const()[name = tensor<string, []>("op_291_to_fp16"), val = tensor<fp16, []>(0x1.5p-17)];
            tensor<fp16, [1, 512, 1024]> x_51_cast_fp16 = layer_norm(axes = x_51_axes_0, epsilon = var_291_to_fp16, x = x_47_cast_fp16)[name = tensor<string, []>("x_51_cast_fp16")];
            tensor<fp16, []> var_325_promoted_to_fp16 = const()[name = tensor<string, []>("op_325_promoted_to_fp16"), val = tensor<fp16, []>(0x1p+0)];
            tensor<fp16, [1, 1, 1024]> gamma_11_cast_fp16 = transpose(perm = gamma_11_perm_0, x = var_319_cast_fp16_0)[name = tensor<string, []>("transpose_32")];
            tensor<fp16, [1, 1, 1024]> var_326_cast_fp16 = add(x = gamma_11_cast_fp16, y = var_325_promoted_to_fp16)[name = tensor<string, []>("op_326_cast_fp16")];
            tensor<fp16, [1, 512, 1024]> var_327_cast_fp16 = mul(x = var_326_cast_fp16, y = x_51_cast_fp16)[name = tensor<string, []>("op_327_cast_fp16")];
            tensor<fp16, [1, 1, 1024]> beta_11_cast_fp16 = transpose(perm = beta_11_perm_0, x = var_319_cast_fp16_1)[name = tensor<string, []>("transpose_31")];
            tensor<fp16, [1, 512, 1024]> x_53_cast_fp16 = add(x = var_327_cast_fp16, y = beta_11_cast_fp16)[name = tensor<string, []>("x_53_cast_fp16")];
            tensor<fp16, [2048, 256]> transformer_blocks_1_attention_norm_context_fc_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_1_attention_norm_context_fc_weight_to_fp16"), val = tensor<fp16, [2048, 256]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(21007232)))];
            tensor<fp16, [2048]> transformer_blocks_1_attention_norm_context_fc_bias_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_1_attention_norm_context_fc_bias_to_fp16"), val = tensor<fp16, [2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(22055872)))];
            tensor<fp16, [1, 2048]> linear_12_cast_fp16 = linear(bias = transformer_blocks_1_attention_norm_context_fc_bias_to_fp16, weight = transformer_blocks_1_attention_norm_context_fc_weight_to_fp16, x = features_to_fp16)[name = tensor<string, []>("linear_12_cast_fp16")];
            tensor<int32, [3]> var_339 = const()[name = tensor<string, []>("op_339"), val = tensor<int32, [3]>([1, 2048, 1])];
            tensor<fp16, [1, 2048, 1]> h_15_cast_fp16 = reshape(shape = var_339, x = linear_12_cast_fp16)[name = tensor<string, []>("h_15_cast_fp16")];
            tensor<int32, [2]> var_341_split_sizes_0 = const()[name = tensor<string, []>("op_341_split_sizes_0"), val = tensor<int32, [2]>([1024, 1024])];
            tensor<int32, []> var_341_axis_0 = const()[name = tensor<string, []>("op_341_axis_0"), val = tensor<int32, []>(1)];
            tensor<fp16, [1, 1024, 1]> var_341_cast_fp16_0, tensor<fp16, [1, 1024, 1]> var_341_cast_fp16_1 = split(axis = var_341_axis_0, split_sizes = var_341_split_sizes_0, x = h_15_cast_fp16)[name = tensor<string, []>("op_341_cast_fp16")];
            tensor<int32, [3]> gamma_15_perm_0 = const()[name = tensor<string, []>("gamma_15_perm_0"), val = tensor<int32, [3]>([0, -1, 1])];
            tensor<int32, [3]> beta_15_perm_0 = const()[name = tensor<string, []>("beta_15_perm_0"), val = tensor<int32, [3]>([0, -1, 1])];
            tensor<fp16, []> var_347_promoted_to_fp16 = const()[name = tensor<string, []>("op_347_promoted_to_fp16"), val = tensor<fp16, []>(0x1p+0)];
            tensor<fp16, [1, 1, 1024]> gamma_15_cast_fp16 = transpose(perm = gamma_15_perm_0, x = var_341_cast_fp16_0)[name = tensor<string, []>("transpose_30")];
            tensor<fp16, [1, 1, 1024]> var_348_cast_fp16 = add(x = gamma_15_cast_fp16, y = var_347_promoted_to_fp16)[name = tensor<string, []>("op_348_cast_fp16")];
            tensor<fp16, [1, 512, 1024]> var_349_cast_fp16 = mul(x = var_348_cast_fp16, y = x_51_cast_fp16)[name = tensor<string, []>("op_349_cast_fp16")];
            tensor<fp16, [1, 1, 1024]> beta_15_cast_fp16 = transpose(perm = beta_15_perm_0, x = var_341_cast_fp16_1)[name = tensor<string, []>("transpose_29")];
            tensor<fp16, [1, 512, 1024]> x_59_cast_fp16 = add(x = var_349_cast_fp16, y = beta_15_cast_fp16)[name = tensor<string, []>("x_59_cast_fp16")];
            tensor<fp16, [512, 1024]> transformer_blocks_1_attention_to_q_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_1_attention_to_q_weight_to_fp16"), val = tensor<fp16, [512, 1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(22060032)))];
            tensor<fp16, [1, 512, 512]> linear_13_cast_fp16 = linear(bias = linear_6_bias_0_to_fp16, weight = transformer_blocks_1_attention_to_q_weight_to_fp16, x = x_53_cast_fp16)[name = tensor<string, []>("linear_13_cast_fp16")];
            tensor<fp16, [1024, 1024]> transformer_blocks_1_attention_to_kv_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_1_attention_to_kv_weight_to_fp16"), val = tensor<fp16, [1024, 1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(23108672)))];
            tensor<fp16, [1, 512, 1024]> linear_14_cast_fp16 = linear(bias = linear_7_bias_0_to_fp16, weight = transformer_blocks_1_attention_to_kv_weight_to_fp16, x = x_59_cast_fp16)[name = tensor<string, []>("linear_14_cast_fp16")];
            tensor<int32, [2]> var_357_split_sizes_0 = const()[name = tensor<string, []>("op_357_split_sizes_0"), val = tensor<int32, [2]>([512, 512])];
            tensor<int32, []> var_357_axis_0 = const()[name = tensor<string, []>("op_357_axis_0"), val = tensor<int32, []>(-1)];
            tensor<fp16, [1, 512, 512]> var_357_cast_fp16_0, tensor<fp16, [1, 512, 512]> var_357_cast_fp16_1 = split(axis = var_357_axis_0, split_sizes = var_357_split_sizes_0, x = linear_14_cast_fp16)[name = tensor<string, []>("op_357_cast_fp16")];
            tensor<int32, [4]> var_366 = const()[name = tensor<string, []>("op_366"), val = tensor<int32, [4]>([1, 512, 8, 64])];
            tensor<fp16, [1, 512, 8, 64]> x_63_cast_fp16 = reshape(shape = var_366, x = linear_13_cast_fp16)[name = tensor<string, []>("x_63_cast_fp16")];
            tensor<int32, [4]> var_376 = const()[name = tensor<string, []>("op_376"), val = tensor<int32, [4]>([1, 512, 8, 64])];
            tensor<fp16, [1, 512, 8, 64]> x_67_cast_fp16 = reshape(shape = var_376, x = var_357_cast_fp16_0)[name = tensor<string, []>("x_67_cast_fp16")];
            tensor<int32, [4]> var_386 = const()[name = tensor<string, []>("op_386"), val = tensor<int32, [4]>([1, 512, 8, 64])];
            tensor<fp16, [1, 512, 8, 64]> x_71_cast_fp16 = reshape(shape = var_386, x = var_357_cast_fp16_1)[name = tensor<string, []>("x_71_cast_fp16")];
            tensor<int32, [4]> var_388 = const()[name = tensor<string, []>("op_388"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<bool, []> sim_5_transpose_x_0 = const()[name = tensor<string, []>("sim_5_transpose_x_0"), val = tensor<bool, []>(false)];
            tensor<bool, []> sim_5_transpose_y_0 = const()[name = tensor<string, []>("sim_5_transpose_y_0"), val = tensor<bool, []>(false)];
            tensor<int32, [4]> transpose_11_perm_0 = const()[name = tensor<string, []>("transpose_11_perm_0"), val = tensor<int32, [4]>([0, 2, -3, -1])];
            tensor<int32, [4]> transpose_12_perm_0 = const()[name = tensor<string, []>("transpose_12_perm_0"), val = tensor<int32, [4]>([0, 2, -1, -3])];
            tensor<fp16, [1, 8, 64, 512]> transpose_12 = transpose(perm = transpose_12_perm_0, x = x_67_cast_fp16)[name = tensor<string, []>("transpose_26")];
            tensor<fp16, [1, 8, 512, 64]> transpose_11 = transpose(perm = transpose_11_perm_0, x = x_63_cast_fp16)[name = tensor<string, []>("transpose_27")];
            tensor<fp16, [1, 8, 512, 512]> sim_5_cast_fp16 = matmul(transpose_x = sim_5_transpose_x_0, transpose_y = sim_5_transpose_y_0, x = transpose_11, y = transpose_12)[name = tensor<string, []>("sim_5_cast_fp16")];
            tensor<fp16, []> var_392_to_fp16 = const()[name = tensor<string, []>("op_392_to_fp16"), val = tensor<fp16, []>(0x1p-3)];
            tensor<fp16, [1, 8, 512, 512]> sim_7_cast_fp16 = mul(x = sim_5_cast_fp16, y = var_392_to_fp16)[name = tensor<string, []>("sim_7_cast_fp16")];
            tensor<fp16, [1, 8, 512, 512]> attn_3_cast_fp16 = softmax(axis = var_298, x = sim_7_cast_fp16)[name = tensor<string, []>("attn_3_cast_fp16")];
            tensor<bool, []> x_73_transpose_x_0 = const()[name = tensor<string, []>("x_73_transpose_x_0"), val = tensor<bool, []>(false)];
            tensor<bool, []> x_73_transpose_y_0 = const()[name = tensor<string, []>("x_73_transpose_y_0"), val = tensor<bool, []>(false)];
            tensor<fp16, [1, 8, 512, 64]> v_3_cast_fp16 = transpose(perm = var_388, x = x_71_cast_fp16)[name = tensor<string, []>("transpose_28")];
            tensor<fp16, [1, 8, 512, 64]> x_73_cast_fp16 = matmul(transpose_x = x_73_transpose_x_0, transpose_y = x_73_transpose_y_0, x = attn_3_cast_fp16, y = v_3_cast_fp16)[name = tensor<string, []>("x_73_cast_fp16")];
            tensor<int32, [4]> var_414 = const()[name = tensor<string, []>("op_414"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<int32, [3]> var_416 = const()[name = tensor<string, []>("op_416"), val = tensor<int32, [3]>([1, 512, 512])];
            tensor<fp16, [1, 512, 8, 64]> x_75_cast_fp16 = transpose(perm = var_414, x = x_73_cast_fp16)[name = tensor<string, []>("transpose_25")];
            tensor<fp16, [1, 512, 512]> input_39_cast_fp16 = reshape(shape = var_416, x = x_75_cast_fp16)[name = tensor<string, []>("input_39_cast_fp16")];
            tensor<fp16, [1024, 512]> transformer_blocks_1_attention_attention_to_out_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_1_attention_attention_to_out_weight_to_fp16"), val = tensor<fp16, [1024, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(25205888)))];
            tensor<fp16, [1024]> transformer_blocks_1_attention_attention_to_out_bias_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_1_attention_attention_to_out_bias_to_fp16"), val = tensor<fp16, [1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(26254528)))];
            tensor<fp16, [1, 512, 1024]> linear_15_cast_fp16 = linear(bias = transformer_blocks_1_attention_attention_to_out_bias_to_fp16, weight = transformer_blocks_1_attention_attention_to_out_weight_to_fp16, x = input_39_cast_fp16)[name = tensor<string, []>("linear_15_cast_fp16")];
            tensor<fp16, [1, 512, 1024]> input_41_cast_fp16 = add(x = linear_15_cast_fp16, y = x_47_cast_fp16)[name = tensor<string, []>("input_41_cast_fp16")];
            tensor<fp16, [2048, 1024]> transformer_blocks_1_feed_forward_0_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_1_feed_forward_0_weight_to_fp16"), val = tensor<fp16, [2048, 1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(26256640)))];
            tensor<fp16, [2048]> transformer_blocks_1_feed_forward_0_bias_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_1_feed_forward_0_bias_to_fp16"), val = tensor<fp16, [2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(30451008)))];
            tensor<fp16, [1, 512, 2048]> linear_16_cast_fp16 = linear(bias = transformer_blocks_1_feed_forward_0_bias_to_fp16, weight = transformer_blocks_1_feed_forward_0_weight_to_fp16, x = input_41_cast_fp16)[name = tensor<string, []>("linear_16_cast_fp16")];
            tensor<string, []> input_45_mode_0 = const()[name = tensor<string, []>("input_45_mode_0"), val = tensor<string, []>("EXACT")];
            tensor<fp16, [1, 512, 2048]> input_45_cast_fp16 = gelu(mode = input_45_mode_0, x = linear_16_cast_fp16)[name = tensor<string, []>("input_45_cast_fp16")];
            tensor<fp16, [1024, 2048]> transformer_blocks_1_feed_forward_2_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_1_feed_forward_2_weight_to_fp16"), val = tensor<fp16, [1024, 2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(30455168)))];
            tensor<fp16, [1024]> transformer_blocks_1_feed_forward_2_bias_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_1_feed_forward_2_bias_to_fp16"), val = tensor<fp16, [1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(34649536)))];
            tensor<fp16, [1, 512, 1024]> linear_17_cast_fp16 = linear(bias = transformer_blocks_1_feed_forward_2_bias_to_fp16, weight = transformer_blocks_1_feed_forward_2_weight_to_fp16, x = input_45_cast_fp16)[name = tensor<string, []>("linear_17_cast_fp16")];
            tensor<fp16, [1, 512, 1024]> x_77_cast_fp16 = add(x = linear_17_cast_fp16, y = input_41_cast_fp16)[name = tensor<string, []>("x_77_cast_fp16")];
            tensor<fp16, [1, 512, 1024]> x_79_cast_fp16 = add(x = x_77_cast_fp16, y = mapping_cast_fp16)[name = tensor<string, []>("x_79_cast_fp16")];
            tensor<int32, []> var_443 = const()[name = tensor<string, []>("op_443"), val = tensor<int32, []>(-1)];
            tensor<fp16, [2048, 256]> transformer_blocks_2_attention_norm_fc_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_2_attention_norm_fc_weight_to_fp16"), val = tensor<fp16, [2048, 256]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(34651648)))];
            tensor<fp16, [2048]> transformer_blocks_2_attention_norm_fc_bias_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_2_attention_norm_fc_bias_to_fp16"), val = tensor<fp16, [2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(35700288)))];
            tensor<fp16, [1, 2048]> linear_18_cast_fp16 = linear(bias = transformer_blocks_2_attention_norm_fc_bias_to_fp16, weight = transformer_blocks_2_attention_norm_fc_weight_to_fp16, x = features_to_fp16)[name = tensor<string, []>("linear_18_cast_fp16")];
            tensor<int32, [3]> var_462 = const()[name = tensor<string, []>("op_462"), val = tensor<int32, [3]>([1, 2048, 1])];
            tensor<fp16, [1, 2048, 1]> h_19_cast_fp16 = reshape(shape = var_462, x = linear_18_cast_fp16)[name = tensor<string, []>("h_19_cast_fp16")];
            tensor<int32, [2]> var_464_split_sizes_0 = const()[name = tensor<string, []>("op_464_split_sizes_0"), val = tensor<int32, [2]>([1024, 1024])];
            tensor<int32, []> var_464_axis_0 = const()[name = tensor<string, []>("op_464_axis_0"), val = tensor<int32, []>(1)];
            tensor<fp16, [1, 1024, 1]> var_464_cast_fp16_0, tensor<fp16, [1, 1024, 1]> var_464_cast_fp16_1 = split(axis = var_464_axis_0, split_sizes = var_464_split_sizes_0, x = h_19_cast_fp16)[name = tensor<string, []>("op_464_cast_fp16")];
            tensor<int32, [3]> gamma_19_perm_0 = const()[name = tensor<string, []>("gamma_19_perm_0"), val = tensor<int32, [3]>([0, -1, 1])];
            tensor<int32, [3]> beta_19_perm_0 = const()[name = tensor<string, []>("beta_19_perm_0"), val = tensor<int32, [3]>([0, -1, 1])];
            tensor<int32, [1]> x_83_axes_0 = const()[name = tensor<string, []>("x_83_axes_0"), val = tensor<int32, [1]>([-1])];
            tensor<fp16, []> var_436_to_fp16 = const()[name = tensor<string, []>("op_436_to_fp16"), val = tensor<fp16, []>(0x1.5p-17)];
            tensor<fp16, [1, 512, 1024]> x_83_cast_fp16 = layer_norm(axes = x_83_axes_0, epsilon = var_436_to_fp16, x = x_79_cast_fp16)[name = tensor<string, []>("x_83_cast_fp16")];
            tensor<fp16, []> var_470_promoted_to_fp16 = const()[name = tensor<string, []>("op_470_promoted_to_fp16"), val = tensor<fp16, []>(0x1p+0)];
            tensor<fp16, [1, 1, 1024]> gamma_19_cast_fp16 = transpose(perm = gamma_19_perm_0, x = var_464_cast_fp16_0)[name = tensor<string, []>("transpose_24")];
            tensor<fp16, [1, 1, 1024]> var_471_cast_fp16 = add(x = gamma_19_cast_fp16, y = var_470_promoted_to_fp16)[name = tensor<string, []>("op_471_cast_fp16")];
            tensor<fp16, [1, 512, 1024]> var_472_cast_fp16 = mul(x = var_471_cast_fp16, y = x_83_cast_fp16)[name = tensor<string, []>("op_472_cast_fp16")];
            tensor<fp16, [1, 1, 1024]> beta_19_cast_fp16 = transpose(perm = beta_19_perm_0, x = var_464_cast_fp16_1)[name = tensor<string, []>("transpose_23")];
            tensor<fp16, [1, 512, 1024]> x_85_cast_fp16 = add(x = var_472_cast_fp16, y = beta_19_cast_fp16)[name = tensor<string, []>("x_85_cast_fp16")];
            tensor<fp16, [2048, 256]> transformer_blocks_2_attention_norm_context_fc_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_2_attention_norm_context_fc_weight_to_fp16"), val = tensor<fp16, [2048, 256]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(35704448)))];
            tensor<fp16, [2048]> transformer_blocks_2_attention_norm_context_fc_bias_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_2_attention_norm_context_fc_bias_to_fp16"), val = tensor<fp16, [2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(36753088)))];
            tensor<fp16, [1, 2048]> linear_19_cast_fp16 = linear(bias = transformer_blocks_2_attention_norm_context_fc_bias_to_fp16, weight = transformer_blocks_2_attention_norm_context_fc_weight_to_fp16, x = features_to_fp16)[name = tensor<string, []>("linear_19_cast_fp16")];
            tensor<int32, [3]> var_484 = const()[name = tensor<string, []>("op_484"), val = tensor<int32, [3]>([1, 2048, 1])];
            tensor<fp16, [1, 2048, 1]> h_cast_fp16 = reshape(shape = var_484, x = linear_19_cast_fp16)[name = tensor<string, []>("h_cast_fp16")];
            tensor<int32, [2]> var_486_split_sizes_0 = const()[name = tensor<string, []>("op_486_split_sizes_0"), val = tensor<int32, [2]>([1024, 1024])];
            tensor<int32, []> var_486_axis_0 = const()[name = tensor<string, []>("op_486_axis_0"), val = tensor<int32, []>(1)];
            tensor<fp16, [1, 1024, 1]> var_486_cast_fp16_0, tensor<fp16, [1, 1024, 1]> var_486_cast_fp16_1 = split(axis = var_486_axis_0, split_sizes = var_486_split_sizes_0, x = h_cast_fp16)[name = tensor<string, []>("op_486_cast_fp16")];
            tensor<int32, [3]> gamma_perm_0 = const()[name = tensor<string, []>("gamma_perm_0"), val = tensor<int32, [3]>([0, -1, 1])];
            tensor<int32, [3]> beta_perm_0 = const()[name = tensor<string, []>("beta_perm_0"), val = tensor<int32, [3]>([0, -1, 1])];
            tensor<fp16, []> var_492_promoted_to_fp16 = const()[name = tensor<string, []>("op_492_promoted_to_fp16"), val = tensor<fp16, []>(0x1p+0)];
            tensor<fp16, [1, 1, 1024]> gamma_cast_fp16 = transpose(perm = gamma_perm_0, x = var_486_cast_fp16_0)[name = tensor<string, []>("transpose_22")];
            tensor<fp16, [1, 1, 1024]> var_493_cast_fp16 = add(x = gamma_cast_fp16, y = var_492_promoted_to_fp16)[name = tensor<string, []>("op_493_cast_fp16")];
            tensor<fp16, [1, 512, 1024]> var_494_cast_fp16 = mul(x = var_493_cast_fp16, y = x_83_cast_fp16)[name = tensor<string, []>("op_494_cast_fp16")];
            tensor<fp16, [1, 1, 1024]> beta_cast_fp16 = transpose(perm = beta_perm_0, x = var_486_cast_fp16_1)[name = tensor<string, []>("transpose_21")];
            tensor<fp16, [1, 512, 1024]> x_91_cast_fp16 = add(x = var_494_cast_fp16, y = beta_cast_fp16)[name = tensor<string, []>("x_91_cast_fp16")];
            tensor<fp16, [512, 1024]> transformer_blocks_2_attention_to_q_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_2_attention_to_q_weight_to_fp16"), val = tensor<fp16, [512, 1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(36757248)))];
            tensor<fp16, [1, 512, 512]> linear_20_cast_fp16 = linear(bias = linear_6_bias_0_to_fp16, weight = transformer_blocks_2_attention_to_q_weight_to_fp16, x = x_85_cast_fp16)[name = tensor<string, []>("linear_20_cast_fp16")];
            tensor<fp16, [1024, 1024]> transformer_blocks_2_attention_to_kv_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_2_attention_to_kv_weight_to_fp16"), val = tensor<fp16, [1024, 1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(37805888)))];
            tensor<fp16, [1, 512, 1024]> linear_21_cast_fp16 = linear(bias = linear_7_bias_0_to_fp16, weight = transformer_blocks_2_attention_to_kv_weight_to_fp16, x = x_91_cast_fp16)[name = tensor<string, []>("linear_21_cast_fp16")];
            tensor<int32, [2]> var_502_split_sizes_0 = const()[name = tensor<string, []>("op_502_split_sizes_0"), val = tensor<int32, [2]>([512, 512])];
            tensor<int32, []> var_502_axis_0 = const()[name = tensor<string, []>("op_502_axis_0"), val = tensor<int32, []>(-1)];
            tensor<fp16, [1, 512, 512]> var_502_cast_fp16_0, tensor<fp16, [1, 512, 512]> var_502_cast_fp16_1 = split(axis = var_502_axis_0, split_sizes = var_502_split_sizes_0, x = linear_21_cast_fp16)[name = tensor<string, []>("op_502_cast_fp16")];
            tensor<int32, [4]> var_511 = const()[name = tensor<string, []>("op_511"), val = tensor<int32, [4]>([1, 512, 8, 64])];
            tensor<fp16, [1, 512, 8, 64]> x_95_cast_fp16 = reshape(shape = var_511, x = linear_20_cast_fp16)[name = tensor<string, []>("x_95_cast_fp16")];
            tensor<int32, [4]> var_521 = const()[name = tensor<string, []>("op_521"), val = tensor<int32, [4]>([1, 512, 8, 64])];
            tensor<fp16, [1, 512, 8, 64]> x_99_cast_fp16 = reshape(shape = var_521, x = var_502_cast_fp16_0)[name = tensor<string, []>("x_99_cast_fp16")];
            tensor<int32, [4]> var_531 = const()[name = tensor<string, []>("op_531"), val = tensor<int32, [4]>([1, 512, 8, 64])];
            tensor<fp16, [1, 512, 8, 64]> x_103_cast_fp16 = reshape(shape = var_531, x = var_502_cast_fp16_1)[name = tensor<string, []>("x_103_cast_fp16")];
            tensor<int32, [4]> var_533 = const()[name = tensor<string, []>("op_533"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<bool, []> sim_9_transpose_x_0 = const()[name = tensor<string, []>("sim_9_transpose_x_0"), val = tensor<bool, []>(false)];
            tensor<bool, []> sim_9_transpose_y_0 = const()[name = tensor<string, []>("sim_9_transpose_y_0"), val = tensor<bool, []>(false)];
            tensor<int32, [4]> transpose_13_perm_0 = const()[name = tensor<string, []>("transpose_13_perm_0"), val = tensor<int32, [4]>([0, 2, -3, -1])];
            tensor<int32, [4]> transpose_14_perm_0 = const()[name = tensor<string, []>("transpose_14_perm_0"), val = tensor<int32, [4]>([0, 2, -1, -3])];
            tensor<fp16, [1, 8, 64, 512]> transpose_14 = transpose(perm = transpose_14_perm_0, x = x_99_cast_fp16)[name = tensor<string, []>("transpose_18")];
            tensor<fp16, [1, 8, 512, 64]> transpose_13 = transpose(perm = transpose_13_perm_0, x = x_95_cast_fp16)[name = tensor<string, []>("transpose_19")];
            tensor<fp16, [1, 8, 512, 512]> sim_9_cast_fp16 = matmul(transpose_x = sim_9_transpose_x_0, transpose_y = sim_9_transpose_y_0, x = transpose_13, y = transpose_14)[name = tensor<string, []>("sim_9_cast_fp16")];
            tensor<fp16, []> var_537_to_fp16 = const()[name = tensor<string, []>("op_537_to_fp16"), val = tensor<fp16, []>(0x1p-3)];
            tensor<fp16, [1, 8, 512, 512]> sim_cast_fp16 = mul(x = sim_9_cast_fp16, y = var_537_to_fp16)[name = tensor<string, []>("sim_cast_fp16")];
            tensor<fp16, [1, 8, 512, 512]> attn_cast_fp16 = softmax(axis = var_443, x = sim_cast_fp16)[name = tensor<string, []>("attn_cast_fp16")];
            tensor<bool, []> x_105_transpose_x_0 = const()[name = tensor<string, []>("x_105_transpose_x_0"), val = tensor<bool, []>(false)];
            tensor<bool, []> x_105_transpose_y_0 = const()[name = tensor<string, []>("x_105_transpose_y_0"), val = tensor<bool, []>(false)];
            tensor<fp16, [1, 8, 512, 64]> v_cast_fp16 = transpose(perm = var_533, x = x_103_cast_fp16)[name = tensor<string, []>("transpose_20")];
            tensor<fp16, [1, 8, 512, 64]> x_105_cast_fp16 = matmul(transpose_x = x_105_transpose_x_0, transpose_y = x_105_transpose_y_0, x = attn_cast_fp16, y = v_cast_fp16)[name = tensor<string, []>("x_105_cast_fp16")];
            tensor<int32, [4]> var_559 = const()[name = tensor<string, []>("op_559"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<int32, [3]> var_561 = const()[name = tensor<string, []>("op_561"), val = tensor<int32, [3]>([1, 512, 512])];
            tensor<fp16, [1, 512, 8, 64]> x_107_cast_fp16 = transpose(perm = var_559, x = x_105_cast_fp16)[name = tensor<string, []>("transpose_17")];
            tensor<fp16, [1, 512, 512]> input_55_cast_fp16 = reshape(shape = var_561, x = x_107_cast_fp16)[name = tensor<string, []>("input_55_cast_fp16")];
            tensor<fp16, [1024, 512]> transformer_blocks_2_attention_attention_to_out_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_2_attention_attention_to_out_weight_to_fp16"), val = tensor<fp16, [1024, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(39903104)))];
            tensor<fp16, [1024]> transformer_blocks_2_attention_attention_to_out_bias_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_2_attention_attention_to_out_bias_to_fp16"), val = tensor<fp16, [1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(40951744)))];
            tensor<fp16, [1, 512, 1024]> linear_22_cast_fp16 = linear(bias = transformer_blocks_2_attention_attention_to_out_bias_to_fp16, weight = transformer_blocks_2_attention_attention_to_out_weight_to_fp16, x = input_55_cast_fp16)[name = tensor<string, []>("linear_22_cast_fp16")];
            tensor<fp16, [1, 512, 1024]> input_57_cast_fp16 = add(x = linear_22_cast_fp16, y = x_79_cast_fp16)[name = tensor<string, []>("input_57_cast_fp16")];
            tensor<fp16, [2048, 1024]> transformer_blocks_2_feed_forward_0_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_2_feed_forward_0_weight_to_fp16"), val = tensor<fp16, [2048, 1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(40953856)))];
            tensor<fp16, [2048]> transformer_blocks_2_feed_forward_0_bias_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_2_feed_forward_0_bias_to_fp16"), val = tensor<fp16, [2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(45148224)))];
            tensor<fp16, [1, 512, 2048]> linear_23_cast_fp16 = linear(bias = transformer_blocks_2_feed_forward_0_bias_to_fp16, weight = transformer_blocks_2_feed_forward_0_weight_to_fp16, x = input_57_cast_fp16)[name = tensor<string, []>("linear_23_cast_fp16")];
            tensor<string, []> input_61_mode_0 = const()[name = tensor<string, []>("input_61_mode_0"), val = tensor<string, []>("EXACT")];
            tensor<fp16, [1, 512, 2048]> input_61_cast_fp16 = gelu(mode = input_61_mode_0, x = linear_23_cast_fp16)[name = tensor<string, []>("input_61_cast_fp16")];
            tensor<fp16, [1024, 2048]> transformer_blocks_2_feed_forward_2_weight_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_2_feed_forward_2_weight_to_fp16"), val = tensor<fp16, [1024, 2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(45152384)))];
            tensor<fp16, [1024]> transformer_blocks_2_feed_forward_2_bias_to_fp16 = const()[name = tensor<string, []>("transformer_blocks_2_feed_forward_2_bias_to_fp16"), val = tensor<fp16, [1024]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(49346752)))];
            tensor<fp16, [1, 512, 1024]> linear_24_cast_fp16 = linear(bias = transformer_blocks_2_feed_forward_2_bias_to_fp16, weight = transformer_blocks_2_feed_forward_2_weight_to_fp16, x = input_61_cast_fp16)[name = tensor<string, []>("linear_24_cast_fp16")];
            tensor<fp16, [1, 512, 1024]> x_109_cast_fp16 = add(x = linear_24_cast_fp16, y = input_57_cast_fp16)[name = tensor<string, []>("x_109_cast_fp16")];
            tensor<int32, [1]> var_581_axes_0 = const()[name = tensor<string, []>("op_581_axes_0"), val = tensor<int32, [1]>([1])];
            tensor<bool, []> var_581_keep_dims_0 = const()[name = tensor<string, []>("op_581_keep_dims_0"), val = tensor<bool, []>(false)];
            tensor<fp16, [1, 1024]> var_581_cast_fp16 = reduce_mean(axes = var_581_axes_0, keep_dims = var_581_keep_dims_0, x = x_109_cast_fp16)[name = tensor<string, []>("op_581_cast_fp16")];
            tensor<int32, [1]> x_111_axes_0 = const()[name = tensor<string, []>("x_111_axes_0"), val = tensor<int32, [1]>([1])];
            tensor<fp16, [1, 1, 1024]> x_111_cast_fp16 = expand_dims(axes = x_111_axes_0, x = var_581_cast_fp16)[name = tensor<string, []>("x_111_cast_fp16")];
            tensor<int32, [3]> var_590 = const()[name = tensor<string, []>("op_590"), val = tensor<int32, [3]>([0, 2, 1])];
            tensor<string, []> x_pad_type_0 = const()[name = tensor<string, []>("x_pad_type_0"), val = tensor<string, []>("valid")];
            tensor<int32, [1]> x_strides_0 = const()[name = tensor<string, []>("x_strides_0"), val = tensor<int32, [1]>([1])];
            tensor<int32, [2]> x_pad_0 = const()[name = tensor<string, []>("x_pad_0"), val = tensor<int32, [2]>([0, 0])];
            tensor<int32, [1]> x_dilations_0 = const()[name = tensor<string, []>("x_dilations_0"), val = tensor<int32, [1]>([1])];
            tensor<int32, []> x_groups_0 = const()[name = tensor<string, []>("x_groups_0"), val = tensor<int32, []>(1)];
            tensor<fp16, [256, 1024, 1]> transformer_to_out_1_weight_to_fp16 = const()[name = tensor<string, []>("transformer_to_out_1_weight_to_fp16"), val = tensor<fp16, [256, 1024, 1]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(49348864)))];
            tensor<fp16, [256]> transformer_to_out_1_bias_to_fp16 = const()[name = tensor<string, []>("transformer_to_out_1_bias_to_fp16"), val = tensor<fp16, [256]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(49873216)))];
            tensor<fp16, [1, 1024, 1]> input_cast_fp16 = transpose(perm = var_590, x = x_111_cast_fp16)[name = tensor<string, []>("transpose_16")];
            tensor<fp16, [1, 256, 1]> x_cast_fp16 = conv(bias = transformer_to_out_1_bias_to_fp16, dilations = x_dilations_0, groups = x_groups_0, pad = x_pad_0, pad_type = x_pad_type_0, strides = x_strides_0, weight = transformer_to_out_1_weight_to_fp16, x = input_cast_fp16)[name = tensor<string, []>("x_cast_fp16")];
            tensor<int32, [3]> x_pred_perm_0 = const()[name = tensor<string, []>("x_pred_perm_0"), val = tensor<int32, [3]>([0, -1, -2])];
            tensor<fp16, [1, 1, 256]> var_602_cast_fp16 = mul(x = c_skip_cast_fp16, y = x_noisy_to_fp16)[name = tensor<string, []>("op_602_cast_fp16")];
            tensor<fp16, [1, 1, 256]> x_pred_cast_fp16 = transpose(perm = x_pred_perm_0, x = x_cast_fp16)[name = tensor<string, []>("transpose_15")];
            tensor<fp16, [1, 1, 256]> var_603_cast_fp16 = mul(x = c_out_cast_fp16, y = x_pred_cast_fp16)[name = tensor<string, []>("op_603_cast_fp16")];
            tensor<fp16, [1, 1, 256]> denoised = add(x = var_602_cast_fp16, y = var_603_cast_fp16)[name = tensor<string, []>("op_605_cast_fp16")];
        } -> (denoised);
}