program(1.0)
[buildInfo = dict<tensor<string, []>, tensor<string, []>>({{"coremlc-component-MIL", "5.33.5"}, {"coremlc-version", "1877.40.3"}, {"coremltools-component-torch", "1.11.0"}, {"coremltools-source-dialect", "TorchScript"}, {"coremltools-version", "7.1"}})]
{
    func main<ios15>(tensor<fp32, [1, 80, 3000]> logmel_data) {
            tensor<int32, []> var_20 = const()[name = tensor<string, []>("op_20"), val = tensor<int32, []>(1)];
            tensor<int32, [1]> var_28 = const()[name = tensor<string, []>("op_28"), val = tensor<int32, [1]>([1])];
            tensor<int32, [1]> var_30 = const()[name = tensor<string, []>("op_30"), val = tensor<int32, [1]>([1])];
            tensor<string, []> var_32_pad_type_0 = const()[name = tensor<string, []>("op_32_pad_type_0"), val = tensor<string, []>("custom")];
            tensor<int32, [2]> var_32_pad_0 = const()[name = tensor<string, []>("op_32_pad_0"), val = tensor<int32, [2]>([1, 1])];
            tensor<string, []> logmel_data_to_fp16_dtype_0 = const()[name = tensor<string, []>("logmel_data_to_fp16_dtype_0"), val = tensor<string, []>("fp16")];
            tensor<fp16, [512, 80, 3]> weight_3_to_fp16 = const()[name = tensor<string, []>("weight_3_to_fp16"), val = tensor<fp16, [512, 80, 3]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(64)))];
            tensor<fp16, [512]> bias_3_to_fp16 = const()[name = tensor<string, []>("bias_3_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(245888)))];
            tensor<fp16, [1, 80, 3000]> cast_37 = cast(dtype = logmel_data_to_fp16_dtype_0, x = logmel_data)[name = tensor<string, []>("cast_37")];
            tensor<fp16, [1, 512, 3000]> var_32_cast_fp16 = conv(bias = bias_3_to_fp16, dilations = var_30, groups = var_20, pad = var_32_pad_0, pad_type = var_32_pad_type_0, strides = var_28, weight = weight_3_to_fp16, x = cast_37)[name = tensor<string, []>("op_32_cast_fp16")];
            tensor<string, []> input_1_mode_0 = const()[name = tensor<string, []>("input_1_mode_0"), val = tensor<string, []>("EXACT")];
            tensor<fp16, [1, 512, 3000]> input_1_cast_fp16 = gelu(mode = input_1_mode_0, x = var_32_cast_fp16)[name = tensor<string, []>("input_1_cast_fp16")];
            tensor<int32, []> var_36 = const()[name = tensor<string, []>("op_36"), val = tensor<int32, []>(1)];
            tensor<int32, [1]> var_45 = const()[name = tensor<string, []>("op_45"), val = tensor<int32, [1]>([2])];
            tensor<int32, [1]> var_47 = const()[name = tensor<string, []>("op_47"), val = tensor<int32, [1]>([1])];
            tensor<string, []> var_49_pad_type_0 = const()[name = tensor<string, []>("op_49_pad_type_0"), val = tensor<string, []>("custom")];
            tensor<int32, [2]> var_49_pad_0 = const()[name = tensor<string, []>("op_49_pad_0"), val = tensor<int32, [2]>([1, 1])];
            tensor<fp16, [512, 512, 3]> weight_7_to_fp16 = const()[name = tensor<string, []>("weight_7_to_fp16"), val = tensor<fp16, [512, 512, 3]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(246976)))];
            tensor<fp16, [512]> bias_7_to_fp16 = const()[name = tensor<string, []>("bias_7_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(1819904)))];
            tensor<fp16, [1, 512, 1500]> var_49_cast_fp16 = conv(bias = bias_7_to_fp16, dilations = var_47, groups = var_36, pad = var_49_pad_0, pad_type = var_49_pad_type_0, strides = var_45, weight = weight_7_to_fp16, x = input_1_cast_fp16)[name = tensor<string, []>("op_49_cast_fp16")];
            tensor<string, []> x_3_mode_0 = const()[name = tensor<string, []>("x_3_mode_0"), val = tensor<string, []>("EXACT")];
            tensor<fp16, [1, 512, 1500]> x_3_cast_fp16 = gelu(mode = x_3_mode_0, x = var_49_cast_fp16)[name = tensor<string, []>("x_3_cast_fp16")];
            tensor<int32, [3]> var_54 = const()[name = tensor<string, []>("op_54"), val = tensor<int32, [3]>([0, 2, 1])];
            tensor<fp16, [1500, 512]> positional_embedding_to_fp16 = const()[name = tensor<string, []>("positional_embedding_to_fp16"), val = tensor<fp16, [1500, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(1820992)))];
            tensor<fp16, [1, 1500, 512]> transpose_60 = transpose(perm = var_54, x = x_3_cast_fp16)[name = tensor<string, []>("transpose_60")];
            tensor<fp16, [1, 1500, 512]> var_57_cast_fp16 = add(x = transpose_60, y = positional_embedding_to_fp16)[name = tensor<string, []>("op_57_cast_fp16")];
            tensor<int32, []> var_70 = const()[name = tensor<string, []>("op_70"), val = tensor<int32, []>(-1)];
            tensor<int32, [1]> var_87_axes_0 = const()[name = tensor<string, []>("op_87_axes_0"), val = tensor<int32, [1]>([-1])];
            tensor<fp16, [512]> blocks_0_attn_ln_weight_to_fp16 = const()[name = tensor<string, []>("blocks_0_attn_ln_weight_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(3357056)))];
            tensor<fp16, [512]> blocks_0_attn_ln_bias_to_fp16 = const()[name = tensor<string, []>("blocks_0_attn_ln_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(3358144)))];
            tensor<fp16, []> var_76_to_fp16 = const()[name = tensor<string, []>("op_76_to_fp16"), val = tensor<fp16, []>(0x1.5p-17)];
            tensor<fp16, [1, 1500, 512]> var_87_cast_fp16 = layer_norm(axes = var_87_axes_0, beta = blocks_0_attn_ln_bias_to_fp16, epsilon = var_76_to_fp16, gamma = blocks_0_attn_ln_weight_to_fp16, x = var_57_cast_fp16)[name = tensor<string, []>("op_87_cast_fp16")];
            tensor<fp16, [512, 512]> var_98_to_fp16 = const()[name = tensor<string, []>("op_98_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(3359232)))];
            tensor<fp16, [512]> var_99_to_fp16 = const()[name = tensor<string, []>("op_99_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(3883584)))];
            tensor<fp16, [1, 1500, 512]> linear_0_cast_fp16 = linear(bias = var_99_to_fp16, weight = var_98_to_fp16, x = var_87_cast_fp16)[name = tensor<string, []>("linear_0_cast_fp16")];
            tensor<fp16, [512, 512]> var_102_to_fp16 = const()[name = tensor<string, []>("op_102_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(3884672)))];
            tensor<fp16, [512]> linear_1_bias_0_to_fp16 = const()[name = tensor<string, []>("linear_1_bias_0_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(4409024)))];
            tensor<fp16, [1, 1500, 512]> linear_1_cast_fp16 = linear(bias = linear_1_bias_0_to_fp16, weight = var_102_to_fp16, x = var_87_cast_fp16)[name = tensor<string, []>("linear_1_cast_fp16")];
            tensor<fp16, [512, 512]> var_106_to_fp16 = const()[name = tensor<string, []>("op_106_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(4410112)))];
            tensor<fp16, [512]> var_107_to_fp16 = const()[name = tensor<string, []>("op_107_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(4934464)))];
            tensor<fp16, [1, 1500, 512]> linear_2_cast_fp16 = linear(bias = var_107_to_fp16, weight = var_106_to_fp16, x = var_87_cast_fp16)[name = tensor<string, []>("linear_2_cast_fp16")];
            tensor<int32, [4]> var_115 = const()[name = tensor<string, []>("op_115"), val = tensor<int32, [4]>([1, 1500, 8, -1])];
            tensor<fp16, [1, 1500, 8, 64]> var_116_cast_fp16 = reshape(shape = var_115, x = linear_0_cast_fp16)[name = tensor<string, []>("op_116_cast_fp16")];
            tensor<fp16, [1, 1, 1, 1]> const_42_to_fp16 = const()[name = tensor<string, []>("const_42_to_fp16"), val = tensor<fp16, [1, 1, 1, 1]>([[[[0x1.6ap-2]]]])];
            tensor<fp16, [1, 1500, 8, 64]> q_3_cast_fp16 = mul(x = var_116_cast_fp16, y = const_42_to_fp16)[name = tensor<string, []>("q_3_cast_fp16")];
            tensor<int32, [4]> var_122 = const()[name = tensor<string, []>("op_122"), val = tensor<int32, [4]>([1, 1500, 8, -1])];
            tensor<fp16, [1, 1500, 8, 64]> var_123_cast_fp16 = reshape(shape = var_122, x = linear_1_cast_fp16)[name = tensor<string, []>("op_123_cast_fp16")];
            tensor<fp16, [1, 1, 1, 1]> const_43_to_fp16 = const()[name = tensor<string, []>("const_43_to_fp16"), val = tensor<fp16, [1, 1, 1, 1]>([[[[0x1.6ap-2]]]])];
            tensor<fp16, [1, 1500, 8, 64]> k_3_cast_fp16 = mul(x = var_123_cast_fp16, y = const_43_to_fp16)[name = tensor<string, []>("k_3_cast_fp16")];
            tensor<int32, [4]> var_129 = const()[name = tensor<string, []>("op_129"), val = tensor<int32, [4]>([1, 1500, 8, -1])];
            tensor<fp16, [1, 1500, 8, 64]> var_130_cast_fp16 = reshape(shape = var_129, x = linear_2_cast_fp16)[name = tensor<string, []>("op_130_cast_fp16")];
            tensor<int32, [4]> var_131 = const()[name = tensor<string, []>("op_131"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<bool, []> qk_1_transpose_x_0 = const()[name = tensor<string, []>("qk_1_transpose_x_0"), val = tensor<bool, []>(false)];
            tensor<bool, []> qk_1_transpose_y_0 = const()[name = tensor<string, []>("qk_1_transpose_y_0"), val = tensor<bool, []>(false)];
            tensor<int32, [4]> transpose_24_perm_0 = const()[name = tensor<string, []>("transpose_24_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<int32, [4]> transpose_25_perm_0 = const()[name = tensor<string, []>("transpose_25_perm_0"), val = tensor<int32, [4]>([0, 2, 3, 1])];
            tensor<fp16, [1, 8, 64, 1500]> transpose_57 = transpose(perm = transpose_25_perm_0, x = k_3_cast_fp16)[name = tensor<string, []>("transpose_57")];
            tensor<fp16, [1, 8, 1500, 64]> transpose_58 = transpose(perm = transpose_24_perm_0, x = q_3_cast_fp16)[name = tensor<string, []>("transpose_58")];
            tensor<fp16, [1, 8, 1500, 1500]> qk_1_cast_fp16 = matmul(transpose_x = qk_1_transpose_x_0, transpose_y = qk_1_transpose_y_0, x = transpose_58, y = transpose_57)[name = tensor<string, []>("qk_1_cast_fp16")];
            tensor<fp16, [1, 8, 1500, 1500]> var_135_cast_fp16 = softmax(axis = var_70, x = qk_1_cast_fp16)[name = tensor<string, []>("op_135_cast_fp16")];
            tensor<bool, []> var_137_transpose_x_0 = const()[name = tensor<string, []>("op_137_transpose_x_0"), val = tensor<bool, []>(false)];
            tensor<bool, []> var_137_transpose_y_0 = const()[name = tensor<string, []>("op_137_transpose_y_0"), val = tensor<bool, []>(false)];
            tensor<fp16, [1, 8, 1500, 64]> transpose_59 = transpose(perm = var_131, x = var_130_cast_fp16)[name = tensor<string, []>("transpose_59")];
            tensor<fp16, [1, 8, 1500, 64]> var_137_cast_fp16 = matmul(transpose_x = var_137_transpose_x_0, transpose_y = var_137_transpose_y_0, x = var_135_cast_fp16, y = transpose_59)[name = tensor<string, []>("op_137_cast_fp16")];
            tensor<int32, [4]> var_138 = const()[name = tensor<string, []>("op_138"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<int32, [3]> concat_0 = const()[name = tensor<string, []>("concat_0"), val = tensor<int32, [3]>([1, 1500, 512])];
            tensor<fp16, [1, 1500, 8, 64]> transpose_56 = transpose(perm = var_138, x = var_137_cast_fp16)[name = tensor<string, []>("transpose_56")];
            tensor<fp16, [1, 1500, 512]> x_11_cast_fp16 = reshape(shape = concat_0, x = transpose_56)[name = tensor<string, []>("x_11_cast_fp16")];
            tensor<fp16, [512, 512]> var_143_to_fp16 = const()[name = tensor<string, []>("op_143_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(4935552)))];
            tensor<fp16, [512]> var_144_to_fp16 = const()[name = tensor<string, []>("op_144_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(5459904)))];
            tensor<fp16, [1, 1500, 512]> linear_3_cast_fp16 = linear(bias = var_144_to_fp16, weight = var_143_to_fp16, x = x_11_cast_fp16)[name = tensor<string, []>("linear_3_cast_fp16")];
            tensor<fp16, [1, 1500, 512]> x_13_cast_fp16 = add(x = var_57_cast_fp16, y = linear_3_cast_fp16)[name = tensor<string, []>("x_13_cast_fp16")];
            tensor<int32, [1]> var_151_axes_0 = const()[name = tensor<string, []>("op_151_axes_0"), val = tensor<int32, [1]>([-1])];
            tensor<fp16, [512]> blocks_0_mlp_ln_weight_to_fp16 = const()[name = tensor<string, []>("blocks_0_mlp_ln_weight_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(5460992)))];
            tensor<fp16, [512]> blocks_0_mlp_ln_bias_to_fp16 = const()[name = tensor<string, []>("blocks_0_mlp_ln_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(5462080)))];
            tensor<fp16, [1, 1500, 512]> var_151_cast_fp16 = layer_norm(axes = var_151_axes_0, beta = blocks_0_mlp_ln_bias_to_fp16, epsilon = var_76_to_fp16, gamma = blocks_0_mlp_ln_weight_to_fp16, x = x_13_cast_fp16)[name = tensor<string, []>("op_151_cast_fp16")];
            tensor<fp16, [2048, 512]> var_160_to_fp16 = const()[name = tensor<string, []>("op_160_to_fp16"), val = tensor<fp16, [2048, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(5463168)))];
            tensor<fp16, [2048]> var_161_to_fp16 = const()[name = tensor<string, []>("op_161_to_fp16"), val = tensor<fp16, [2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(7560384)))];
            tensor<fp16, [1, 1500, 2048]> linear_4_cast_fp16 = linear(bias = var_161_to_fp16, weight = var_160_to_fp16, x = var_151_cast_fp16)[name = tensor<string, []>("linear_4_cast_fp16")];
            tensor<string, []> x_17_mode_0 = const()[name = tensor<string, []>("x_17_mode_0"), val = tensor<string, []>("EXACT")];
            tensor<fp16, [1, 1500, 2048]> x_17_cast_fp16 = gelu(mode = x_17_mode_0, x = linear_4_cast_fp16)[name = tensor<string, []>("x_17_cast_fp16")];
            tensor<fp16, [512, 2048]> var_166_to_fp16 = const()[name = tensor<string, []>("op_166_to_fp16"), val = tensor<fp16, [512, 2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(7564544)))];
            tensor<fp16, [512]> var_167_to_fp16 = const()[name = tensor<string, []>("op_167_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(9661760)))];
            tensor<fp16, [1, 1500, 512]> linear_5_cast_fp16 = linear(bias = var_167_to_fp16, weight = var_166_to_fp16, x = x_17_cast_fp16)[name = tensor<string, []>("linear_5_cast_fp16")];
            tensor<fp16, [1, 1500, 512]> x_19_cast_fp16 = add(x = x_13_cast_fp16, y = linear_5_cast_fp16)[name = tensor<string, []>("x_19_cast_fp16")];
            tensor<int32, []> var_177 = const()[name = tensor<string, []>("op_177"), val = tensor<int32, []>(-1)];
            tensor<int32, [1]> var_194_axes_0 = const()[name = tensor<string, []>("op_194_axes_0"), val = tensor<int32, [1]>([-1])];
            tensor<fp16, [512]> blocks_1_attn_ln_weight_to_fp16 = const()[name = tensor<string, []>("blocks_1_attn_ln_weight_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(9662848)))];
            tensor<fp16, [512]> blocks_1_attn_ln_bias_to_fp16 = const()[name = tensor<string, []>("blocks_1_attn_ln_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(9663936)))];
            tensor<fp16, []> var_183_to_fp16 = const()[name = tensor<string, []>("op_183_to_fp16"), val = tensor<fp16, []>(0x1.5p-17)];
            tensor<fp16, [1, 1500, 512]> var_194_cast_fp16 = layer_norm(axes = var_194_axes_0, beta = blocks_1_attn_ln_bias_to_fp16, epsilon = var_183_to_fp16, gamma = blocks_1_attn_ln_weight_to_fp16, x = x_19_cast_fp16)[name = tensor<string, []>("op_194_cast_fp16")];
            tensor<fp16, [512, 512]> var_205_to_fp16 = const()[name = tensor<string, []>("op_205_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(9665024)))];
            tensor<fp16, [512]> var_206_to_fp16 = const()[name = tensor<string, []>("op_206_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(10189376)))];
            tensor<fp16, [1, 1500, 512]> linear_6_cast_fp16 = linear(bias = var_206_to_fp16, weight = var_205_to_fp16, x = var_194_cast_fp16)[name = tensor<string, []>("linear_6_cast_fp16")];
            tensor<fp16, [512, 512]> var_209_to_fp16 = const()[name = tensor<string, []>("op_209_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(10190464)))];
            tensor<fp16, [1, 1500, 512]> linear_7_cast_fp16 = linear(bias = linear_1_bias_0_to_fp16, weight = var_209_to_fp16, x = var_194_cast_fp16)[name = tensor<string, []>("linear_7_cast_fp16")];
            tensor<fp16, [512, 512]> var_213_to_fp16 = const()[name = tensor<string, []>("op_213_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(10714816)))];
            tensor<fp16, [512]> var_214_to_fp16 = const()[name = tensor<string, []>("op_214_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(11239168)))];
            tensor<fp16, [1, 1500, 512]> linear_8_cast_fp16 = linear(bias = var_214_to_fp16, weight = var_213_to_fp16, x = var_194_cast_fp16)[name = tensor<string, []>("linear_8_cast_fp16")];
            tensor<int32, [4]> var_222 = const()[name = tensor<string, []>("op_222"), val = tensor<int32, [4]>([1, 1500, 8, -1])];
            tensor<fp16, [1, 1500, 8, 64]> var_223_cast_fp16 = reshape(shape = var_222, x = linear_6_cast_fp16)[name = tensor<string, []>("op_223_cast_fp16")];
            tensor<fp16, [1, 1, 1, 1]> const_44_to_fp16 = const()[name = tensor<string, []>("const_44_to_fp16"), val = tensor<fp16, [1, 1, 1, 1]>([[[[0x1.6ap-2]]]])];
            tensor<fp16, [1, 1500, 8, 64]> q_7_cast_fp16 = mul(x = var_223_cast_fp16, y = const_44_to_fp16)[name = tensor<string, []>("q_7_cast_fp16")];
            tensor<int32, [4]> var_229 = const()[name = tensor<string, []>("op_229"), val = tensor<int32, [4]>([1, 1500, 8, -1])];
            tensor<fp16, [1, 1500, 8, 64]> var_230_cast_fp16 = reshape(shape = var_229, x = linear_7_cast_fp16)[name = tensor<string, []>("op_230_cast_fp16")];
            tensor<fp16, [1, 1, 1, 1]> const_45_to_fp16 = const()[name = tensor<string, []>("const_45_to_fp16"), val = tensor<fp16, [1, 1, 1, 1]>([[[[0x1.6ap-2]]]])];
            tensor<fp16, [1, 1500, 8, 64]> k_7_cast_fp16 = mul(x = var_230_cast_fp16, y = const_45_to_fp16)[name = tensor<string, []>("k_7_cast_fp16")];
            tensor<int32, [4]> var_236 = const()[name = tensor<string, []>("op_236"), val = tensor<int32, [4]>([1, 1500, 8, -1])];
            tensor<fp16, [1, 1500, 8, 64]> var_237_cast_fp16 = reshape(shape = var_236, x = linear_8_cast_fp16)[name = tensor<string, []>("op_237_cast_fp16")];
            tensor<int32, [4]> var_238 = const()[name = tensor<string, []>("op_238"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<bool, []> qk_3_transpose_x_0 = const()[name = tensor<string, []>("qk_3_transpose_x_0"), val = tensor<bool, []>(false)];
            tensor<bool, []> qk_3_transpose_y_0 = const()[name = tensor<string, []>("qk_3_transpose_y_0"), val = tensor<bool, []>(false)];
            tensor<int32, [4]> transpose_26_perm_0 = const()[name = tensor<string, []>("transpose_26_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<int32, [4]> transpose_27_perm_0 = const()[name = tensor<string, []>("transpose_27_perm_0"), val = tensor<int32, [4]>([0, 2, 3, 1])];
            tensor<fp16, [1, 8, 64, 1500]> transpose_53 = transpose(perm = transpose_27_perm_0, x = k_7_cast_fp16)[name = tensor<string, []>("transpose_53")];
            tensor<fp16, [1, 8, 1500, 64]> transpose_54 = transpose(perm = transpose_26_perm_0, x = q_7_cast_fp16)[name = tensor<string, []>("transpose_54")];
            tensor<fp16, [1, 8, 1500, 1500]> qk_3_cast_fp16 = matmul(transpose_x = qk_3_transpose_x_0, transpose_y = qk_3_transpose_y_0, x = transpose_54, y = transpose_53)[name = tensor<string, []>("qk_3_cast_fp16")];
            tensor<fp16, [1, 8, 1500, 1500]> var_242_cast_fp16 = softmax(axis = var_177, x = qk_3_cast_fp16)[name = tensor<string, []>("op_242_cast_fp16")];
            tensor<bool, []> var_244_transpose_x_0 = const()[name = tensor<string, []>("op_244_transpose_x_0"), val = tensor<bool, []>(false)];
            tensor<bool, []> var_244_transpose_y_0 = const()[name = tensor<string, []>("op_244_transpose_y_0"), val = tensor<bool, []>(false)];
            tensor<fp16, [1, 8, 1500, 64]> transpose_55 = transpose(perm = var_238, x = var_237_cast_fp16)[name = tensor<string, []>("transpose_55")];
            tensor<fp16, [1, 8, 1500, 64]> var_244_cast_fp16 = matmul(transpose_x = var_244_transpose_x_0, transpose_y = var_244_transpose_y_0, x = var_242_cast_fp16, y = transpose_55)[name = tensor<string, []>("op_244_cast_fp16")];
            tensor<int32, [4]> var_245 = const()[name = tensor<string, []>("op_245"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<int32, [3]> concat_1 = const()[name = tensor<string, []>("concat_1"), val = tensor<int32, [3]>([1, 1500, 512])];
            tensor<fp16, [1, 1500, 8, 64]> transpose_52 = transpose(perm = var_245, x = var_244_cast_fp16)[name = tensor<string, []>("transpose_52")];
            tensor<fp16, [1, 1500, 512]> x_23_cast_fp16 = reshape(shape = concat_1, x = transpose_52)[name = tensor<string, []>("x_23_cast_fp16")];
            tensor<fp16, [512, 512]> var_250_to_fp16 = const()[name = tensor<string, []>("op_250_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(11240256)))];
            tensor<fp16, [512]> var_251_to_fp16 = const()[name = tensor<string, []>("op_251_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(11764608)))];
            tensor<fp16, [1, 1500, 512]> linear_9_cast_fp16 = linear(bias = var_251_to_fp16, weight = var_250_to_fp16, x = x_23_cast_fp16)[name = tensor<string, []>("linear_9_cast_fp16")];
            tensor<fp16, [1, 1500, 512]> x_25_cast_fp16 = add(x = x_19_cast_fp16, y = linear_9_cast_fp16)[name = tensor<string, []>("x_25_cast_fp16")];
            tensor<int32, [1]> var_258_axes_0 = const()[name = tensor<string, []>("op_258_axes_0"), val = tensor<int32, [1]>([-1])];
            tensor<fp16, [512]> blocks_1_mlp_ln_weight_to_fp16 = const()[name = tensor<string, []>("blocks_1_mlp_ln_weight_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(11765696)))];
            tensor<fp16, [512]> blocks_1_mlp_ln_bias_to_fp16 = const()[name = tensor<string, []>("blocks_1_mlp_ln_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(11766784)))];
            tensor<fp16, [1, 1500, 512]> var_258_cast_fp16 = layer_norm(axes = var_258_axes_0, beta = blocks_1_mlp_ln_bias_to_fp16, epsilon = var_183_to_fp16, gamma = blocks_1_mlp_ln_weight_to_fp16, x = x_25_cast_fp16)[name = tensor<string, []>("op_258_cast_fp16")];
            tensor<fp16, [2048, 512]> var_267_to_fp16 = const()[name = tensor<string, []>("op_267_to_fp16"), val = tensor<fp16, [2048, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(11767872)))];
            tensor<fp16, [2048]> var_268_to_fp16 = const()[name = tensor<string, []>("op_268_to_fp16"), val = tensor<fp16, [2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(13865088)))];
            tensor<fp16, [1, 1500, 2048]> linear_10_cast_fp16 = linear(bias = var_268_to_fp16, weight = var_267_to_fp16, x = var_258_cast_fp16)[name = tensor<string, []>("linear_10_cast_fp16")];
            tensor<string, []> x_29_mode_0 = const()[name = tensor<string, []>("x_29_mode_0"), val = tensor<string, []>("EXACT")];
            tensor<fp16, [1, 1500, 2048]> x_29_cast_fp16 = gelu(mode = x_29_mode_0, x = linear_10_cast_fp16)[name = tensor<string, []>("x_29_cast_fp16")];
            tensor<fp16, [512, 2048]> var_273_to_fp16 = const()[name = tensor<string, []>("op_273_to_fp16"), val = tensor<fp16, [512, 2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(13869248)))];
            tensor<fp16, [512]> var_274_to_fp16 = const()[name = tensor<string, []>("op_274_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(15966464)))];
            tensor<fp16, [1, 1500, 512]> linear_11_cast_fp16 = linear(bias = var_274_to_fp16, weight = var_273_to_fp16, x = x_29_cast_fp16)[name = tensor<string, []>("linear_11_cast_fp16")];
            tensor<fp16, [1, 1500, 512]> x_31_cast_fp16 = add(x = x_25_cast_fp16, y = linear_11_cast_fp16)[name = tensor<string, []>("x_31_cast_fp16")];
            tensor<int32, []> var_284 = const()[name = tensor<string, []>("op_284"), val = tensor<int32, []>(-1)];
            tensor<int32, [1]> var_301_axes_0 = const()[name = tensor<string, []>("op_301_axes_0"), val = tensor<int32, [1]>([-1])];
            tensor<fp16, [512]> blocks_2_attn_ln_weight_to_fp16 = const()[name = tensor<string, []>("blocks_2_attn_ln_weight_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(15967552)))];
            tensor<fp16, [512]> blocks_2_attn_ln_bias_to_fp16 = const()[name = tensor<string, []>("blocks_2_attn_ln_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(15968640)))];
            tensor<fp16, []> var_290_to_fp16 = const()[name = tensor<string, []>("op_290_to_fp16"), val = tensor<fp16, []>(0x1.5p-17)];
            tensor<fp16, [1, 1500, 512]> var_301_cast_fp16 = layer_norm(axes = var_301_axes_0, beta = blocks_2_attn_ln_bias_to_fp16, epsilon = var_290_to_fp16, gamma = blocks_2_attn_ln_weight_to_fp16, x = x_31_cast_fp16)[name = tensor<string, []>("op_301_cast_fp16")];
            tensor<fp16, [512, 512]> var_312_to_fp16 = const()[name = tensor<string, []>("op_312_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(15969728)))];
            tensor<fp16, [512]> var_313_to_fp16 = const()[name = tensor<string, []>("op_313_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(16494080)))];
            tensor<fp16, [1, 1500, 512]> linear_12_cast_fp16 = linear(bias = var_313_to_fp16, weight = var_312_to_fp16, x = var_301_cast_fp16)[name = tensor<string, []>("linear_12_cast_fp16")];
            tensor<fp16, [512, 512]> var_316_to_fp16 = const()[name = tensor<string, []>("op_316_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(16495168)))];
            tensor<fp16, [1, 1500, 512]> linear_13_cast_fp16 = linear(bias = linear_1_bias_0_to_fp16, weight = var_316_to_fp16, x = var_301_cast_fp16)[name = tensor<string, []>("linear_13_cast_fp16")];
            tensor<fp16, [512, 512]> var_320_to_fp16 = const()[name = tensor<string, []>("op_320_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(17019520)))];
            tensor<fp16, [512]> var_321_to_fp16 = const()[name = tensor<string, []>("op_321_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(17543872)))];
            tensor<fp16, [1, 1500, 512]> linear_14_cast_fp16 = linear(bias = var_321_to_fp16, weight = var_320_to_fp16, x = var_301_cast_fp16)[name = tensor<string, []>("linear_14_cast_fp16")];
            tensor<int32, [4]> var_329 = const()[name = tensor<string, []>("op_329"), val = tensor<int32, [4]>([1, 1500, 8, -1])];
            tensor<fp16, [1, 1500, 8, 64]> var_330_cast_fp16 = reshape(shape = var_329, x = linear_12_cast_fp16)[name = tensor<string, []>("op_330_cast_fp16")];
            tensor<fp16, [1, 1, 1, 1]> const_46_to_fp16 = const()[name = tensor<string, []>("const_46_to_fp16"), val = tensor<fp16, [1, 1, 1, 1]>([[[[0x1.6ap-2]]]])];
            tensor<fp16, [1, 1500, 8, 64]> q_11_cast_fp16 = mul(x = var_330_cast_fp16, y = const_46_to_fp16)[name = tensor<string, []>("q_11_cast_fp16")];
            tensor<int32, [4]> var_336 = const()[name = tensor<string, []>("op_336"), val = tensor<int32, [4]>([1, 1500, 8, -1])];
            tensor<fp16, [1, 1500, 8, 64]> var_337_cast_fp16 = reshape(shape = var_336, x = linear_13_cast_fp16)[name = tensor<string, []>("op_337_cast_fp16")];
            tensor<fp16, [1, 1, 1, 1]> const_47_to_fp16 = const()[name = tensor<string, []>("const_47_to_fp16"), val = tensor<fp16, [1, 1, 1, 1]>([[[[0x1.6ap-2]]]])];
            tensor<fp16, [1, 1500, 8, 64]> k_11_cast_fp16 = mul(x = var_337_cast_fp16, y = const_47_to_fp16)[name = tensor<string, []>("k_11_cast_fp16")];
            tensor<int32, [4]> var_343 = const()[name = tensor<string, []>("op_343"), val = tensor<int32, [4]>([1, 1500, 8, -1])];
            tensor<fp16, [1, 1500, 8, 64]> var_344_cast_fp16 = reshape(shape = var_343, x = linear_14_cast_fp16)[name = tensor<string, []>("op_344_cast_fp16")];
            tensor<int32, [4]> var_345 = const()[name = tensor<string, []>("op_345"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<bool, []> qk_5_transpose_x_0 = const()[name = tensor<string, []>("qk_5_transpose_x_0"), val = tensor<bool, []>(false)];
            tensor<bool, []> qk_5_transpose_y_0 = const()[name = tensor<string, []>("qk_5_transpose_y_0"), val = tensor<bool, []>(false)];
            tensor<int32, [4]> transpose_28_perm_0 = const()[name = tensor<string, []>("transpose_28_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<int32, [4]> transpose_29_perm_0 = const()[name = tensor<string, []>("transpose_29_perm_0"), val = tensor<int32, [4]>([0, 2, 3, 1])];
            tensor<fp16, [1, 8, 64, 1500]> transpose_49 = transpose(perm = transpose_29_perm_0, x = k_11_cast_fp16)[name = tensor<string, []>("transpose_49")];
            tensor<fp16, [1, 8, 1500, 64]> transpose_50 = transpose(perm = transpose_28_perm_0, x = q_11_cast_fp16)[name = tensor<string, []>("transpose_50")];
            tensor<fp16, [1, 8, 1500, 1500]> qk_5_cast_fp16 = matmul(transpose_x = qk_5_transpose_x_0, transpose_y = qk_5_transpose_y_0, x = transpose_50, y = transpose_49)[name = tensor<string, []>("qk_5_cast_fp16")];
            tensor<fp16, [1, 8, 1500, 1500]> var_349_cast_fp16 = softmax(axis = var_284, x = qk_5_cast_fp16)[name = tensor<string, []>("op_349_cast_fp16")];
            tensor<bool, []> var_351_transpose_x_0 = const()[name = tensor<string, []>("op_351_transpose_x_0"), val = tensor<bool, []>(false)];
            tensor<bool, []> var_351_transpose_y_0 = const()[name = tensor<string, []>("op_351_transpose_y_0"), val = tensor<bool, []>(false)];
            tensor<fp16, [1, 8, 1500, 64]> transpose_51 = transpose(perm = var_345, x = var_344_cast_fp16)[name = tensor<string, []>("transpose_51")];
            tensor<fp16, [1, 8, 1500, 64]> var_351_cast_fp16 = matmul(transpose_x = var_351_transpose_x_0, transpose_y = var_351_transpose_y_0, x = var_349_cast_fp16, y = transpose_51)[name = tensor<string, []>("op_351_cast_fp16")];
            tensor<int32, [4]> var_352 = const()[name = tensor<string, []>("op_352"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<int32, [3]> concat_2 = const()[name = tensor<string, []>("concat_2"), val = tensor<int32, [3]>([1, 1500, 512])];
            tensor<fp16, [1, 1500, 8, 64]> transpose_48 = transpose(perm = var_352, x = var_351_cast_fp16)[name = tensor<string, []>("transpose_48")];
            tensor<fp16, [1, 1500, 512]> x_35_cast_fp16 = reshape(shape = concat_2, x = transpose_48)[name = tensor<string, []>("x_35_cast_fp16")];
            tensor<fp16, [512, 512]> var_357_to_fp16 = const()[name = tensor<string, []>("op_357_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(17544960)))];
            tensor<fp16, [512]> var_358_to_fp16 = const()[name = tensor<string, []>("op_358_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(18069312)))];
            tensor<fp16, [1, 1500, 512]> linear_15_cast_fp16 = linear(bias = var_358_to_fp16, weight = var_357_to_fp16, x = x_35_cast_fp16)[name = tensor<string, []>("linear_15_cast_fp16")];
            tensor<fp16, [1, 1500, 512]> x_37_cast_fp16 = add(x = x_31_cast_fp16, y = linear_15_cast_fp16)[name = tensor<string, []>("x_37_cast_fp16")];
            tensor<int32, [1]> var_365_axes_0 = const()[name = tensor<string, []>("op_365_axes_0"), val = tensor<int32, [1]>([-1])];
            tensor<fp16, [512]> blocks_2_mlp_ln_weight_to_fp16 = const()[name = tensor<string, []>("blocks_2_mlp_ln_weight_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(18070400)))];
            tensor<fp16, [512]> blocks_2_mlp_ln_bias_to_fp16 = const()[name = tensor<string, []>("blocks_2_mlp_ln_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(18071488)))];
            tensor<fp16, [1, 1500, 512]> var_365_cast_fp16 = layer_norm(axes = var_365_axes_0, beta = blocks_2_mlp_ln_bias_to_fp16, epsilon = var_290_to_fp16, gamma = blocks_2_mlp_ln_weight_to_fp16, x = x_37_cast_fp16)[name = tensor<string, []>("op_365_cast_fp16")];
            tensor<fp16, [2048, 512]> var_374_to_fp16 = const()[name = tensor<string, []>("op_374_to_fp16"), val = tensor<fp16, [2048, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(18072576)))];
            tensor<fp16, [2048]> var_375_to_fp16 = const()[name = tensor<string, []>("op_375_to_fp16"), val = tensor<fp16, [2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(20169792)))];
            tensor<fp16, [1, 1500, 2048]> linear_16_cast_fp16 = linear(bias = var_375_to_fp16, weight = var_374_to_fp16, x = var_365_cast_fp16)[name = tensor<string, []>("linear_16_cast_fp16")];
            tensor<string, []> x_41_mode_0 = const()[name = tensor<string, []>("x_41_mode_0"), val = tensor<string, []>("EXACT")];
            tensor<fp16, [1, 1500, 2048]> x_41_cast_fp16 = gelu(mode = x_41_mode_0, x = linear_16_cast_fp16)[name = tensor<string, []>("x_41_cast_fp16")];
            tensor<fp16, [512, 2048]> var_380_to_fp16 = const()[name = tensor<string, []>("op_380_to_fp16"), val = tensor<fp16, [512, 2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(20173952)))];
            tensor<fp16, [512]> var_381_to_fp16 = const()[name = tensor<string, []>("op_381_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(22271168)))];
            tensor<fp16, [1, 1500, 512]> linear_17_cast_fp16 = linear(bias = var_381_to_fp16, weight = var_380_to_fp16, x = x_41_cast_fp16)[name = tensor<string, []>("linear_17_cast_fp16")];
            tensor<fp16, [1, 1500, 512]> x_43_cast_fp16 = add(x = x_37_cast_fp16, y = linear_17_cast_fp16)[name = tensor<string, []>("x_43_cast_fp16")];
            tensor<int32, []> var_391 = const()[name = tensor<string, []>("op_391"), val = tensor<int32, []>(-1)];
            tensor<int32, [1]> var_408_axes_0 = const()[name = tensor<string, []>("op_408_axes_0"), val = tensor<int32, [1]>([-1])];
            tensor<fp16, [512]> blocks_3_attn_ln_weight_to_fp16 = const()[name = tensor<string, []>("blocks_3_attn_ln_weight_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(22272256)))];
            tensor<fp16, [512]> blocks_3_attn_ln_bias_to_fp16 = const()[name = tensor<string, []>("blocks_3_attn_ln_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(22273344)))];
            tensor<fp16, []> var_397_to_fp16 = const()[name = tensor<string, []>("op_397_to_fp16"), val = tensor<fp16, []>(0x1.5p-17)];
            tensor<fp16, [1, 1500, 512]> var_408_cast_fp16 = layer_norm(axes = var_408_axes_0, beta = blocks_3_attn_ln_bias_to_fp16, epsilon = var_397_to_fp16, gamma = blocks_3_attn_ln_weight_to_fp16, x = x_43_cast_fp16)[name = tensor<string, []>("op_408_cast_fp16")];
            tensor<fp16, [512, 512]> var_419_to_fp16 = const()[name = tensor<string, []>("op_419_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(22274432)))];
            tensor<fp16, [512]> var_420_to_fp16 = const()[name = tensor<string, []>("op_420_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(22798784)))];
            tensor<fp16, [1, 1500, 512]> linear_18_cast_fp16 = linear(bias = var_420_to_fp16, weight = var_419_to_fp16, x = var_408_cast_fp16)[name = tensor<string, []>("linear_18_cast_fp16")];
            tensor<fp16, [512, 512]> var_423_to_fp16 = const()[name = tensor<string, []>("op_423_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(22799872)))];
            tensor<fp16, [1, 1500, 512]> linear_19_cast_fp16 = linear(bias = linear_1_bias_0_to_fp16, weight = var_423_to_fp16, x = var_408_cast_fp16)[name = tensor<string, []>("linear_19_cast_fp16")];
            tensor<fp16, [512, 512]> var_427_to_fp16 = const()[name = tensor<string, []>("op_427_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(23324224)))];
            tensor<fp16, [512]> var_428_to_fp16 = const()[name = tensor<string, []>("op_428_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(23848576)))];
            tensor<fp16, [1, 1500, 512]> linear_20_cast_fp16 = linear(bias = var_428_to_fp16, weight = var_427_to_fp16, x = var_408_cast_fp16)[name = tensor<string, []>("linear_20_cast_fp16")];
            tensor<int32, [4]> var_436 = const()[name = tensor<string, []>("op_436"), val = tensor<int32, [4]>([1, 1500, 8, -1])];
            tensor<fp16, [1, 1500, 8, 64]> var_437_cast_fp16 = reshape(shape = var_436, x = linear_18_cast_fp16)[name = tensor<string, []>("op_437_cast_fp16")];
            tensor<fp16, [1, 1, 1, 1]> const_48_to_fp16 = const()[name = tensor<string, []>("const_48_to_fp16"), val = tensor<fp16, [1, 1, 1, 1]>([[[[0x1.6ap-2]]]])];
            tensor<fp16, [1, 1500, 8, 64]> q_15_cast_fp16 = mul(x = var_437_cast_fp16, y = const_48_to_fp16)[name = tensor<string, []>("q_15_cast_fp16")];
            tensor<int32, [4]> var_443 = const()[name = tensor<string, []>("op_443"), val = tensor<int32, [4]>([1, 1500, 8, -1])];
            tensor<fp16, [1, 1500, 8, 64]> var_444_cast_fp16 = reshape(shape = var_443, x = linear_19_cast_fp16)[name = tensor<string, []>("op_444_cast_fp16")];
            tensor<fp16, [1, 1, 1, 1]> const_49_to_fp16 = const()[name = tensor<string, []>("const_49_to_fp16"), val = tensor<fp16, [1, 1, 1, 1]>([[[[0x1.6ap-2]]]])];
            tensor<fp16, [1, 1500, 8, 64]> k_15_cast_fp16 = mul(x = var_444_cast_fp16, y = const_49_to_fp16)[name = tensor<string, []>("k_15_cast_fp16")];
            tensor<int32, [4]> var_450 = const()[name = tensor<string, []>("op_450"), val = tensor<int32, [4]>([1, 1500, 8, -1])];
            tensor<fp16, [1, 1500, 8, 64]> var_451_cast_fp16 = reshape(shape = var_450, x = linear_20_cast_fp16)[name = tensor<string, []>("op_451_cast_fp16")];
            tensor<int32, [4]> var_452 = const()[name = tensor<string, []>("op_452"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<bool, []> qk_7_transpose_x_0 = const()[name = tensor<string, []>("qk_7_transpose_x_0"), val = tensor<bool, []>(false)];
            tensor<bool, []> qk_7_transpose_y_0 = const()[name = tensor<string, []>("qk_7_transpose_y_0"), val = tensor<bool, []>(false)];
            tensor<int32, [4]> transpose_30_perm_0 = const()[name = tensor<string, []>("transpose_30_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<int32, [4]> transpose_31_perm_0 = const()[name = tensor<string, []>("transpose_31_perm_0"), val = tensor<int32, [4]>([0, 2, 3, 1])];
            tensor<fp16, [1, 8, 64, 1500]> transpose_45 = transpose(perm = transpose_31_perm_0, x = k_15_cast_fp16)[name = tensor<string, []>("transpose_45")];
            tensor<fp16, [1, 8, 1500, 64]> transpose_46 = transpose(perm = transpose_30_perm_0, x = q_15_cast_fp16)[name = tensor<string, []>("transpose_46")];
            tensor<fp16, [1, 8, 1500, 1500]> qk_7_cast_fp16 = matmul(transpose_x = qk_7_transpose_x_0, transpose_y = qk_7_transpose_y_0, x = transpose_46, y = transpose_45)[name = tensor<string, []>("qk_7_cast_fp16")];
            tensor<fp16, [1, 8, 1500, 1500]> var_456_cast_fp16 = softmax(axis = var_391, x = qk_7_cast_fp16)[name = tensor<string, []>("op_456_cast_fp16")];
            tensor<bool, []> var_458_transpose_x_0 = const()[name = tensor<string, []>("op_458_transpose_x_0"), val = tensor<bool, []>(false)];
            tensor<bool, []> var_458_transpose_y_0 = const()[name = tensor<string, []>("op_458_transpose_y_0"), val = tensor<bool, []>(false)];
            tensor<fp16, [1, 8, 1500, 64]> transpose_47 = transpose(perm = var_452, x = var_451_cast_fp16)[name = tensor<string, []>("transpose_47")];
            tensor<fp16, [1, 8, 1500, 64]> var_458_cast_fp16 = matmul(transpose_x = var_458_transpose_x_0, transpose_y = var_458_transpose_y_0, x = var_456_cast_fp16, y = transpose_47)[name = tensor<string, []>("op_458_cast_fp16")];
            tensor<int32, [4]> var_459 = const()[name = tensor<string, []>("op_459"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<int32, [3]> concat_3 = const()[name = tensor<string, []>("concat_3"), val = tensor<int32, [3]>([1, 1500, 512])];
            tensor<fp16, [1, 1500, 8, 64]> transpose_44 = transpose(perm = var_459, x = var_458_cast_fp16)[name = tensor<string, []>("transpose_44")];
            tensor<fp16, [1, 1500, 512]> x_47_cast_fp16 = reshape(shape = concat_3, x = transpose_44)[name = tensor<string, []>("x_47_cast_fp16")];
            tensor<fp16, [512, 512]> var_464_to_fp16 = const()[name = tensor<string, []>("op_464_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(23849664)))];
            tensor<fp16, [512]> var_465_to_fp16 = const()[name = tensor<string, []>("op_465_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(24374016)))];
            tensor<fp16, [1, 1500, 512]> linear_21_cast_fp16 = linear(bias = var_465_to_fp16, weight = var_464_to_fp16, x = x_47_cast_fp16)[name = tensor<string, []>("linear_21_cast_fp16")];
            tensor<fp16, [1, 1500, 512]> x_49_cast_fp16 = add(x = x_43_cast_fp16, y = linear_21_cast_fp16)[name = tensor<string, []>("x_49_cast_fp16")];
            tensor<int32, [1]> var_472_axes_0 = const()[name = tensor<string, []>("op_472_axes_0"), val = tensor<int32, [1]>([-1])];
            tensor<fp16, [512]> blocks_3_mlp_ln_weight_to_fp16 = const()[name = tensor<string, []>("blocks_3_mlp_ln_weight_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(24375104)))];
            tensor<fp16, [512]> blocks_3_mlp_ln_bias_to_fp16 = const()[name = tensor<string, []>("blocks_3_mlp_ln_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(24376192)))];
            tensor<fp16, [1, 1500, 512]> var_472_cast_fp16 = layer_norm(axes = var_472_axes_0, beta = blocks_3_mlp_ln_bias_to_fp16, epsilon = var_397_to_fp16, gamma = blocks_3_mlp_ln_weight_to_fp16, x = x_49_cast_fp16)[name = tensor<string, []>("op_472_cast_fp16")];
            tensor<fp16, [2048, 512]> var_481_to_fp16 = const()[name = tensor<string, []>("op_481_to_fp16"), val = tensor<fp16, [2048, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(24377280)))];
            tensor<fp16, [2048]> var_482_to_fp16 = const()[name = tensor<string, []>("op_482_to_fp16"), val = tensor<fp16, [2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(26474496)))];
            tensor<fp16, [1, 1500, 2048]> linear_22_cast_fp16 = linear(bias = var_482_to_fp16, weight = var_481_to_fp16, x = var_472_cast_fp16)[name = tensor<string, []>("linear_22_cast_fp16")];
            tensor<string, []> x_53_mode_0 = const()[name = tensor<string, []>("x_53_mode_0"), val = tensor<string, []>("EXACT")];
            tensor<fp16, [1, 1500, 2048]> x_53_cast_fp16 = gelu(mode = x_53_mode_0, x = linear_22_cast_fp16)[name = tensor<string, []>("x_53_cast_fp16")];
            tensor<fp16, [512, 2048]> var_487_to_fp16 = const()[name = tensor<string, []>("op_487_to_fp16"), val = tensor<fp16, [512, 2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(26478656)))];
            tensor<fp16, [512]> var_488_to_fp16 = const()[name = tensor<string, []>("op_488_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(28575872)))];
            tensor<fp16, [1, 1500, 512]> linear_23_cast_fp16 = linear(bias = var_488_to_fp16, weight = var_487_to_fp16, x = x_53_cast_fp16)[name = tensor<string, []>("linear_23_cast_fp16")];
            tensor<fp16, [1, 1500, 512]> x_55_cast_fp16 = add(x = x_49_cast_fp16, y = linear_23_cast_fp16)[name = tensor<string, []>("x_55_cast_fp16")];
            tensor<int32, []> var_498 = const()[name = tensor<string, []>("op_498"), val = tensor<int32, []>(-1)];
            tensor<int32, [1]> var_515_axes_0 = const()[name = tensor<string, []>("op_515_axes_0"), val = tensor<int32, [1]>([-1])];
            tensor<fp16, [512]> blocks_4_attn_ln_weight_to_fp16 = const()[name = tensor<string, []>("blocks_4_attn_ln_weight_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(28576960)))];
            tensor<fp16, [512]> blocks_4_attn_ln_bias_to_fp16 = const()[name = tensor<string, []>("blocks_4_attn_ln_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(28578048)))];
            tensor<fp16, []> var_504_to_fp16 = const()[name = tensor<string, []>("op_504_to_fp16"), val = tensor<fp16, []>(0x1.5p-17)];
            tensor<fp16, [1, 1500, 512]> var_515_cast_fp16 = layer_norm(axes = var_515_axes_0, beta = blocks_4_attn_ln_bias_to_fp16, epsilon = var_504_to_fp16, gamma = blocks_4_attn_ln_weight_to_fp16, x = x_55_cast_fp16)[name = tensor<string, []>("op_515_cast_fp16")];
            tensor<fp16, [512, 512]> var_526_to_fp16 = const()[name = tensor<string, []>("op_526_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(28579136)))];
            tensor<fp16, [512]> var_527_to_fp16 = const()[name = tensor<string, []>("op_527_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(29103488)))];
            tensor<fp16, [1, 1500, 512]> linear_24_cast_fp16 = linear(bias = var_527_to_fp16, weight = var_526_to_fp16, x = var_515_cast_fp16)[name = tensor<string, []>("linear_24_cast_fp16")];
            tensor<fp16, [512, 512]> var_530_to_fp16 = const()[name = tensor<string, []>("op_530_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(29104576)))];
            tensor<fp16, [1, 1500, 512]> linear_25_cast_fp16 = linear(bias = linear_1_bias_0_to_fp16, weight = var_530_to_fp16, x = var_515_cast_fp16)[name = tensor<string, []>("linear_25_cast_fp16")];
            tensor<fp16, [512, 512]> var_534_to_fp16 = const()[name = tensor<string, []>("op_534_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(29628928)))];
            tensor<fp16, [512]> var_535_to_fp16 = const()[name = tensor<string, []>("op_535_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(30153280)))];
            tensor<fp16, [1, 1500, 512]> linear_26_cast_fp16 = linear(bias = var_535_to_fp16, weight = var_534_to_fp16, x = var_515_cast_fp16)[name = tensor<string, []>("linear_26_cast_fp16")];
            tensor<int32, [4]> var_543 = const()[name = tensor<string, []>("op_543"), val = tensor<int32, [4]>([1, 1500, 8, -1])];
            tensor<fp16, [1, 1500, 8, 64]> var_544_cast_fp16 = reshape(shape = var_543, x = linear_24_cast_fp16)[name = tensor<string, []>("op_544_cast_fp16")];
            tensor<fp16, [1, 1, 1, 1]> const_50_to_fp16 = const()[name = tensor<string, []>("const_50_to_fp16"), val = tensor<fp16, [1, 1, 1, 1]>([[[[0x1.6ap-2]]]])];
            tensor<fp16, [1, 1500, 8, 64]> q_19_cast_fp16 = mul(x = var_544_cast_fp16, y = const_50_to_fp16)[name = tensor<string, []>("q_19_cast_fp16")];
            tensor<int32, [4]> var_550 = const()[name = tensor<string, []>("op_550"), val = tensor<int32, [4]>([1, 1500, 8, -1])];
            tensor<fp16, [1, 1500, 8, 64]> var_551_cast_fp16 = reshape(shape = var_550, x = linear_25_cast_fp16)[name = tensor<string, []>("op_551_cast_fp16")];
            tensor<fp16, [1, 1, 1, 1]> const_51_to_fp16 = const()[name = tensor<string, []>("const_51_to_fp16"), val = tensor<fp16, [1, 1, 1, 1]>([[[[0x1.6ap-2]]]])];
            tensor<fp16, [1, 1500, 8, 64]> k_19_cast_fp16 = mul(x = var_551_cast_fp16, y = const_51_to_fp16)[name = tensor<string, []>("k_19_cast_fp16")];
            tensor<int32, [4]> var_557 = const()[name = tensor<string, []>("op_557"), val = tensor<int32, [4]>([1, 1500, 8, -1])];
            tensor<fp16, [1, 1500, 8, 64]> var_558_cast_fp16 = reshape(shape = var_557, x = linear_26_cast_fp16)[name = tensor<string, []>("op_558_cast_fp16")];
            tensor<int32, [4]> var_559 = const()[name = tensor<string, []>("op_559"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<bool, []> qk_9_transpose_x_0 = const()[name = tensor<string, []>("qk_9_transpose_x_0"), val = tensor<bool, []>(false)];
            tensor<bool, []> qk_9_transpose_y_0 = const()[name = tensor<string, []>("qk_9_transpose_y_0"), val = tensor<bool, []>(false)];
            tensor<int32, [4]> transpose_32_perm_0 = const()[name = tensor<string, []>("transpose_32_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<int32, [4]> transpose_33_perm_0 = const()[name = tensor<string, []>("transpose_33_perm_0"), val = tensor<int32, [4]>([0, 2, 3, 1])];
            tensor<fp16, [1, 8, 64, 1500]> transpose_41 = transpose(perm = transpose_33_perm_0, x = k_19_cast_fp16)[name = tensor<string, []>("transpose_41")];
            tensor<fp16, [1, 8, 1500, 64]> transpose_42 = transpose(perm = transpose_32_perm_0, x = q_19_cast_fp16)[name = tensor<string, []>("transpose_42")];
            tensor<fp16, [1, 8, 1500, 1500]> qk_9_cast_fp16 = matmul(transpose_x = qk_9_transpose_x_0, transpose_y = qk_9_transpose_y_0, x = transpose_42, y = transpose_41)[name = tensor<string, []>("qk_9_cast_fp16")];
            tensor<fp16, [1, 8, 1500, 1500]> var_563_cast_fp16 = softmax(axis = var_498, x = qk_9_cast_fp16)[name = tensor<string, []>("op_563_cast_fp16")];
            tensor<bool, []> var_565_transpose_x_0 = const()[name = tensor<string, []>("op_565_transpose_x_0"), val = tensor<bool, []>(false)];
            tensor<bool, []> var_565_transpose_y_0 = const()[name = tensor<string, []>("op_565_transpose_y_0"), val = tensor<bool, []>(false)];
            tensor<fp16, [1, 8, 1500, 64]> transpose_43 = transpose(perm = var_559, x = var_558_cast_fp16)[name = tensor<string, []>("transpose_43")];
            tensor<fp16, [1, 8, 1500, 64]> var_565_cast_fp16 = matmul(transpose_x = var_565_transpose_x_0, transpose_y = var_565_transpose_y_0, x = var_563_cast_fp16, y = transpose_43)[name = tensor<string, []>("op_565_cast_fp16")];
            tensor<int32, [4]> var_566 = const()[name = tensor<string, []>("op_566"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<int32, [3]> concat_4 = const()[name = tensor<string, []>("concat_4"), val = tensor<int32, [3]>([1, 1500, 512])];
            tensor<fp16, [1, 1500, 8, 64]> transpose_40 = transpose(perm = var_566, x = var_565_cast_fp16)[name = tensor<string, []>("transpose_40")];
            tensor<fp16, [1, 1500, 512]> x_59_cast_fp16 = reshape(shape = concat_4, x = transpose_40)[name = tensor<string, []>("x_59_cast_fp16")];
            tensor<fp16, [512, 512]> var_571_to_fp16 = const()[name = tensor<string, []>("op_571_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(30154368)))];
            tensor<fp16, [512]> var_572_to_fp16 = const()[name = tensor<string, []>("op_572_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(30678720)))];
            tensor<fp16, [1, 1500, 512]> linear_27_cast_fp16 = linear(bias = var_572_to_fp16, weight = var_571_to_fp16, x = x_59_cast_fp16)[name = tensor<string, []>("linear_27_cast_fp16")];
            tensor<fp16, [1, 1500, 512]> x_61_cast_fp16 = add(x = x_55_cast_fp16, y = linear_27_cast_fp16)[name = tensor<string, []>("x_61_cast_fp16")];
            tensor<int32, [1]> var_579_axes_0 = const()[name = tensor<string, []>("op_579_axes_0"), val = tensor<int32, [1]>([-1])];
            tensor<fp16, [512]> blocks_4_mlp_ln_weight_to_fp16 = const()[name = tensor<string, []>("blocks_4_mlp_ln_weight_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(30679808)))];
            tensor<fp16, [512]> blocks_4_mlp_ln_bias_to_fp16 = const()[name = tensor<string, []>("blocks_4_mlp_ln_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(30680896)))];
            tensor<fp16, [1, 1500, 512]> var_579_cast_fp16 = layer_norm(axes = var_579_axes_0, beta = blocks_4_mlp_ln_bias_to_fp16, epsilon = var_504_to_fp16, gamma = blocks_4_mlp_ln_weight_to_fp16, x = x_61_cast_fp16)[name = tensor<string, []>("op_579_cast_fp16")];
            tensor<fp16, [2048, 512]> var_588_to_fp16 = const()[name = tensor<string, []>("op_588_to_fp16"), val = tensor<fp16, [2048, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(30681984)))];
            tensor<fp16, [2048]> var_589_to_fp16 = const()[name = tensor<string, []>("op_589_to_fp16"), val = tensor<fp16, [2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(32779200)))];
            tensor<fp16, [1, 1500, 2048]> linear_28_cast_fp16 = linear(bias = var_589_to_fp16, weight = var_588_to_fp16, x = var_579_cast_fp16)[name = tensor<string, []>("linear_28_cast_fp16")];
            tensor<string, []> x_65_mode_0 = const()[name = tensor<string, []>("x_65_mode_0"), val = tensor<string, []>("EXACT")];
            tensor<fp16, [1, 1500, 2048]> x_65_cast_fp16 = gelu(mode = x_65_mode_0, x = linear_28_cast_fp16)[name = tensor<string, []>("x_65_cast_fp16")];
            tensor<fp16, [512, 2048]> var_594_to_fp16 = const()[name = tensor<string, []>("op_594_to_fp16"), val = tensor<fp16, [512, 2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(32783360)))];
            tensor<fp16, [512]> var_595_to_fp16 = const()[name = tensor<string, []>("op_595_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(34880576)))];
            tensor<fp16, [1, 1500, 512]> linear_29_cast_fp16 = linear(bias = var_595_to_fp16, weight = var_594_to_fp16, x = x_65_cast_fp16)[name = tensor<string, []>("linear_29_cast_fp16")];
            tensor<fp16, [1, 1500, 512]> x_67_cast_fp16 = add(x = x_61_cast_fp16, y = linear_29_cast_fp16)[name = tensor<string, []>("x_67_cast_fp16")];
            tensor<int32, []> var_605 = const()[name = tensor<string, []>("op_605"), val = tensor<int32, []>(-1)];
            tensor<int32, [1]> var_622_axes_0 = const()[name = tensor<string, []>("op_622_axes_0"), val = tensor<int32, [1]>([-1])];
            tensor<fp16, [512]> blocks_5_attn_ln_weight_to_fp16 = const()[name = tensor<string, []>("blocks_5_attn_ln_weight_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(34881664)))];
            tensor<fp16, [512]> blocks_5_attn_ln_bias_to_fp16 = const()[name = tensor<string, []>("blocks_5_attn_ln_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(34882752)))];
            tensor<fp16, []> var_611_to_fp16 = const()[name = tensor<string, []>("op_611_to_fp16"), val = tensor<fp16, []>(0x1.5p-17)];
            tensor<fp16, [1, 1500, 512]> var_622_cast_fp16 = layer_norm(axes = var_622_axes_0, beta = blocks_5_attn_ln_bias_to_fp16, epsilon = var_611_to_fp16, gamma = blocks_5_attn_ln_weight_to_fp16, x = x_67_cast_fp16)[name = tensor<string, []>("op_622_cast_fp16")];
            tensor<fp16, [512, 512]> var_633_to_fp16 = const()[name = tensor<string, []>("op_633_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(34883840)))];
            tensor<fp16, [512]> var_634_to_fp16 = const()[name = tensor<string, []>("op_634_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(35408192)))];
            tensor<fp16, [1, 1500, 512]> linear_30_cast_fp16 = linear(bias = var_634_to_fp16, weight = var_633_to_fp16, x = var_622_cast_fp16)[name = tensor<string, []>("linear_30_cast_fp16")];
            tensor<fp16, [512, 512]> var_637_to_fp16 = const()[name = tensor<string, []>("op_637_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(35409280)))];
            tensor<fp16, [1, 1500, 512]> linear_31_cast_fp16 = linear(bias = linear_1_bias_0_to_fp16, weight = var_637_to_fp16, x = var_622_cast_fp16)[name = tensor<string, []>("linear_31_cast_fp16")];
            tensor<fp16, [512, 512]> var_641_to_fp16 = const()[name = tensor<string, []>("op_641_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(35933632)))];
            tensor<fp16, [512]> var_642_to_fp16 = const()[name = tensor<string, []>("op_642_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(36457984)))];
            tensor<fp16, [1, 1500, 512]> linear_32_cast_fp16 = linear(bias = var_642_to_fp16, weight = var_641_to_fp16, x = var_622_cast_fp16)[name = tensor<string, []>("linear_32_cast_fp16")];
            tensor<int32, [4]> var_650 = const()[name = tensor<string, []>("op_650"), val = tensor<int32, [4]>([1, 1500, 8, -1])];
            tensor<fp16, [1, 1500, 8, 64]> var_651_cast_fp16 = reshape(shape = var_650, x = linear_30_cast_fp16)[name = tensor<string, []>("op_651_cast_fp16")];
            tensor<fp16, [1, 1, 1, 1]> const_52_to_fp16 = const()[name = tensor<string, []>("const_52_to_fp16"), val = tensor<fp16, [1, 1, 1, 1]>([[[[0x1.6ap-2]]]])];
            tensor<fp16, [1, 1500, 8, 64]> q_cast_fp16 = mul(x = var_651_cast_fp16, y = const_52_to_fp16)[name = tensor<string, []>("q_cast_fp16")];
            tensor<int32, [4]> var_657 = const()[name = tensor<string, []>("op_657"), val = tensor<int32, [4]>([1, 1500, 8, -1])];
            tensor<fp16, [1, 1500, 8, 64]> var_658_cast_fp16 = reshape(shape = var_657, x = linear_31_cast_fp16)[name = tensor<string, []>("op_658_cast_fp16")];
            tensor<fp16, [1, 1, 1, 1]> const_53_to_fp16 = const()[name = tensor<string, []>("const_53_to_fp16"), val = tensor<fp16, [1, 1, 1, 1]>([[[[0x1.6ap-2]]]])];
            tensor<fp16, [1, 1500, 8, 64]> k_cast_fp16 = mul(x = var_658_cast_fp16, y = const_53_to_fp16)[name = tensor<string, []>("k_cast_fp16")];
            tensor<int32, [4]> var_664 = const()[name = tensor<string, []>("op_664"), val = tensor<int32, [4]>([1, 1500, 8, -1])];
            tensor<fp16, [1, 1500, 8, 64]> var_665_cast_fp16 = reshape(shape = var_664, x = linear_32_cast_fp16)[name = tensor<string, []>("op_665_cast_fp16")];
            tensor<int32, [4]> var_666 = const()[name = tensor<string, []>("op_666"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<bool, []> qk_transpose_x_0 = const()[name = tensor<string, []>("qk_transpose_x_0"), val = tensor<bool, []>(false)];
            tensor<bool, []> qk_transpose_y_0 = const()[name = tensor<string, []>("qk_transpose_y_0"), val = tensor<bool, []>(false)];
            tensor<int32, [4]> transpose_34_perm_0 = const()[name = tensor<string, []>("transpose_34_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<int32, [4]> transpose_35_perm_0 = const()[name = tensor<string, []>("transpose_35_perm_0"), val = tensor<int32, [4]>([0, 2, 3, 1])];
            tensor<fp16, [1, 8, 64, 1500]> transpose_37 = transpose(perm = transpose_35_perm_0, x = k_cast_fp16)[name = tensor<string, []>("transpose_37")];
            tensor<fp16, [1, 8, 1500, 64]> transpose_38 = transpose(perm = transpose_34_perm_0, x = q_cast_fp16)[name = tensor<string, []>("transpose_38")];
            tensor<fp16, [1, 8, 1500, 1500]> qk_cast_fp16 = matmul(transpose_x = qk_transpose_x_0, transpose_y = qk_transpose_y_0, x = transpose_38, y = transpose_37)[name = tensor<string, []>("qk_cast_fp16")];
            tensor<fp16, [1, 8, 1500, 1500]> var_670_cast_fp16 = softmax(axis = var_605, x = qk_cast_fp16)[name = tensor<string, []>("op_670_cast_fp16")];
            tensor<bool, []> var_672_transpose_x_0 = const()[name = tensor<string, []>("op_672_transpose_x_0"), val = tensor<bool, []>(false)];
            tensor<bool, []> var_672_transpose_y_0 = const()[name = tensor<string, []>("op_672_transpose_y_0"), val = tensor<bool, []>(false)];
            tensor<fp16, [1, 8, 1500, 64]> transpose_39 = transpose(perm = var_666, x = var_665_cast_fp16)[name = tensor<string, []>("transpose_39")];
            tensor<fp16, [1, 8, 1500, 64]> var_672_cast_fp16 = matmul(transpose_x = var_672_transpose_x_0, transpose_y = var_672_transpose_y_0, x = var_670_cast_fp16, y = transpose_39)[name = tensor<string, []>("op_672_cast_fp16")];
            tensor<int32, [4]> var_673 = const()[name = tensor<string, []>("op_673"), val = tensor<int32, [4]>([0, 2, 1, 3])];
            tensor<int32, [3]> concat_5 = const()[name = tensor<string, []>("concat_5"), val = tensor<int32, [3]>([1, 1500, 512])];
            tensor<fp16, [1, 1500, 8, 64]> transpose_36 = transpose(perm = var_673, x = var_672_cast_fp16)[name = tensor<string, []>("transpose_36")];
            tensor<fp16, [1, 1500, 512]> x_71_cast_fp16 = reshape(shape = concat_5, x = transpose_36)[name = tensor<string, []>("x_71_cast_fp16")];
            tensor<fp16, [512, 512]> var_678_to_fp16 = const()[name = tensor<string, []>("op_678_to_fp16"), val = tensor<fp16, [512, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(36459072)))];
            tensor<fp16, [512]> var_679_to_fp16 = const()[name = tensor<string, []>("op_679_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(36983424)))];
            tensor<fp16, [1, 1500, 512]> linear_33_cast_fp16 = linear(bias = var_679_to_fp16, weight = var_678_to_fp16, x = x_71_cast_fp16)[name = tensor<string, []>("linear_33_cast_fp16")];
            tensor<fp16, [1, 1500, 512]> x_73_cast_fp16 = add(x = x_67_cast_fp16, y = linear_33_cast_fp16)[name = tensor<string, []>("x_73_cast_fp16")];
            tensor<int32, [1]> var_686_axes_0 = const()[name = tensor<string, []>("op_686_axes_0"), val = tensor<int32, [1]>([-1])];
            tensor<fp16, [512]> blocks_5_mlp_ln_weight_to_fp16 = const()[name = tensor<string, []>("blocks_5_mlp_ln_weight_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(36984512)))];
            tensor<fp16, [512]> blocks_5_mlp_ln_bias_to_fp16 = const()[name = tensor<string, []>("blocks_5_mlp_ln_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(36985600)))];
            tensor<fp16, [1, 1500, 512]> var_686_cast_fp16 = layer_norm(axes = var_686_axes_0, beta = blocks_5_mlp_ln_bias_to_fp16, epsilon = var_611_to_fp16, gamma = blocks_5_mlp_ln_weight_to_fp16, x = x_73_cast_fp16)[name = tensor<string, []>("op_686_cast_fp16")];
            tensor<fp16, [2048, 512]> var_695_to_fp16 = const()[name = tensor<string, []>("op_695_to_fp16"), val = tensor<fp16, [2048, 512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(36986688)))];
            tensor<fp16, [2048]> var_696_to_fp16 = const()[name = tensor<string, []>("op_696_to_fp16"), val = tensor<fp16, [2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(39083904)))];
            tensor<fp16, [1, 1500, 2048]> linear_34_cast_fp16 = linear(bias = var_696_to_fp16, weight = var_695_to_fp16, x = var_686_cast_fp16)[name = tensor<string, []>("linear_34_cast_fp16")];
            tensor<string, []> x_77_mode_0 = const()[name = tensor<string, []>("x_77_mode_0"), val = tensor<string, []>("EXACT")];
            tensor<fp16, [1, 1500, 2048]> x_77_cast_fp16 = gelu(mode = x_77_mode_0, x = linear_34_cast_fp16)[name = tensor<string, []>("x_77_cast_fp16")];
            tensor<fp16, [512, 2048]> var_701_to_fp16 = const()[name = tensor<string, []>("op_701_to_fp16"), val = tensor<fp16, [512, 2048]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(39088064)))];
            tensor<fp16, [512]> var_702_to_fp16 = const()[name = tensor<string, []>("op_702_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(41185280)))];
            tensor<fp16, [1, 1500, 512]> linear_35_cast_fp16 = linear(bias = var_702_to_fp16, weight = var_701_to_fp16, x = x_77_cast_fp16)[name = tensor<string, []>("linear_35_cast_fp16")];
            tensor<fp16, [1, 1500, 512]> x_cast_fp16 = add(x = x_73_cast_fp16, y = linear_35_cast_fp16)[name = tensor<string, []>("x_cast_fp16")];
            tensor<int32, [1]> var_716_axes_0 = const()[name = tensor<string, []>("op_716_axes_0"), val = tensor<int32, [1]>([-1])];
            tensor<fp16, [512]> ln_post_weight_to_fp16 = const()[name = tensor<string, []>("ln_post_weight_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(41186368)))];
            tensor<fp16, [512]> ln_post_bias_to_fp16 = const()[name = tensor<string, []>("ln_post_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(41187456)))];
            tensor<fp16, []> var_707_to_fp16 = const()[name = tensor<string, []>("op_707_to_fp16"), val = tensor<fp16, []>(0x1.5p-17)];
            tensor<fp16, [1, 1500, 512]> var_716_cast_fp16 = layer_norm(axes = var_716_axes_0, beta = ln_post_bias_to_fp16, epsilon = var_707_to_fp16, gamma = ln_post_weight_to_fp16, x = x_cast_fp16)[name = tensor<string, []>("op_716_cast_fp16")];
            tensor<string, []> var_716_cast_fp16_to_fp32_dtype_0 = const()[name = tensor<string, []>("op_716_cast_fp16_to_fp32_dtype_0"), val = tensor<string, []>("fp32")];
            tensor<fp32, [1, 1500, 512]> output = cast(dtype = var_716_cast_fp16_to_fp32_dtype_0, x = var_716_cast_fp16)[name = tensor<string, []>("cast_36")];
        } -> (output);
}