| program(1.3) |
| [buildInfo = dict<string, string>({{"coremlc-component-MIL", "3520.4.1"}, {"coremlc-version", "3520.5.1"}, {"coremltools-component-torch", "2.11.0"}, {"coremltools-source-dialect", "TorchScript"}, {"coremltools-version", "9.0"}})] |
| { |
| func main<ios18>(tensor<int32, [1, 57]> attention_mask, tensor<int32, [1, 57]> tokens) { |
| int32 inputs_embeds_batch_dims_0 = const()[name = string("inputs_embeds_batch_dims_0"), val = int32(0)]; |
| bool inputs_embeds_validate_indices_0 = const()[name = string("inputs_embeds_validate_indices_0"), val = bool(false)]; |
| tensor<fp16, [178, 128]> bert_embeddings_word_embeddings_weight_to_fp16 = const()[name = string("bert_embeddings_word_embeddings_weight_to_fp16"), val = tensor<fp16, [178, 128]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(64)))]; |
| string tokens_to_int16_dtype_0 = const()[name = string("tokens_to_int16_dtype_0"), val = string("int16")]; |
| string cast_53_dtype_0 = const()[name = string("cast_53_dtype_0"), val = string("int32")]; |
| int32 greater_equal_0_y_0 = const()[name = string("greater_equal_0_y_0"), val = int32(0)]; |
| tensor<int16, [1, 57]> tokens_to_int16 = cast(dtype = tokens_to_int16_dtype_0, x = tokens)[name = string("cast_58")]; |
| tensor<int32, [1, 57]> cast_53 = cast(dtype = cast_53_dtype_0, x = tokens_to_int16)[name = string("cast_57")]; |
| tensor<bool, [1, 57]> greater_equal_0 = greater_equal(x = cast_53, y = greater_equal_0_y_0)[name = string("greater_equal_0")]; |
| int32 slice_by_index_0 = const()[name = string("slice_by_index_0"), val = int32(178)]; |
| tensor<int32, [1, 57]> add_0 = add(x = cast_53, y = slice_by_index_0)[name = string("add_0")]; |
| tensor<int32, [1, 57]> select_0 = select(a = cast_53, b = add_0, cond = greater_equal_0)[name = string("select_0")]; |
| int32 inputs_embeds_cast_fp16_cast_uint16_axis_0 = const()[name = string("inputs_embeds_cast_fp16_cast_uint16_axis_0"), val = int32(0)]; |
| string select_0_to_int16_dtype_0 = const()[name = string("select_0_to_int16_dtype_0"), val = string("int16")]; |
| tensor<int16, [1, 57]> select_0_to_int16 = cast(dtype = select_0_to_int16_dtype_0, x = select_0)[name = string("cast_56")]; |
| tensor<fp16, [1, 57, 128]> inputs_embeds_cast_fp16_cast_uint16_cast_uint16 = gather(axis = inputs_embeds_cast_fp16_cast_uint16_axis_0, batch_dims = inputs_embeds_batch_dims_0, indices = select_0_to_int16, validate_indices = inputs_embeds_validate_indices_0, x = bert_embeddings_word_embeddings_weight_to_fp16)[name = string("inputs_embeds_cast_fp16_cast_uint16_cast_uint16")]; |
| tensor<fp16, [1, 57, 128]> token_type_embeddings_1_to_fp16 = const()[name = string("token_type_embeddings_1_to_fp16"), val = tensor<fp16, [1, 57, 128]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(45696)))]; |
| tensor<fp16, [1, 57, 128]> embeddings_1_cast_fp16 = add(x = inputs_embeds_cast_fp16_cast_uint16_cast_uint16, y = token_type_embeddings_1_to_fp16)[name = string("embeddings_1_cast_fp16")]; |
| tensor<fp16, [1, 57, 128]> position_embeddings_1_to_fp16 = const()[name = string("position_embeddings_1_to_fp16"), val = tensor<fp16, [1, 57, 128]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(60352)))]; |
| tensor<fp16, [1, 57, 128]> input_5_cast_fp16 = add(x = embeddings_1_cast_fp16, y = position_embeddings_1_to_fp16)[name = string("input_5_cast_fp16")]; |
| tensor<int32, [1]> input_7_axes_0 = const()[name = string("input_7_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [128]> bert_embeddings_LayerNorm_weight_to_fp16 = const()[name = string("bert_embeddings_LayerNorm_weight_to_fp16"), val = tensor<fp16, [128]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(75008)))]; |
| tensor<fp16, [128]> bert_embeddings_LayerNorm_bias_to_fp16 = const()[name = string("bert_embeddings_LayerNorm_bias_to_fp16"), val = tensor<fp16, [128]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(75328)))]; |
| fp16 var_34_to_fp16 = const()[name = string("op_34_to_fp16"), val = fp16(0x1p-24)]; |
| tensor<fp16, [1, 57, 128]> input_7_cast_fp16 = layer_norm(axes = input_7_axes_0, beta = bert_embeddings_LayerNorm_bias_to_fp16, epsilon = var_34_to_fp16, gamma = bert_embeddings_LayerNorm_weight_to_fp16, x = input_5_cast_fp16)[name = string("input_7_cast_fp16")]; |
| tensor<int32, [1]> var_79_axes_0 = const()[name = string("op_79_axes_0"), val = tensor<int32, [1]>([1])]; |
| tensor<int32, [1, 1, 57]> var_79 = expand_dims(axes = var_79_axes_0, x = attention_mask)[name = string("op_79")]; |
| tensor<int32, [1]> var_81_axes_0 = const()[name = string("op_81_axes_0"), val = tensor<int32, [1]>([2])]; |
| tensor<int32, [1, 1, 1, 57]> var_81 = expand_dims(axes = var_81_axes_0, x = var_79)[name = string("op_81")]; |
| tensor<int32, [4]> var_90_reps_0 = const()[name = string("op_90_reps_0"), val = tensor<int32, [4]>([1, 1, 57, 1])]; |
| tensor<int32, [1, 1, 57, 57]> var_90 = tile(reps = var_90_reps_0, x = var_81)[name = string("op_90")]; |
| fp16 var_96_to_fp16 = const()[name = string("op_96_to_fp16"), val = fp16(0x1p+0)]; |
| string var_95_to_fp16_dtype_0 = const()[name = string("op_95_to_fp16_dtype_0"), val = string("fp16")]; |
| tensor<fp16, [1, 1, 57, 57]> var_90_to_fp16 = cast(dtype = var_95_to_fp16_dtype_0, x = var_90)[name = string("cast_55")]; |
| tensor<fp16, [1, 1, 57, 57]> inverted_mask_cast_fp16 = sub(x = var_96_to_fp16, y = var_90_to_fp16)[name = string("inverted_mask_cast_fp16")]; |
| string var_103_dtype_0 = const()[name = string("op_103_dtype_0"), val = string("bool")]; |
| fp16 var_104_to_fp16 = const()[name = string("op_104_to_fp16"), val = fp16(-inf)]; |
| tensor<bool, [1, 1, 57, 57]> inverted_mask_cast_fp16_to_bool = cast(dtype = var_103_dtype_0, x = inverted_mask_cast_fp16)[name = string("cast_54")]; |
| tensor<fp16, [1, 1, 57, 57]> attention_mask_cast_fp16 = select(a = var_104_to_fp16, b = inverted_mask_cast_fp16, cond = inverted_mask_cast_fp16_to_bool)[name = string("attention_mask_cast_fp16")]; |
| tensor<fp16, [768, 128]> bert_encoder_embedding_hidden_mapping_in_weight_to_fp16 = const()[name = string("bert_encoder_embedding_hidden_mapping_in_weight_to_fp16"), val = tensor<fp16, [768, 128]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(75648)))]; |
| tensor<fp16, [768]> bert_encoder_embedding_hidden_mapping_in_bias_to_fp16 = const()[name = string("bert_encoder_embedding_hidden_mapping_in_bias_to_fp16"), val = tensor<fp16, [768]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(272320)))]; |
| tensor<fp16, [1, 57, 768]> linear_0_cast_fp16 = linear(bias = bert_encoder_embedding_hidden_mapping_in_bias_to_fp16, weight = bert_encoder_embedding_hidden_mapping_in_weight_to_fp16, x = input_7_cast_fp16)[name = string("linear_0_cast_fp16")]; |
| tensor<fp16, [768, 768]> bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_weight_to_fp16 = const()[name = string("bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_weight_to_fp16"), val = tensor<fp16, [768, 768]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(273920)))]; |
| tensor<fp16, [768]> bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_bias_to_fp16 = const()[name = string("bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_bias_to_fp16"), val = tensor<fp16, [768]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(1453632)))]; |
| tensor<fp16, [1, 57, 768]> linear_1_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_weight_to_fp16, x = linear_0_cast_fp16)[name = string("linear_1_cast_fp16")]; |
| tensor<int32, [4]> var_143 = const()[name = string("op_143"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_3_cast_fp16 = reshape(shape = var_143, x = linear_1_cast_fp16)[name = string("x_3_cast_fp16")]; |
| tensor<fp16, [768, 768]> bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_weight_to_fp16 = const()[name = string("bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_weight_to_fp16"), val = tensor<fp16, [768, 768]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(1455232)))]; |
| tensor<fp16, [768]> bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_bias_to_fp16 = const()[name = string("bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_bias_to_fp16"), val = tensor<fp16, [768]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(2634944)))]; |
| tensor<fp16, [1, 57, 768]> linear_2_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_weight_to_fp16, x = linear_0_cast_fp16)[name = string("linear_2_cast_fp16")]; |
| tensor<int32, [4]> var_152 = const()[name = string("op_152"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_7_cast_fp16 = reshape(shape = var_152, x = linear_2_cast_fp16)[name = string("x_7_cast_fp16")]; |
| tensor<fp16, [768, 768]> bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_weight_to_fp16 = const()[name = string("bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_weight_to_fp16"), val = tensor<fp16, [768, 768]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(2636544)))]; |
| tensor<fp16, [768]> bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_bias_to_fp16 = const()[name = string("bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_bias_to_fp16"), val = tensor<fp16, [768]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(3816256)))]; |
| tensor<fp16, [1, 57, 768]> linear_3_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_weight_to_fp16, x = linear_0_cast_fp16)[name = string("linear_3_cast_fp16")]; |
| tensor<int32, [4]> var_161 = const()[name = string("op_161"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_11_cast_fp16 = reshape(shape = var_161, x = linear_3_cast_fp16)[name = string("x_11_cast_fp16")]; |
| tensor<int32, [4]> transpose_72_perm_0 = const()[name = string("transpose_72_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_73_perm_0 = const()[name = string("transpose_73_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_74_perm_0 = const()[name = string("transpose_74_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_74 = transpose(perm = transpose_74_perm_0, x = x_11_cast_fp16)[name = string("transpose_154")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_73 = transpose(perm = transpose_73_perm_0, x = x_7_cast_fp16)[name = string("transpose_155")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_72 = transpose(perm = transpose_72_perm_0, x = x_3_cast_fp16)[name = string("transpose_156")]; |
| tensor<fp16, [1, 12, 57, 64]> attention_output_1_cast_fp16 = scaled_dot_product_attention(attn_mask = attention_mask_cast_fp16, key = transpose_73, query = transpose_72, value = transpose_74)[name = string("attention_output_1_cast_fp16")]; |
| tensor<int32, [4]> attention_output_3_perm_0 = const()[name = string("attention_output_3_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [3]> var_167 = const()[name = string("op_167"), val = tensor<int32, [3]>([1, 57, 768])]; |
| tensor<fp16, [1, 57, 12, 64]> attention_output_3_cast_fp16 = transpose(perm = attention_output_3_perm_0, x = attention_output_1_cast_fp16)[name = string("transpose_153")]; |
| tensor<fp16, [1, 57, 768]> input_9_cast_fp16 = reshape(shape = var_167, x = attention_output_3_cast_fp16)[name = string("input_9_cast_fp16")]; |
| tensor<fp16, [768, 768]> bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_weight_to_fp16 = const()[name = string("bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_weight_to_fp16"), val = tensor<fp16, [768, 768]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(3817856)))]; |
| tensor<fp16, [768]> bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_bias_to_fp16 = const()[name = string("bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_bias_to_fp16"), val = tensor<fp16, [768]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(4997568)))]; |
| tensor<fp16, [1, 57, 768]> linear_4_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_weight_to_fp16, x = input_9_cast_fp16)[name = string("linear_4_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_11_cast_fp16 = add(x = linear_0_cast_fp16, y = linear_4_cast_fp16)[name = string("input_11_cast_fp16")]; |
| tensor<int32, [1]> input_13_axes_0 = const()[name = string("input_13_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [768]> bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_weight_to_fp16 = const()[name = string("bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_weight_to_fp16"), val = tensor<fp16, [768]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(4999168)))]; |
| tensor<fp16, [768]> bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_bias_to_fp16 = const()[name = string("bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_bias_to_fp16"), val = tensor<fp16, [768]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(5000768)))]; |
| fp16 var_118_to_fp16 = const()[name = string("op_118_to_fp16"), val = fp16(0x1p-24)]; |
| tensor<fp16, [1, 57, 768]> input_13_cast_fp16 = layer_norm(axes = input_13_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_weight_to_fp16, x = input_11_cast_fp16)[name = string("input_13_cast_fp16")]; |
| tensor<fp16, [2048, 768]> bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_weight_to_fp16 = const()[name = string("bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_weight_to_fp16"), val = tensor<fp16, [2048, 768]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(5002368)))]; |
| tensor<fp16, [2048]> bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_bias_to_fp16 = const()[name = string("bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_bias_to_fp16"), val = tensor<fp16, [2048]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(8148160)))]; |
| tensor<fp16, [1, 57, 2048]> linear_5_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_weight_to_fp16, x = input_13_cast_fp16)[name = string("linear_5_cast_fp16")]; |
| string input_17_mode_0 = const()[name = string("input_17_mode_0"), val = string("TANH_APPROXIMATION")]; |
| tensor<fp16, [1, 57, 2048]> input_17_cast_fp16 = gelu(mode = input_17_mode_0, x = linear_5_cast_fp16)[name = string("input_17_cast_fp16")]; |
| tensor<fp16, [768, 2048]> bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_weight_to_fp16 = const()[name = string("bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_weight_to_fp16"), val = tensor<fp16, [768, 2048]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(8152320)))]; |
| tensor<fp16, [768]> bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_bias_to_fp16 = const()[name = string("bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_bias_to_fp16"), val = tensor<fp16, [768]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(11298112)))]; |
| tensor<fp16, [1, 57, 768]> linear_6_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_weight_to_fp16, x = input_17_cast_fp16)[name = string("linear_6_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_19_cast_fp16 = add(x = linear_6_cast_fp16, y = input_13_cast_fp16)[name = string("input_19_cast_fp16")]; |
| tensor<int32, [1]> hidden_states_3_axes_0 = const()[name = string("hidden_states_3_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [768]> bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_weight_to_fp16 = const()[name = string("bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_weight_to_fp16"), val = tensor<fp16, [768]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(11299712)))]; |
| tensor<fp16, [768]> bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_bias_to_fp16 = const()[name = string("bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_bias_to_fp16"), val = tensor<fp16, [768]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(11301312)))]; |
| tensor<fp16, [1, 57, 768]> hidden_states_3_cast_fp16 = layer_norm(axes = hidden_states_3_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_weight_to_fp16, x = input_19_cast_fp16)[name = string("hidden_states_3_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_7_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_weight_to_fp16, x = hidden_states_3_cast_fp16)[name = string("linear_7_cast_fp16")]; |
| tensor<int32, [4]> var_218 = const()[name = string("op_218"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_15_cast_fp16 = reshape(shape = var_218, x = linear_7_cast_fp16)[name = string("x_15_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_8_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_weight_to_fp16, x = hidden_states_3_cast_fp16)[name = string("linear_8_cast_fp16")]; |
| tensor<int32, [4]> var_227 = const()[name = string("op_227"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_19_cast_fp16 = reshape(shape = var_227, x = linear_8_cast_fp16)[name = string("x_19_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_9_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_weight_to_fp16, x = hidden_states_3_cast_fp16)[name = string("linear_9_cast_fp16")]; |
| tensor<int32, [4]> var_236 = const()[name = string("op_236"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_23_cast_fp16 = reshape(shape = var_236, x = linear_9_cast_fp16)[name = string("x_23_cast_fp16")]; |
| tensor<int32, [4]> transpose_75_perm_0 = const()[name = string("transpose_75_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_76_perm_0 = const()[name = string("transpose_76_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_77_perm_0 = const()[name = string("transpose_77_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_77 = transpose(perm = transpose_77_perm_0, x = x_23_cast_fp16)[name = string("transpose_150")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_76 = transpose(perm = transpose_76_perm_0, x = x_19_cast_fp16)[name = string("transpose_151")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_75 = transpose(perm = transpose_75_perm_0, x = x_15_cast_fp16)[name = string("transpose_152")]; |
| tensor<fp16, [1, 12, 57, 64]> attention_output_5_cast_fp16 = scaled_dot_product_attention(attn_mask = attention_mask_cast_fp16, key = transpose_76, query = transpose_75, value = transpose_77)[name = string("attention_output_5_cast_fp16")]; |
| tensor<int32, [4]> attention_output_7_perm_0 = const()[name = string("attention_output_7_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [3]> var_242 = const()[name = string("op_242"), val = tensor<int32, [3]>([1, 57, 768])]; |
| tensor<fp16, [1, 57, 12, 64]> attention_output_7_cast_fp16 = transpose(perm = attention_output_7_perm_0, x = attention_output_5_cast_fp16)[name = string("transpose_149")]; |
| tensor<fp16, [1, 57, 768]> input_21_cast_fp16 = reshape(shape = var_242, x = attention_output_7_cast_fp16)[name = string("input_21_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_10_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_weight_to_fp16, x = input_21_cast_fp16)[name = string("linear_10_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_23_cast_fp16 = add(x = hidden_states_3_cast_fp16, y = linear_10_cast_fp16)[name = string("input_23_cast_fp16")]; |
| tensor<int32, [1]> input_25_axes_0 = const()[name = string("input_25_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> input_25_cast_fp16 = layer_norm(axes = input_25_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_weight_to_fp16, x = input_23_cast_fp16)[name = string("input_25_cast_fp16")]; |
| tensor<fp16, [1, 57, 2048]> linear_11_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_weight_to_fp16, x = input_25_cast_fp16)[name = string("linear_11_cast_fp16")]; |
| string input_29_mode_0 = const()[name = string("input_29_mode_0"), val = string("TANH_APPROXIMATION")]; |
| tensor<fp16, [1, 57, 2048]> input_29_cast_fp16 = gelu(mode = input_29_mode_0, x = linear_11_cast_fp16)[name = string("input_29_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_12_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_weight_to_fp16, x = input_29_cast_fp16)[name = string("linear_12_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_31_cast_fp16 = add(x = linear_12_cast_fp16, y = input_25_cast_fp16)[name = string("input_31_cast_fp16")]; |
| tensor<int32, [1]> hidden_states_5_axes_0 = const()[name = string("hidden_states_5_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> hidden_states_5_cast_fp16 = layer_norm(axes = hidden_states_5_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_weight_to_fp16, x = input_31_cast_fp16)[name = string("hidden_states_5_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_13_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_weight_to_fp16, x = hidden_states_5_cast_fp16)[name = string("linear_13_cast_fp16")]; |
| tensor<int32, [4]> var_293 = const()[name = string("op_293"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_27_cast_fp16 = reshape(shape = var_293, x = linear_13_cast_fp16)[name = string("x_27_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_14_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_weight_to_fp16, x = hidden_states_5_cast_fp16)[name = string("linear_14_cast_fp16")]; |
| tensor<int32, [4]> var_302 = const()[name = string("op_302"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_31_cast_fp16 = reshape(shape = var_302, x = linear_14_cast_fp16)[name = string("x_31_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_15_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_weight_to_fp16, x = hidden_states_5_cast_fp16)[name = string("linear_15_cast_fp16")]; |
| tensor<int32, [4]> var_311 = const()[name = string("op_311"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_35_cast_fp16 = reshape(shape = var_311, x = linear_15_cast_fp16)[name = string("x_35_cast_fp16")]; |
| tensor<int32, [4]> transpose_78_perm_0 = const()[name = string("transpose_78_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_79_perm_0 = const()[name = string("transpose_79_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_80_perm_0 = const()[name = string("transpose_80_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_80 = transpose(perm = transpose_80_perm_0, x = x_35_cast_fp16)[name = string("transpose_146")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_79 = transpose(perm = transpose_79_perm_0, x = x_31_cast_fp16)[name = string("transpose_147")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_78 = transpose(perm = transpose_78_perm_0, x = x_27_cast_fp16)[name = string("transpose_148")]; |
| tensor<fp16, [1, 12, 57, 64]> attention_output_9_cast_fp16 = scaled_dot_product_attention(attn_mask = attention_mask_cast_fp16, key = transpose_79, query = transpose_78, value = transpose_80)[name = string("attention_output_9_cast_fp16")]; |
| tensor<int32, [4]> attention_output_11_perm_0 = const()[name = string("attention_output_11_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [3]> var_317 = const()[name = string("op_317"), val = tensor<int32, [3]>([1, 57, 768])]; |
| tensor<fp16, [1, 57, 12, 64]> attention_output_11_cast_fp16 = transpose(perm = attention_output_11_perm_0, x = attention_output_9_cast_fp16)[name = string("transpose_145")]; |
| tensor<fp16, [1, 57, 768]> input_33_cast_fp16 = reshape(shape = var_317, x = attention_output_11_cast_fp16)[name = string("input_33_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_16_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_weight_to_fp16, x = input_33_cast_fp16)[name = string("linear_16_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_35_cast_fp16 = add(x = hidden_states_5_cast_fp16, y = linear_16_cast_fp16)[name = string("input_35_cast_fp16")]; |
| tensor<int32, [1]> input_37_axes_0 = const()[name = string("input_37_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> input_37_cast_fp16 = layer_norm(axes = input_37_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_weight_to_fp16, x = input_35_cast_fp16)[name = string("input_37_cast_fp16")]; |
| tensor<fp16, [1, 57, 2048]> linear_17_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_weight_to_fp16, x = input_37_cast_fp16)[name = string("linear_17_cast_fp16")]; |
| string input_41_mode_0 = const()[name = string("input_41_mode_0"), val = string("TANH_APPROXIMATION")]; |
| tensor<fp16, [1, 57, 2048]> input_41_cast_fp16 = gelu(mode = input_41_mode_0, x = linear_17_cast_fp16)[name = string("input_41_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_18_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_weight_to_fp16, x = input_41_cast_fp16)[name = string("linear_18_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_43_cast_fp16 = add(x = linear_18_cast_fp16, y = input_37_cast_fp16)[name = string("input_43_cast_fp16")]; |
| tensor<int32, [1]> hidden_states_7_axes_0 = const()[name = string("hidden_states_7_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> hidden_states_7_cast_fp16 = layer_norm(axes = hidden_states_7_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_weight_to_fp16, x = input_43_cast_fp16)[name = string("hidden_states_7_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_19_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_weight_to_fp16, x = hidden_states_7_cast_fp16)[name = string("linear_19_cast_fp16")]; |
| tensor<int32, [4]> var_368 = const()[name = string("op_368"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_39_cast_fp16 = reshape(shape = var_368, x = linear_19_cast_fp16)[name = string("x_39_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_20_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_weight_to_fp16, x = hidden_states_7_cast_fp16)[name = string("linear_20_cast_fp16")]; |
| tensor<int32, [4]> var_377 = const()[name = string("op_377"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_43_cast_fp16 = reshape(shape = var_377, x = linear_20_cast_fp16)[name = string("x_43_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_21_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_weight_to_fp16, x = hidden_states_7_cast_fp16)[name = string("linear_21_cast_fp16")]; |
| tensor<int32, [4]> var_386 = const()[name = string("op_386"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_47_cast_fp16 = reshape(shape = var_386, x = linear_21_cast_fp16)[name = string("x_47_cast_fp16")]; |
| tensor<int32, [4]> transpose_81_perm_0 = const()[name = string("transpose_81_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_82_perm_0 = const()[name = string("transpose_82_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_83_perm_0 = const()[name = string("transpose_83_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_83 = transpose(perm = transpose_83_perm_0, x = x_47_cast_fp16)[name = string("transpose_142")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_82 = transpose(perm = transpose_82_perm_0, x = x_43_cast_fp16)[name = string("transpose_143")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_81 = transpose(perm = transpose_81_perm_0, x = x_39_cast_fp16)[name = string("transpose_144")]; |
| tensor<fp16, [1, 12, 57, 64]> attention_output_13_cast_fp16 = scaled_dot_product_attention(attn_mask = attention_mask_cast_fp16, key = transpose_82, query = transpose_81, value = transpose_83)[name = string("attention_output_13_cast_fp16")]; |
| tensor<int32, [4]> attention_output_15_perm_0 = const()[name = string("attention_output_15_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [3]> var_392 = const()[name = string("op_392"), val = tensor<int32, [3]>([1, 57, 768])]; |
| tensor<fp16, [1, 57, 12, 64]> attention_output_15_cast_fp16 = transpose(perm = attention_output_15_perm_0, x = attention_output_13_cast_fp16)[name = string("transpose_141")]; |
| tensor<fp16, [1, 57, 768]> input_45_cast_fp16 = reshape(shape = var_392, x = attention_output_15_cast_fp16)[name = string("input_45_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_22_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_weight_to_fp16, x = input_45_cast_fp16)[name = string("linear_22_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_47_cast_fp16 = add(x = hidden_states_7_cast_fp16, y = linear_22_cast_fp16)[name = string("input_47_cast_fp16")]; |
| tensor<int32, [1]> input_49_axes_0 = const()[name = string("input_49_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> input_49_cast_fp16 = layer_norm(axes = input_49_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_weight_to_fp16, x = input_47_cast_fp16)[name = string("input_49_cast_fp16")]; |
| tensor<fp16, [1, 57, 2048]> linear_23_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_weight_to_fp16, x = input_49_cast_fp16)[name = string("linear_23_cast_fp16")]; |
| string input_53_mode_0 = const()[name = string("input_53_mode_0"), val = string("TANH_APPROXIMATION")]; |
| tensor<fp16, [1, 57, 2048]> input_53_cast_fp16 = gelu(mode = input_53_mode_0, x = linear_23_cast_fp16)[name = string("input_53_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_24_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_weight_to_fp16, x = input_53_cast_fp16)[name = string("linear_24_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_55_cast_fp16 = add(x = linear_24_cast_fp16, y = input_49_cast_fp16)[name = string("input_55_cast_fp16")]; |
| tensor<int32, [1]> hidden_states_9_axes_0 = const()[name = string("hidden_states_9_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> hidden_states_9_cast_fp16 = layer_norm(axes = hidden_states_9_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_weight_to_fp16, x = input_55_cast_fp16)[name = string("hidden_states_9_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_25_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_weight_to_fp16, x = hidden_states_9_cast_fp16)[name = string("linear_25_cast_fp16")]; |
| tensor<int32, [4]> var_443 = const()[name = string("op_443"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_51_cast_fp16 = reshape(shape = var_443, x = linear_25_cast_fp16)[name = string("x_51_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_26_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_weight_to_fp16, x = hidden_states_9_cast_fp16)[name = string("linear_26_cast_fp16")]; |
| tensor<int32, [4]> var_452 = const()[name = string("op_452"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_55_cast_fp16 = reshape(shape = var_452, x = linear_26_cast_fp16)[name = string("x_55_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_27_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_weight_to_fp16, x = hidden_states_9_cast_fp16)[name = string("linear_27_cast_fp16")]; |
| tensor<int32, [4]> var_461 = const()[name = string("op_461"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_59_cast_fp16 = reshape(shape = var_461, x = linear_27_cast_fp16)[name = string("x_59_cast_fp16")]; |
| tensor<int32, [4]> transpose_84_perm_0 = const()[name = string("transpose_84_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_85_perm_0 = const()[name = string("transpose_85_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_86_perm_0 = const()[name = string("transpose_86_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_86 = transpose(perm = transpose_86_perm_0, x = x_59_cast_fp16)[name = string("transpose_138")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_85 = transpose(perm = transpose_85_perm_0, x = x_55_cast_fp16)[name = string("transpose_139")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_84 = transpose(perm = transpose_84_perm_0, x = x_51_cast_fp16)[name = string("transpose_140")]; |
| tensor<fp16, [1, 12, 57, 64]> attention_output_17_cast_fp16 = scaled_dot_product_attention(attn_mask = attention_mask_cast_fp16, key = transpose_85, query = transpose_84, value = transpose_86)[name = string("attention_output_17_cast_fp16")]; |
| tensor<int32, [4]> attention_output_19_perm_0 = const()[name = string("attention_output_19_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [3]> var_467 = const()[name = string("op_467"), val = tensor<int32, [3]>([1, 57, 768])]; |
| tensor<fp16, [1, 57, 12, 64]> attention_output_19_cast_fp16 = transpose(perm = attention_output_19_perm_0, x = attention_output_17_cast_fp16)[name = string("transpose_137")]; |
| tensor<fp16, [1, 57, 768]> input_57_cast_fp16 = reshape(shape = var_467, x = attention_output_19_cast_fp16)[name = string("input_57_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_28_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_weight_to_fp16, x = input_57_cast_fp16)[name = string("linear_28_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_59_cast_fp16 = add(x = hidden_states_9_cast_fp16, y = linear_28_cast_fp16)[name = string("input_59_cast_fp16")]; |
| tensor<int32, [1]> input_61_axes_0 = const()[name = string("input_61_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> input_61_cast_fp16 = layer_norm(axes = input_61_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_weight_to_fp16, x = input_59_cast_fp16)[name = string("input_61_cast_fp16")]; |
| tensor<fp16, [1, 57, 2048]> linear_29_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_weight_to_fp16, x = input_61_cast_fp16)[name = string("linear_29_cast_fp16")]; |
| string input_65_mode_0 = const()[name = string("input_65_mode_0"), val = string("TANH_APPROXIMATION")]; |
| tensor<fp16, [1, 57, 2048]> input_65_cast_fp16 = gelu(mode = input_65_mode_0, x = linear_29_cast_fp16)[name = string("input_65_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_30_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_weight_to_fp16, x = input_65_cast_fp16)[name = string("linear_30_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_67_cast_fp16 = add(x = linear_30_cast_fp16, y = input_61_cast_fp16)[name = string("input_67_cast_fp16")]; |
| tensor<int32, [1]> hidden_states_11_axes_0 = const()[name = string("hidden_states_11_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> hidden_states_11_cast_fp16 = layer_norm(axes = hidden_states_11_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_weight_to_fp16, x = input_67_cast_fp16)[name = string("hidden_states_11_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_31_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_weight_to_fp16, x = hidden_states_11_cast_fp16)[name = string("linear_31_cast_fp16")]; |
| tensor<int32, [4]> var_518 = const()[name = string("op_518"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_63_cast_fp16 = reshape(shape = var_518, x = linear_31_cast_fp16)[name = string("x_63_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_32_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_weight_to_fp16, x = hidden_states_11_cast_fp16)[name = string("linear_32_cast_fp16")]; |
| tensor<int32, [4]> var_527 = const()[name = string("op_527"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_67_cast_fp16 = reshape(shape = var_527, x = linear_32_cast_fp16)[name = string("x_67_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_33_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_weight_to_fp16, x = hidden_states_11_cast_fp16)[name = string("linear_33_cast_fp16")]; |
| tensor<int32, [4]> var_536 = const()[name = string("op_536"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_71_cast_fp16 = reshape(shape = var_536, x = linear_33_cast_fp16)[name = string("x_71_cast_fp16")]; |
| tensor<int32, [4]> transpose_87_perm_0 = const()[name = string("transpose_87_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_88_perm_0 = const()[name = string("transpose_88_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_89_perm_0 = const()[name = string("transpose_89_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_89 = transpose(perm = transpose_89_perm_0, x = x_71_cast_fp16)[name = string("transpose_134")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_88 = transpose(perm = transpose_88_perm_0, x = x_67_cast_fp16)[name = string("transpose_135")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_87 = transpose(perm = transpose_87_perm_0, x = x_63_cast_fp16)[name = string("transpose_136")]; |
| tensor<fp16, [1, 12, 57, 64]> attention_output_21_cast_fp16 = scaled_dot_product_attention(attn_mask = attention_mask_cast_fp16, key = transpose_88, query = transpose_87, value = transpose_89)[name = string("attention_output_21_cast_fp16")]; |
| tensor<int32, [4]> attention_output_23_perm_0 = const()[name = string("attention_output_23_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [3]> var_542 = const()[name = string("op_542"), val = tensor<int32, [3]>([1, 57, 768])]; |
| tensor<fp16, [1, 57, 12, 64]> attention_output_23_cast_fp16 = transpose(perm = attention_output_23_perm_0, x = attention_output_21_cast_fp16)[name = string("transpose_133")]; |
| tensor<fp16, [1, 57, 768]> input_69_cast_fp16 = reshape(shape = var_542, x = attention_output_23_cast_fp16)[name = string("input_69_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_34_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_weight_to_fp16, x = input_69_cast_fp16)[name = string("linear_34_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_71_cast_fp16 = add(x = hidden_states_11_cast_fp16, y = linear_34_cast_fp16)[name = string("input_71_cast_fp16")]; |
| tensor<int32, [1]> input_73_axes_0 = const()[name = string("input_73_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> input_73_cast_fp16 = layer_norm(axes = input_73_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_weight_to_fp16, x = input_71_cast_fp16)[name = string("input_73_cast_fp16")]; |
| tensor<fp16, [1, 57, 2048]> linear_35_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_weight_to_fp16, x = input_73_cast_fp16)[name = string("linear_35_cast_fp16")]; |
| string input_77_mode_0 = const()[name = string("input_77_mode_0"), val = string("TANH_APPROXIMATION")]; |
| tensor<fp16, [1, 57, 2048]> input_77_cast_fp16 = gelu(mode = input_77_mode_0, x = linear_35_cast_fp16)[name = string("input_77_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_36_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_weight_to_fp16, x = input_77_cast_fp16)[name = string("linear_36_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_79_cast_fp16 = add(x = linear_36_cast_fp16, y = input_73_cast_fp16)[name = string("input_79_cast_fp16")]; |
| tensor<int32, [1]> hidden_states_13_axes_0 = const()[name = string("hidden_states_13_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> hidden_states_13_cast_fp16 = layer_norm(axes = hidden_states_13_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_weight_to_fp16, x = input_79_cast_fp16)[name = string("hidden_states_13_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_37_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_weight_to_fp16, x = hidden_states_13_cast_fp16)[name = string("linear_37_cast_fp16")]; |
| tensor<int32, [4]> var_593 = const()[name = string("op_593"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_75_cast_fp16 = reshape(shape = var_593, x = linear_37_cast_fp16)[name = string("x_75_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_38_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_weight_to_fp16, x = hidden_states_13_cast_fp16)[name = string("linear_38_cast_fp16")]; |
| tensor<int32, [4]> var_602 = const()[name = string("op_602"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_79_cast_fp16 = reshape(shape = var_602, x = linear_38_cast_fp16)[name = string("x_79_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_39_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_weight_to_fp16, x = hidden_states_13_cast_fp16)[name = string("linear_39_cast_fp16")]; |
| tensor<int32, [4]> var_611 = const()[name = string("op_611"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_83_cast_fp16 = reshape(shape = var_611, x = linear_39_cast_fp16)[name = string("x_83_cast_fp16")]; |
| tensor<int32, [4]> transpose_90_perm_0 = const()[name = string("transpose_90_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_91_perm_0 = const()[name = string("transpose_91_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_92_perm_0 = const()[name = string("transpose_92_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_92 = transpose(perm = transpose_92_perm_0, x = x_83_cast_fp16)[name = string("transpose_130")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_91 = transpose(perm = transpose_91_perm_0, x = x_79_cast_fp16)[name = string("transpose_131")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_90 = transpose(perm = transpose_90_perm_0, x = x_75_cast_fp16)[name = string("transpose_132")]; |
| tensor<fp16, [1, 12, 57, 64]> attention_output_25_cast_fp16 = scaled_dot_product_attention(attn_mask = attention_mask_cast_fp16, key = transpose_91, query = transpose_90, value = transpose_92)[name = string("attention_output_25_cast_fp16")]; |
| tensor<int32, [4]> attention_output_27_perm_0 = const()[name = string("attention_output_27_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [3]> var_617 = const()[name = string("op_617"), val = tensor<int32, [3]>([1, 57, 768])]; |
| tensor<fp16, [1, 57, 12, 64]> attention_output_27_cast_fp16 = transpose(perm = attention_output_27_perm_0, x = attention_output_25_cast_fp16)[name = string("transpose_129")]; |
| tensor<fp16, [1, 57, 768]> input_81_cast_fp16 = reshape(shape = var_617, x = attention_output_27_cast_fp16)[name = string("input_81_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_40_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_weight_to_fp16, x = input_81_cast_fp16)[name = string("linear_40_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_83_cast_fp16 = add(x = hidden_states_13_cast_fp16, y = linear_40_cast_fp16)[name = string("input_83_cast_fp16")]; |
| tensor<int32, [1]> input_85_axes_0 = const()[name = string("input_85_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> input_85_cast_fp16 = layer_norm(axes = input_85_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_weight_to_fp16, x = input_83_cast_fp16)[name = string("input_85_cast_fp16")]; |
| tensor<fp16, [1, 57, 2048]> linear_41_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_weight_to_fp16, x = input_85_cast_fp16)[name = string("linear_41_cast_fp16")]; |
| string input_89_mode_0 = const()[name = string("input_89_mode_0"), val = string("TANH_APPROXIMATION")]; |
| tensor<fp16, [1, 57, 2048]> input_89_cast_fp16 = gelu(mode = input_89_mode_0, x = linear_41_cast_fp16)[name = string("input_89_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_42_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_weight_to_fp16, x = input_89_cast_fp16)[name = string("linear_42_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_91_cast_fp16 = add(x = linear_42_cast_fp16, y = input_85_cast_fp16)[name = string("input_91_cast_fp16")]; |
| tensor<int32, [1]> hidden_states_15_axes_0 = const()[name = string("hidden_states_15_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> hidden_states_15_cast_fp16 = layer_norm(axes = hidden_states_15_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_weight_to_fp16, x = input_91_cast_fp16)[name = string("hidden_states_15_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_43_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_weight_to_fp16, x = hidden_states_15_cast_fp16)[name = string("linear_43_cast_fp16")]; |
| tensor<int32, [4]> var_668 = const()[name = string("op_668"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_87_cast_fp16 = reshape(shape = var_668, x = linear_43_cast_fp16)[name = string("x_87_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_44_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_weight_to_fp16, x = hidden_states_15_cast_fp16)[name = string("linear_44_cast_fp16")]; |
| tensor<int32, [4]> var_677 = const()[name = string("op_677"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_91_cast_fp16 = reshape(shape = var_677, x = linear_44_cast_fp16)[name = string("x_91_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_45_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_weight_to_fp16, x = hidden_states_15_cast_fp16)[name = string("linear_45_cast_fp16")]; |
| tensor<int32, [4]> var_686 = const()[name = string("op_686"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_95_cast_fp16 = reshape(shape = var_686, x = linear_45_cast_fp16)[name = string("x_95_cast_fp16")]; |
| tensor<int32, [4]> transpose_93_perm_0 = const()[name = string("transpose_93_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_94_perm_0 = const()[name = string("transpose_94_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_95_perm_0 = const()[name = string("transpose_95_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_95 = transpose(perm = transpose_95_perm_0, x = x_95_cast_fp16)[name = string("transpose_126")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_94 = transpose(perm = transpose_94_perm_0, x = x_91_cast_fp16)[name = string("transpose_127")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_93 = transpose(perm = transpose_93_perm_0, x = x_87_cast_fp16)[name = string("transpose_128")]; |
| tensor<fp16, [1, 12, 57, 64]> attention_output_29_cast_fp16 = scaled_dot_product_attention(attn_mask = attention_mask_cast_fp16, key = transpose_94, query = transpose_93, value = transpose_95)[name = string("attention_output_29_cast_fp16")]; |
| tensor<int32, [4]> attention_output_31_perm_0 = const()[name = string("attention_output_31_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [3]> var_692 = const()[name = string("op_692"), val = tensor<int32, [3]>([1, 57, 768])]; |
| tensor<fp16, [1, 57, 12, 64]> attention_output_31_cast_fp16 = transpose(perm = attention_output_31_perm_0, x = attention_output_29_cast_fp16)[name = string("transpose_125")]; |
| tensor<fp16, [1, 57, 768]> input_93_cast_fp16 = reshape(shape = var_692, x = attention_output_31_cast_fp16)[name = string("input_93_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_46_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_weight_to_fp16, x = input_93_cast_fp16)[name = string("linear_46_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_95_cast_fp16 = add(x = hidden_states_15_cast_fp16, y = linear_46_cast_fp16)[name = string("input_95_cast_fp16")]; |
| tensor<int32, [1]> input_97_axes_0 = const()[name = string("input_97_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> input_97_cast_fp16 = layer_norm(axes = input_97_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_weight_to_fp16, x = input_95_cast_fp16)[name = string("input_97_cast_fp16")]; |
| tensor<fp16, [1, 57, 2048]> linear_47_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_weight_to_fp16, x = input_97_cast_fp16)[name = string("linear_47_cast_fp16")]; |
| string input_101_mode_0 = const()[name = string("input_101_mode_0"), val = string("TANH_APPROXIMATION")]; |
| tensor<fp16, [1, 57, 2048]> input_101_cast_fp16 = gelu(mode = input_101_mode_0, x = linear_47_cast_fp16)[name = string("input_101_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_48_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_weight_to_fp16, x = input_101_cast_fp16)[name = string("linear_48_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_103_cast_fp16 = add(x = linear_48_cast_fp16, y = input_97_cast_fp16)[name = string("input_103_cast_fp16")]; |
| tensor<int32, [1]> hidden_states_17_axes_0 = const()[name = string("hidden_states_17_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> hidden_states_17_cast_fp16 = layer_norm(axes = hidden_states_17_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_weight_to_fp16, x = input_103_cast_fp16)[name = string("hidden_states_17_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_49_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_weight_to_fp16, x = hidden_states_17_cast_fp16)[name = string("linear_49_cast_fp16")]; |
| tensor<int32, [4]> var_743 = const()[name = string("op_743"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_99_cast_fp16 = reshape(shape = var_743, x = linear_49_cast_fp16)[name = string("x_99_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_50_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_weight_to_fp16, x = hidden_states_17_cast_fp16)[name = string("linear_50_cast_fp16")]; |
| tensor<int32, [4]> var_752 = const()[name = string("op_752"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_103_cast_fp16 = reshape(shape = var_752, x = linear_50_cast_fp16)[name = string("x_103_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_51_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_weight_to_fp16, x = hidden_states_17_cast_fp16)[name = string("linear_51_cast_fp16")]; |
| tensor<int32, [4]> var_761 = const()[name = string("op_761"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_107_cast_fp16 = reshape(shape = var_761, x = linear_51_cast_fp16)[name = string("x_107_cast_fp16")]; |
| tensor<int32, [4]> transpose_96_perm_0 = const()[name = string("transpose_96_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_97_perm_0 = const()[name = string("transpose_97_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_98_perm_0 = const()[name = string("transpose_98_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_98 = transpose(perm = transpose_98_perm_0, x = x_107_cast_fp16)[name = string("transpose_122")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_97 = transpose(perm = transpose_97_perm_0, x = x_103_cast_fp16)[name = string("transpose_123")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_96 = transpose(perm = transpose_96_perm_0, x = x_99_cast_fp16)[name = string("transpose_124")]; |
| tensor<fp16, [1, 12, 57, 64]> attention_output_33_cast_fp16 = scaled_dot_product_attention(attn_mask = attention_mask_cast_fp16, key = transpose_97, query = transpose_96, value = transpose_98)[name = string("attention_output_33_cast_fp16")]; |
| tensor<int32, [4]> attention_output_35_perm_0 = const()[name = string("attention_output_35_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [3]> var_767 = const()[name = string("op_767"), val = tensor<int32, [3]>([1, 57, 768])]; |
| tensor<fp16, [1, 57, 12, 64]> attention_output_35_cast_fp16 = transpose(perm = attention_output_35_perm_0, x = attention_output_33_cast_fp16)[name = string("transpose_121")]; |
| tensor<fp16, [1, 57, 768]> input_105_cast_fp16 = reshape(shape = var_767, x = attention_output_35_cast_fp16)[name = string("input_105_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_52_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_weight_to_fp16, x = input_105_cast_fp16)[name = string("linear_52_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_107_cast_fp16 = add(x = hidden_states_17_cast_fp16, y = linear_52_cast_fp16)[name = string("input_107_cast_fp16")]; |
| tensor<int32, [1]> input_109_axes_0 = const()[name = string("input_109_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> input_109_cast_fp16 = layer_norm(axes = input_109_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_weight_to_fp16, x = input_107_cast_fp16)[name = string("input_109_cast_fp16")]; |
| tensor<fp16, [1, 57, 2048]> linear_53_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_weight_to_fp16, x = input_109_cast_fp16)[name = string("linear_53_cast_fp16")]; |
| string input_113_mode_0 = const()[name = string("input_113_mode_0"), val = string("TANH_APPROXIMATION")]; |
| tensor<fp16, [1, 57, 2048]> input_113_cast_fp16 = gelu(mode = input_113_mode_0, x = linear_53_cast_fp16)[name = string("input_113_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_54_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_weight_to_fp16, x = input_113_cast_fp16)[name = string("linear_54_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_115_cast_fp16 = add(x = linear_54_cast_fp16, y = input_109_cast_fp16)[name = string("input_115_cast_fp16")]; |
| tensor<int32, [1]> hidden_states_19_axes_0 = const()[name = string("hidden_states_19_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> hidden_states_19_cast_fp16 = layer_norm(axes = hidden_states_19_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_weight_to_fp16, x = input_115_cast_fp16)[name = string("hidden_states_19_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_55_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_weight_to_fp16, x = hidden_states_19_cast_fp16)[name = string("linear_55_cast_fp16")]; |
| tensor<int32, [4]> var_818 = const()[name = string("op_818"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_111_cast_fp16 = reshape(shape = var_818, x = linear_55_cast_fp16)[name = string("x_111_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_56_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_weight_to_fp16, x = hidden_states_19_cast_fp16)[name = string("linear_56_cast_fp16")]; |
| tensor<int32, [4]> var_827 = const()[name = string("op_827"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_115_cast_fp16 = reshape(shape = var_827, x = linear_56_cast_fp16)[name = string("x_115_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_57_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_weight_to_fp16, x = hidden_states_19_cast_fp16)[name = string("linear_57_cast_fp16")]; |
| tensor<int32, [4]> var_836 = const()[name = string("op_836"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_119_cast_fp16 = reshape(shape = var_836, x = linear_57_cast_fp16)[name = string("x_119_cast_fp16")]; |
| tensor<int32, [4]> transpose_99_perm_0 = const()[name = string("transpose_99_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_100_perm_0 = const()[name = string("transpose_100_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_101_perm_0 = const()[name = string("transpose_101_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_101 = transpose(perm = transpose_101_perm_0, x = x_119_cast_fp16)[name = string("transpose_118")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_100 = transpose(perm = transpose_100_perm_0, x = x_115_cast_fp16)[name = string("transpose_119")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_99 = transpose(perm = transpose_99_perm_0, x = x_111_cast_fp16)[name = string("transpose_120")]; |
| tensor<fp16, [1, 12, 57, 64]> attention_output_37_cast_fp16 = scaled_dot_product_attention(attn_mask = attention_mask_cast_fp16, key = transpose_100, query = transpose_99, value = transpose_101)[name = string("attention_output_37_cast_fp16")]; |
| tensor<int32, [4]> attention_output_39_perm_0 = const()[name = string("attention_output_39_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [3]> var_842 = const()[name = string("op_842"), val = tensor<int32, [3]>([1, 57, 768])]; |
| tensor<fp16, [1, 57, 12, 64]> attention_output_39_cast_fp16 = transpose(perm = attention_output_39_perm_0, x = attention_output_37_cast_fp16)[name = string("transpose_117")]; |
| tensor<fp16, [1, 57, 768]> input_117_cast_fp16 = reshape(shape = var_842, x = attention_output_39_cast_fp16)[name = string("input_117_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_58_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_weight_to_fp16, x = input_117_cast_fp16)[name = string("linear_58_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_119_cast_fp16 = add(x = hidden_states_19_cast_fp16, y = linear_58_cast_fp16)[name = string("input_119_cast_fp16")]; |
| tensor<int32, [1]> input_121_axes_0 = const()[name = string("input_121_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> input_121_cast_fp16 = layer_norm(axes = input_121_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_weight_to_fp16, x = input_119_cast_fp16)[name = string("input_121_cast_fp16")]; |
| tensor<fp16, [1, 57, 2048]> linear_59_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_weight_to_fp16, x = input_121_cast_fp16)[name = string("linear_59_cast_fp16")]; |
| string input_125_mode_0 = const()[name = string("input_125_mode_0"), val = string("TANH_APPROXIMATION")]; |
| tensor<fp16, [1, 57, 2048]> input_125_cast_fp16 = gelu(mode = input_125_mode_0, x = linear_59_cast_fp16)[name = string("input_125_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_60_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_weight_to_fp16, x = input_125_cast_fp16)[name = string("linear_60_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_127_cast_fp16 = add(x = linear_60_cast_fp16, y = input_121_cast_fp16)[name = string("input_127_cast_fp16")]; |
| tensor<int32, [1]> hidden_states_21_axes_0 = const()[name = string("hidden_states_21_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> hidden_states_21_cast_fp16 = layer_norm(axes = hidden_states_21_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_weight_to_fp16, x = input_127_cast_fp16)[name = string("hidden_states_21_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_61_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_weight_to_fp16, x = hidden_states_21_cast_fp16)[name = string("linear_61_cast_fp16")]; |
| tensor<int32, [4]> var_893 = const()[name = string("op_893"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_123_cast_fp16 = reshape(shape = var_893, x = linear_61_cast_fp16)[name = string("x_123_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_62_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_weight_to_fp16, x = hidden_states_21_cast_fp16)[name = string("linear_62_cast_fp16")]; |
| tensor<int32, [4]> var_902 = const()[name = string("op_902"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_127_cast_fp16 = reshape(shape = var_902, x = linear_62_cast_fp16)[name = string("x_127_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_63_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_weight_to_fp16, x = hidden_states_21_cast_fp16)[name = string("linear_63_cast_fp16")]; |
| tensor<int32, [4]> var_911 = const()[name = string("op_911"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_131_cast_fp16 = reshape(shape = var_911, x = linear_63_cast_fp16)[name = string("x_131_cast_fp16")]; |
| tensor<int32, [4]> transpose_102_perm_0 = const()[name = string("transpose_102_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_103_perm_0 = const()[name = string("transpose_103_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_104_perm_0 = const()[name = string("transpose_104_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_104 = transpose(perm = transpose_104_perm_0, x = x_131_cast_fp16)[name = string("transpose_114")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_103 = transpose(perm = transpose_103_perm_0, x = x_127_cast_fp16)[name = string("transpose_115")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_102 = transpose(perm = transpose_102_perm_0, x = x_123_cast_fp16)[name = string("transpose_116")]; |
| tensor<fp16, [1, 12, 57, 64]> attention_output_41_cast_fp16 = scaled_dot_product_attention(attn_mask = attention_mask_cast_fp16, key = transpose_103, query = transpose_102, value = transpose_104)[name = string("attention_output_41_cast_fp16")]; |
| tensor<int32, [4]> attention_output_43_perm_0 = const()[name = string("attention_output_43_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [3]> var_917 = const()[name = string("op_917"), val = tensor<int32, [3]>([1, 57, 768])]; |
| tensor<fp16, [1, 57, 12, 64]> attention_output_43_cast_fp16 = transpose(perm = attention_output_43_perm_0, x = attention_output_41_cast_fp16)[name = string("transpose_113")]; |
| tensor<fp16, [1, 57, 768]> input_129_cast_fp16 = reshape(shape = var_917, x = attention_output_43_cast_fp16)[name = string("input_129_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_64_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_weight_to_fp16, x = input_129_cast_fp16)[name = string("linear_64_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_131_cast_fp16 = add(x = hidden_states_21_cast_fp16, y = linear_64_cast_fp16)[name = string("input_131_cast_fp16")]; |
| tensor<int32, [1]> input_133_axes_0 = const()[name = string("input_133_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> input_133_cast_fp16 = layer_norm(axes = input_133_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_weight_to_fp16, x = input_131_cast_fp16)[name = string("input_133_cast_fp16")]; |
| tensor<fp16, [1, 57, 2048]> linear_65_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_weight_to_fp16, x = input_133_cast_fp16)[name = string("linear_65_cast_fp16")]; |
| string input_137_mode_0 = const()[name = string("input_137_mode_0"), val = string("TANH_APPROXIMATION")]; |
| tensor<fp16, [1, 57, 2048]> input_137_cast_fp16 = gelu(mode = input_137_mode_0, x = linear_65_cast_fp16)[name = string("input_137_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_66_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_weight_to_fp16, x = input_137_cast_fp16)[name = string("linear_66_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_139_cast_fp16 = add(x = linear_66_cast_fp16, y = input_133_cast_fp16)[name = string("input_139_cast_fp16")]; |
| tensor<int32, [1]> hidden_states_axes_0 = const()[name = string("hidden_states_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> hidden_states_cast_fp16 = layer_norm(axes = hidden_states_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_weight_to_fp16, x = input_139_cast_fp16)[name = string("hidden_states_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_67_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_query_weight_to_fp16, x = hidden_states_cast_fp16)[name = string("linear_67_cast_fp16")]; |
| tensor<int32, [4]> var_968 = const()[name = string("op_968"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_135_cast_fp16 = reshape(shape = var_968, x = linear_67_cast_fp16)[name = string("x_135_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_68_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_key_weight_to_fp16, x = hidden_states_cast_fp16)[name = string("linear_68_cast_fp16")]; |
| tensor<int32, [4]> var_977 = const()[name = string("op_977"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_139_cast_fp16 = reshape(shape = var_977, x = linear_68_cast_fp16)[name = string("x_139_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_69_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_value_weight_to_fp16, x = hidden_states_cast_fp16)[name = string("linear_69_cast_fp16")]; |
| tensor<int32, [4]> var_986 = const()[name = string("op_986"), val = tensor<int32, [4]>([1, 57, 12, 64])]; |
| tensor<fp16, [1, 57, 12, 64]> x_cast_fp16 = reshape(shape = var_986, x = linear_69_cast_fp16)[name = string("x_cast_fp16")]; |
| tensor<int32, [4]> transpose_105_perm_0 = const()[name = string("transpose_105_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_106_perm_0 = const()[name = string("transpose_106_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [4]> transpose_107_perm_0 = const()[name = string("transpose_107_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_107 = transpose(perm = transpose_107_perm_0, x = x_cast_fp16)[name = string("transpose_110")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_106 = transpose(perm = transpose_106_perm_0, x = x_139_cast_fp16)[name = string("transpose_111")]; |
| tensor<fp16, [1, 12, 57, 64]> transpose_105 = transpose(perm = transpose_105_perm_0, x = x_135_cast_fp16)[name = string("transpose_112")]; |
| tensor<fp16, [1, 12, 57, 64]> attention_output_45_cast_fp16 = scaled_dot_product_attention(attn_mask = attention_mask_cast_fp16, key = transpose_106, query = transpose_105, value = transpose_107)[name = string("attention_output_45_cast_fp16")]; |
| tensor<int32, [4]> attention_output_perm_0 = const()[name = string("attention_output_perm_0"), val = tensor<int32, [4]>([0, 2, 1, 3])]; |
| tensor<int32, [3]> var_992 = const()[name = string("op_992"), val = tensor<int32, [3]>([1, 57, 768])]; |
| tensor<fp16, [1, 57, 12, 64]> attention_output_cast_fp16 = transpose(perm = attention_output_perm_0, x = attention_output_45_cast_fp16)[name = string("transpose_109")]; |
| tensor<fp16, [1, 57, 768]> input_141_cast_fp16 = reshape(shape = var_992, x = attention_output_cast_fp16)[name = string("input_141_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_70_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_dense_weight_to_fp16, x = input_141_cast_fp16)[name = string("linear_70_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_143_cast_fp16 = add(x = hidden_states_cast_fp16, y = linear_70_cast_fp16)[name = string("input_143_cast_fp16")]; |
| tensor<int32, [1]> input_145_axes_0 = const()[name = string("input_145_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> input_145_cast_fp16 = layer_norm(axes = input_145_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_attention_LayerNorm_weight_to_fp16, x = input_143_cast_fp16)[name = string("input_145_cast_fp16")]; |
| tensor<fp16, [1, 57, 2048]> linear_71_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_weight_to_fp16, x = input_145_cast_fp16)[name = string("linear_71_cast_fp16")]; |
| string input_149_mode_0 = const()[name = string("input_149_mode_0"), val = string("TANH_APPROXIMATION")]; |
| tensor<fp16, [1, 57, 2048]> input_149_cast_fp16 = gelu(mode = input_149_mode_0, x = linear_71_cast_fp16)[name = string("input_149_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> linear_72_cast_fp16 = linear(bias = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_bias_to_fp16, weight = bert_encoder_albert_layer_groups_0_albert_layers_0_ffn_output_weight_to_fp16, x = input_149_cast_fp16)[name = string("linear_72_cast_fp16")]; |
| tensor<fp16, [1, 57, 768]> input_151_cast_fp16 = add(x = linear_72_cast_fp16, y = input_145_cast_fp16)[name = string("input_151_cast_fp16")]; |
| tensor<int32, [1]> sequence_output_axes_0 = const()[name = string("sequence_output_axes_0"), val = tensor<int32, [1]>([-1])]; |
| tensor<fp16, [1, 57, 768]> sequence_output = layer_norm(axes = sequence_output_axes_0, beta = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_bias_to_fp16, epsilon = var_118_to_fp16, gamma = bert_encoder_albert_layer_groups_0_albert_layers_0_full_layer_layer_norm_weight_to_fp16, x = input_151_cast_fp16)[name = string("sequence_output_cast_fp16")]; |
| tensor<fp16, [512, 768]> bert_encoder_weight_to_fp16 = const()[name = string("bert_encoder_weight_to_fp16"), val = tensor<fp16, [512, 768]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(11302912)))]; |
| tensor<fp16, [512]> bert_encoder_bias_to_fp16 = const()[name = string("bert_encoder_bias_to_fp16"), val = tensor<fp16, [512]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(12089408)))]; |
| tensor<fp16, [1, 57, 512]> linear_73_cast_fp16 = linear(bias = bert_encoder_bias_to_fp16, weight = bert_encoder_weight_to_fp16, x = sequence_output)[name = string("linear_73_cast_fp16")]; |
| tensor<int32, [3]> var_1030_perm_0 = const()[name = string("op_1030_perm_0"), val = tensor<int32, [3]>([0, -1, -2])]; |
| tensor<fp16, [1, 512, 57]> var_1030 = transpose(perm = var_1030_perm_0, x = linear_73_cast_fp16)[name = string("transpose_108")]; |
| } -> (sequence_output, var_1030); |
| } |
