| program(1.0) | |
| [buildInfo = dict<tensor<string, []>, tensor<string, []>>({{"coremlc-component-MIL", "4.28.4"}, {"coremlc-version", "1436.100.10"}})] | |
| { | |
| 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_187 = cast(dtype = logmel_data_to_fp16_dtype_0, x = logmel_data); | |
| tensor<fp16, [1, 512, 3000]> var_32_cast = 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_187); | |
| 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 = gelu(mode = input_1_mode_0, x = var_32_cast); | |
| 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 = 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); | |
| 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 = gelu(mode = x_3_mode_0, x = var_49_cast); | |
| 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_48 = transpose(perm = var_54, x = x_3_cast); | |
| tensor<fp16, [1, 1500, 512]> var_57_cast = add(x = transpose_48, y = positional_embedding_to_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 = 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); | |
| 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]> q_1_cast = linear(bias = var_99_to_fp16, weight = var_98_to_fp16, x = var_87_cast); | |
| 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]> k_1_bias_0_to_fp16 = const()[name = tensor<string, []>("k_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]> k_1_cast = linear(bias = k_1_bias_0_to_fp16, weight = var_102_to_fp16, x = var_87_cast); | |
| 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]> v_1_cast = linear(bias = var_107_to_fp16, weight = var_106_to_fp16, x = var_87_cast); | |
| 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 = reshape(shape = var_115, x = q_1_cast); | |
| 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 = mul(x = var_116_cast, y = const_42_to_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 = reshape(shape = var_122, x = k_1_cast); | |
| 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 = mul(x = var_123_cast, y = const_43_to_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 = reshape(shape = var_129, x = v_1_cast); | |
| 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_12_perm_0 = const()[name = tensor<string, []>("transpose_12_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; | |
| tensor<int32, [4]> transpose_13_perm_0 = const()[name = tensor<string, []>("transpose_13_perm_0"), val = tensor<int32, [4]>([0, 2, 3, 1])]; | |
| tensor<fp16, [1, 8, 64, 1500]> transpose_45 = transpose(perm = transpose_13_perm_0, x = k_3_cast); | |
| tensor<fp16, [1, 8, 1500, 64]> transpose_46 = transpose(perm = transpose_12_perm_0, x = q_3_cast); | |
| tensor<fp16, [1, 8, 1500, 1500]> qk_1_cast = matmul(transpose_x = qk_1_transpose_x_0, transpose_y = qk_1_transpose_y_0, x = transpose_46, y = transpose_45); | |
| tensor<fp16, [1, 8, 1500, 1500]> var_135_cast = softmax(axis = var_70, x = qk_1_cast); | |
| 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_47 = transpose(perm = var_131, x = var_130_cast); | |
| tensor<fp16, [1, 8, 1500, 64]> var_137_cast = matmul(transpose_x = var_137_transpose_x_0, transpose_y = var_137_transpose_y_0, x = var_135_cast, y = transpose_47); | |
| 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_44 = transpose(perm = var_138, x = var_137_cast); | |
| tensor<fp16, [1, 1500, 512]> x_11_cast = reshape(shape = concat_0, x = transpose_44); | |
| 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]> var_145_cast = linear(bias = var_144_to_fp16, weight = var_143_to_fp16, x = x_11_cast); | |
| tensor<fp16, [1, 1500, 512]> x_13_cast = add(x = var_57_cast, y = var_145_cast); | |
| 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 = 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); | |
| 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]> input_9_cast = linear(bias = var_161_to_fp16, weight = var_160_to_fp16, x = var_151_cast); | |
| 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 = gelu(mode = x_17_mode_0, x = input_9_cast); | |
| 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]> var_168_cast = linear(bias = var_167_to_fp16, weight = var_166_to_fp16, x = x_17_cast); | |
| tensor<fp16, [1, 1500, 512]> x_19_cast = add(x = x_13_cast, y = var_168_cast); | |
| 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 = 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); | |
| 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]> q_5_cast = linear(bias = var_206_to_fp16, weight = var_205_to_fp16, x = var_194_cast); | |
| 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, [512]> k_5_bias_0_to_fp16 = const()[name = tensor<string, []>("k_5_bias_0_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(10714816)))]; | |
| tensor<fp16, [1, 1500, 512]> k_5_cast = linear(bias = k_5_bias_0_to_fp16, weight = var_209_to_fp16, x = var_194_cast); | |
| 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, []>(10715904)))]; | |
| 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, []>(11240256)))]; | |
| tensor<fp16, [1, 1500, 512]> v_5_cast = linear(bias = var_214_to_fp16, weight = var_213_to_fp16, x = var_194_cast); | |
| 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 = reshape(shape = var_222, x = q_5_cast); | |
| 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 = mul(x = var_223_cast, y = const_44_to_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 = reshape(shape = var_229, x = k_5_cast); | |
| 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 = mul(x = var_230_cast, y = const_45_to_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 = reshape(shape = var_236, x = v_5_cast); | |
| 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_14_perm_0 = const()[name = tensor<string, []>("transpose_14_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; | |
| tensor<int32, [4]> transpose_15_perm_0 = const()[name = tensor<string, []>("transpose_15_perm_0"), val = tensor<int32, [4]>([0, 2, 3, 1])]; | |
| tensor<fp16, [1, 8, 64, 1500]> transpose_41 = transpose(perm = transpose_15_perm_0, x = k_7_cast); | |
| tensor<fp16, [1, 8, 1500, 64]> transpose_42 = transpose(perm = transpose_14_perm_0, x = q_7_cast); | |
| tensor<fp16, [1, 8, 1500, 1500]> qk_3_cast = matmul(transpose_x = qk_3_transpose_x_0, transpose_y = qk_3_transpose_y_0, x = transpose_42, y = transpose_41); | |
| tensor<fp16, [1, 8, 1500, 1500]> var_242_cast = softmax(axis = var_177, x = qk_3_cast); | |
| 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_43 = transpose(perm = var_238, x = var_237_cast); | |
| tensor<fp16, [1, 8, 1500, 64]> var_244_cast = matmul(transpose_x = var_244_transpose_x_0, transpose_y = var_244_transpose_y_0, x = var_242_cast, y = transpose_43); | |
| 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_40 = transpose(perm = var_245, x = var_244_cast); | |
| tensor<fp16, [1, 1500, 512]> x_23_cast = reshape(shape = concat_1, x = transpose_40); | |
| 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, []>(11241344)))]; | |
| 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, []>(11765696)))]; | |
| tensor<fp16, [1, 1500, 512]> var_252_cast = linear(bias = var_251_to_fp16, weight = var_250_to_fp16, x = x_23_cast); | |
| tensor<fp16, [1, 1500, 512]> x_25_cast = add(x = x_19_cast, y = var_252_cast); | |
| 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, []>(11766784)))]; | |
| 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, []>(11767872)))]; | |
| tensor<fp16, [1, 1500, 512]> var_258_cast = 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); | |
| 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, []>(11768960)))]; | |
| 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, []>(13866176)))]; | |
| tensor<fp16, [1, 1500, 2048]> input_17_cast = linear(bias = var_268_to_fp16, weight = var_267_to_fp16, x = var_258_cast); | |
| 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 = gelu(mode = x_29_mode_0, x = input_17_cast); | |
| 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, []>(13870336)))]; | |
| 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, []>(15967552)))]; | |
| tensor<fp16, [1, 1500, 512]> var_275_cast = linear(bias = var_274_to_fp16, weight = var_273_to_fp16, x = x_29_cast); | |
| tensor<fp16, [1, 1500, 512]> x_31_cast = add(x = x_25_cast, y = var_275_cast); | |
| 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, []>(15968640)))]; | |
| 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, []>(15969728)))]; | |
| 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 = 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); | |
| 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, []>(15970816)))]; | |
| 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, []>(16495168)))]; | |
| tensor<fp16, [1, 1500, 512]> q_9_cast = linear(bias = var_313_to_fp16, weight = var_312_to_fp16, x = var_301_cast); | |
| 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, []>(16496256)))]; | |
| tensor<fp16, [512]> k_9_bias_0_to_fp16 = const()[name = tensor<string, []>("k_9_bias_0_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(17020608)))]; | |
| tensor<fp16, [1, 1500, 512]> k_9_cast = linear(bias = k_9_bias_0_to_fp16, weight = var_316_to_fp16, x = var_301_cast); | |
| 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, []>(17021696)))]; | |
| 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, []>(17546048)))]; | |
| tensor<fp16, [1, 1500, 512]> v_9_cast = linear(bias = var_321_to_fp16, weight = var_320_to_fp16, x = var_301_cast); | |
| 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 = reshape(shape = var_329, x = q_9_cast); | |
| 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 = mul(x = var_330_cast, y = const_46_to_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 = reshape(shape = var_336, x = k_9_cast); | |
| 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 = mul(x = var_337_cast, y = const_47_to_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 = reshape(shape = var_343, x = v_9_cast); | |
| 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_16_perm_0 = const()[name = tensor<string, []>("transpose_16_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; | |
| tensor<int32, [4]> transpose_17_perm_0 = const()[name = tensor<string, []>("transpose_17_perm_0"), val = tensor<int32, [4]>([0, 2, 3, 1])]; | |
| tensor<fp16, [1, 8, 64, 1500]> transpose_37 = transpose(perm = transpose_17_perm_0, x = k_11_cast); | |
| tensor<fp16, [1, 8, 1500, 64]> transpose_38 = transpose(perm = transpose_16_perm_0, x = q_11_cast); | |
| tensor<fp16, [1, 8, 1500, 1500]> qk_5_cast = matmul(transpose_x = qk_5_transpose_x_0, transpose_y = qk_5_transpose_y_0, x = transpose_38, y = transpose_37); | |
| tensor<fp16, [1, 8, 1500, 1500]> var_349_cast = softmax(axis = var_284, x = qk_5_cast); | |
| 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_39 = transpose(perm = var_345, x = var_344_cast); | |
| tensor<fp16, [1, 8, 1500, 64]> var_351_cast = matmul(transpose_x = var_351_transpose_x_0, transpose_y = var_351_transpose_y_0, x = var_349_cast, y = transpose_39); | |
| 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_36 = transpose(perm = var_352, x = var_351_cast); | |
| tensor<fp16, [1, 1500, 512]> x_35_cast = reshape(shape = concat_2, x = transpose_36); | |
| 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, []>(17547136)))]; | |
| 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, []>(18071488)))]; | |
| tensor<fp16, [1, 1500, 512]> var_359_cast = linear(bias = var_358_to_fp16, weight = var_357_to_fp16, x = x_35_cast); | |
| tensor<fp16, [1, 1500, 512]> x_37_cast = add(x = x_31_cast, y = var_359_cast); | |
| 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, []>(18072576)))]; | |
| 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, []>(18073664)))]; | |
| tensor<fp16, [1, 1500, 512]> var_365_cast = 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); | |
| 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, []>(18074752)))]; | |
| 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, []>(20171968)))]; | |
| tensor<fp16, [1, 1500, 2048]> input_25_cast = linear(bias = var_375_to_fp16, weight = var_374_to_fp16, x = var_365_cast); | |
| 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 = gelu(mode = x_41_mode_0, x = input_25_cast); | |
| 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, []>(20176128)))]; | |
| 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, []>(22273344)))]; | |
| tensor<fp16, [1, 1500, 512]> var_382_cast = linear(bias = var_381_to_fp16, weight = var_380_to_fp16, x = x_41_cast); | |
| tensor<fp16, [1, 1500, 512]> x_43_cast = add(x = x_37_cast, y = var_382_cast); | |
| 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, []>(22274432)))]; | |
| 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, []>(22275520)))]; | |
| 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 = 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); | |
| 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, []>(22276608)))]; | |
| 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, []>(22800960)))]; | |
| tensor<fp16, [1, 1500, 512]> q_13_cast = linear(bias = var_420_to_fp16, weight = var_419_to_fp16, x = var_408_cast); | |
| 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, []>(22802048)))]; | |
| tensor<fp16, [512]> k_13_bias_0_to_fp16 = const()[name = tensor<string, []>("k_13_bias_0_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(23326400)))]; | |
| tensor<fp16, [1, 1500, 512]> k_13_cast = linear(bias = k_13_bias_0_to_fp16, weight = var_423_to_fp16, x = var_408_cast); | |
| 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, []>(23327488)))]; | |
| 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, []>(23851840)))]; | |
| tensor<fp16, [1, 1500, 512]> v_13_cast = linear(bias = var_428_to_fp16, weight = var_427_to_fp16, x = var_408_cast); | |
| 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 = reshape(shape = var_436, x = q_13_cast); | |
| 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 = mul(x = var_437_cast, y = const_48_to_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 = reshape(shape = var_443, x = k_13_cast); | |
| 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 = mul(x = var_444_cast, y = const_49_to_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 = reshape(shape = var_450, x = v_13_cast); | |
| 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_18_perm_0 = const()[name = tensor<string, []>("transpose_18_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; | |
| tensor<int32, [4]> transpose_19_perm_0 = const()[name = tensor<string, []>("transpose_19_perm_0"), val = tensor<int32, [4]>([0, 2, 3, 1])]; | |
| tensor<fp16, [1, 8, 64, 1500]> transpose_33 = transpose(perm = transpose_19_perm_0, x = k_15_cast); | |
| tensor<fp16, [1, 8, 1500, 64]> transpose_34 = transpose(perm = transpose_18_perm_0, x = q_15_cast); | |
| tensor<fp16, [1, 8, 1500, 1500]> qk_7_cast = matmul(transpose_x = qk_7_transpose_x_0, transpose_y = qk_7_transpose_y_0, x = transpose_34, y = transpose_33); | |
| tensor<fp16, [1, 8, 1500, 1500]> var_456_cast = softmax(axis = var_391, x = qk_7_cast); | |
| 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_35 = transpose(perm = var_452, x = var_451_cast); | |
| tensor<fp16, [1, 8, 1500, 64]> var_458_cast = matmul(transpose_x = var_458_transpose_x_0, transpose_y = var_458_transpose_y_0, x = var_456_cast, y = transpose_35); | |
| 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_32 = transpose(perm = var_459, x = var_458_cast); | |
| tensor<fp16, [1, 1500, 512]> x_47_cast = reshape(shape = concat_3, x = transpose_32); | |
| 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, []>(23852928)))]; | |
| 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, []>(24377280)))]; | |
| tensor<fp16, [1, 1500, 512]> var_466_cast = linear(bias = var_465_to_fp16, weight = var_464_to_fp16, x = x_47_cast); | |
| tensor<fp16, [1, 1500, 512]> x_49_cast = add(x = x_43_cast, y = var_466_cast); | |
| 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, []>(24378368)))]; | |
| 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, []>(24379456)))]; | |
| tensor<fp16, [1, 1500, 512]> var_472_cast = 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); | |
| 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, []>(24380544)))]; | |
| 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, []>(26477760)))]; | |
| tensor<fp16, [1, 1500, 2048]> input_33_cast = linear(bias = var_482_to_fp16, weight = var_481_to_fp16, x = var_472_cast); | |
| 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 = gelu(mode = x_53_mode_0, x = input_33_cast); | |
| 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, []>(26481920)))]; | |
| 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, []>(28579136)))]; | |
| tensor<fp16, [1, 1500, 512]> var_489_cast = linear(bias = var_488_to_fp16, weight = var_487_to_fp16, x = x_53_cast); | |
| tensor<fp16, [1, 1500, 512]> x_55_cast = add(x = x_49_cast, y = var_489_cast); | |
| 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, []>(28580224)))]; | |
| 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, []>(28581312)))]; | |
| 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 = 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); | |
| 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, []>(28582400)))]; | |
| 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, []>(29106752)))]; | |
| tensor<fp16, [1, 1500, 512]> q_17_cast = linear(bias = var_527_to_fp16, weight = var_526_to_fp16, x = var_515_cast); | |
| 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, []>(29107840)))]; | |
| tensor<fp16, [512]> k_17_bias_0_to_fp16 = const()[name = tensor<string, []>("k_17_bias_0_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(29632192)))]; | |
| tensor<fp16, [1, 1500, 512]> k_17_cast = linear(bias = k_17_bias_0_to_fp16, weight = var_530_to_fp16, x = var_515_cast); | |
| 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, []>(29633280)))]; | |
| 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, []>(30157632)))]; | |
| tensor<fp16, [1, 1500, 512]> v_17_cast = linear(bias = var_535_to_fp16, weight = var_534_to_fp16, x = var_515_cast); | |
| 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 = reshape(shape = var_543, x = q_17_cast); | |
| 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 = mul(x = var_544_cast, y = const_50_to_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 = reshape(shape = var_550, x = k_17_cast); | |
| 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 = mul(x = var_551_cast, y = const_51_to_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 = reshape(shape = var_557, x = v_17_cast); | |
| 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_20_perm_0 = const()[name = tensor<string, []>("transpose_20_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; | |
| tensor<int32, [4]> transpose_21_perm_0 = const()[name = tensor<string, []>("transpose_21_perm_0"), val = tensor<int32, [4]>([0, 2, 3, 1])]; | |
| tensor<fp16, [1, 8, 64, 1500]> transpose_29 = transpose(perm = transpose_21_perm_0, x = k_19_cast); | |
| tensor<fp16, [1, 8, 1500, 64]> transpose_30 = transpose(perm = transpose_20_perm_0, x = q_19_cast); | |
| tensor<fp16, [1, 8, 1500, 1500]> qk_9_cast = matmul(transpose_x = qk_9_transpose_x_0, transpose_y = qk_9_transpose_y_0, x = transpose_30, y = transpose_29); | |
| tensor<fp16, [1, 8, 1500, 1500]> var_563_cast = softmax(axis = var_498, x = qk_9_cast); | |
| 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_31 = transpose(perm = var_559, x = var_558_cast); | |
| tensor<fp16, [1, 8, 1500, 64]> var_565_cast = matmul(transpose_x = var_565_transpose_x_0, transpose_y = var_565_transpose_y_0, x = var_563_cast, y = transpose_31); | |
| 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_28 = transpose(perm = var_566, x = var_565_cast); | |
| tensor<fp16, [1, 1500, 512]> x_59_cast = reshape(shape = concat_4, x = transpose_28); | |
| 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, []>(30158720)))]; | |
| 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, []>(30683072)))]; | |
| tensor<fp16, [1, 1500, 512]> var_573_cast = linear(bias = var_572_to_fp16, weight = var_571_to_fp16, x = x_59_cast); | |
| tensor<fp16, [1, 1500, 512]> x_61_cast = add(x = x_55_cast, y = var_573_cast); | |
| 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, []>(30684160)))]; | |
| 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, []>(30685248)))]; | |
| tensor<fp16, [1, 1500, 512]> var_579_cast = 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); | |
| 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, []>(30686336)))]; | |
| 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, []>(32783552)))]; | |
| tensor<fp16, [1, 1500, 2048]> input_41_cast = linear(bias = var_589_to_fp16, weight = var_588_to_fp16, x = var_579_cast); | |
| 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 = gelu(mode = x_65_mode_0, x = input_41_cast); | |
| 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, []>(32787712)))]; | |
| 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, []>(34884928)))]; | |
| tensor<fp16, [1, 1500, 512]> var_596_cast = linear(bias = var_595_to_fp16, weight = var_594_to_fp16, x = x_65_cast); | |
| tensor<fp16, [1, 1500, 512]> x_67_cast = add(x = x_61_cast, y = var_596_cast); | |
| 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, []>(34886016)))]; | |
| 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, []>(34887104)))]; | |
| 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 = 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); | |
| 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, []>(34888192)))]; | |
| 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, []>(35412544)))]; | |
| tensor<fp16, [1, 1500, 512]> q_21_cast = linear(bias = var_634_to_fp16, weight = var_633_to_fp16, x = var_622_cast); | |
| 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, []>(35413632)))]; | |
| tensor<fp16, [512]> k_21_bias_0_to_fp16 = const()[name = tensor<string, []>("k_21_bias_0_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = tensor<string, []>("@model_path/weights/weight.bin"), offset = tensor<uint64, []>(35937984)))]; | |
| tensor<fp16, [1, 1500, 512]> k_21_cast = linear(bias = k_21_bias_0_to_fp16, weight = var_637_to_fp16, x = var_622_cast); | |
| 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, []>(35939072)))]; | |
| 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, []>(36463424)))]; | |
| tensor<fp16, [1, 1500, 512]> v_21_cast = linear(bias = var_642_to_fp16, weight = var_641_to_fp16, x = var_622_cast); | |
| 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 = reshape(shape = var_650, x = q_21_cast); | |
| 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 = mul(x = var_651_cast, y = const_52_to_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 = reshape(shape = var_657, x = k_21_cast); | |
| 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 = mul(x = var_658_cast, y = const_53_to_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 = reshape(shape = var_664, x = v_21_cast); | |
| 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_22_perm_0 = const()[name = tensor<string, []>("transpose_22_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; | |
| tensor<int32, [4]> transpose_23_perm_0 = const()[name = tensor<string, []>("transpose_23_perm_0"), val = tensor<int32, [4]>([0, 2, 3, 1])]; | |
| tensor<fp16, [1, 8, 64, 1500]> transpose_25 = transpose(perm = transpose_23_perm_0, x = k_cast); | |
| tensor<fp16, [1, 8, 1500, 64]> transpose_26 = transpose(perm = transpose_22_perm_0, x = q_cast); | |
| tensor<fp16, [1, 8, 1500, 1500]> qk_cast = matmul(transpose_x = qk_transpose_x_0, transpose_y = qk_transpose_y_0, x = transpose_26, y = transpose_25); | |
| tensor<fp16, [1, 8, 1500, 1500]> var_670_cast = softmax(axis = var_605, x = qk_cast); | |
| 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_27 = transpose(perm = var_666, x = var_665_cast); | |
| tensor<fp16, [1, 8, 1500, 64]> var_672_cast = matmul(transpose_x = var_672_transpose_x_0, transpose_y = var_672_transpose_y_0, x = var_670_cast, y = transpose_27); | |
| 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_24 = transpose(perm = var_673, x = var_672_cast); | |
| tensor<fp16, [1, 1500, 512]> x_71_cast = reshape(shape = concat_5, x = transpose_24); | |
| 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, []>(36464512)))]; | |
| 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, []>(36988864)))]; | |
| tensor<fp16, [1, 1500, 512]> var_680_cast = linear(bias = var_679_to_fp16, weight = var_678_to_fp16, x = x_71_cast); | |
| tensor<fp16, [1, 1500, 512]> x_73_cast = add(x = x_67_cast, y = var_680_cast); | |
| 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, []>(36989952)))]; | |
| 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, []>(36991040)))]; | |
| tensor<fp16, [1, 1500, 512]> var_686_cast = 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); | |
| 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, []>(36992128)))]; | |
| 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, []>(39089344)))]; | |
| tensor<fp16, [1, 1500, 2048]> input_49_cast = linear(bias = var_696_to_fp16, weight = var_695_to_fp16, x = var_686_cast); | |
| 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 = gelu(mode = x_77_mode_0, x = input_49_cast); | |
| 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, []>(39093504)))]; | |
| 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, []>(41190720)))]; | |
| tensor<fp16, [1, 1500, 512]> var_703_cast = linear(bias = var_702_to_fp16, weight = var_701_to_fp16, x = x_77_cast); | |
| tensor<fp16, [1, 1500, 512]> x_cast = add(x = x_73_cast, y = var_703_cast); | |
| 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, []>(41191808)))]; | |
| 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, []>(41192896)))]; | |
| 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 = 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); | |
| tensor<string, []> var_716_cast_to_fp32_dtype_0 = const()[name = tensor<string, []>("op_716_cast_to_fp32_dtype_0"), val = tensor<string, []>("fp32")]; | |
| tensor<fp32, [1, 1500, 512]> output = cast(dtype = var_716_cast_to_fp32_dtype_0, x = var_716_cast); | |
| } -> (output); | |
| } |