| {"module": "keras.src.models.functional", "class_name": "Functional", "config": {"name": "functional_1", "trainable": true, "layers": [{"module": "keras.layers", "class_name": "InputLayer", "config": {"batch_shape": [null, null], "dtype": "int64", "sparse": false, "ragged": false, "name": "encoder_input"}, "registered_name": null, "name": "encoder_input", "inbound_nodes": []}, {"module": "keras_hub.src.layers.modeling.token_and_position_embedding", "class_name": "TokenAndPositionEmbedding", "config": {"name": "token_and_position_embedding", "trainable": true, "dtype": {"module": "keras", "class_name": "DTypePolicy", "config": {"name": "float32"}, "registered_name": null}, "vocabulary_size": 34407, "sequence_length": 210, "embedding_dim": 256, "embeddings_initializer": {"module": "keras.initializers", "class_name": "RandomUniform", "config": {"seed": null, "minval": -0.05, "maxval": 0.05}, "registered_name": null}, "tie_weights": true, "mask_zero": false}, "registered_name": "keras_hub>TokenAndPositionEmbedding", "build_config": {"input_shape": [null, null]}, "name": "token_and_position_embedding", "inbound_nodes": [{"args": [{"class_name": "__keras_tensor__", "config": {"shape": [null, null], "dtype": "int64", "keras_history": ["encoder_input", 0, 0]}}], "kwargs": {}}]}, {"module": "keras.layers", "class_name": "InputLayer", "config": {"batch_shape": [null, null], "dtype": "int64", "sparse": false, "ragged": false, "name": "decoder_input"}, "registered_name": null, "name": "decoder_input", "inbound_nodes": [], "shared_object_id": 135257918797968}, {"module": "keras_hub.src.layers.modeling.transformer_encoder", "class_name": "TransformerEncoder", "config": {"name": "transformer_encoder", "trainable": true, "dtype": {"module": "keras", "class_name": "DTypePolicy", "config": {"name": "float32"}, "registered_name": null, "shared_object_id": 135258055796560}, "intermediate_dim": 256, "num_heads": 8, "dropout": 0, "activation": "relu", "layer_norm_epsilon": 1e-05, "kernel_initializer": {"module": "keras.initializers", "class_name": "GlorotUniform", "config": {"seed": null}, "registered_name": null}, "bias_initializer": {"module": "keras.initializers", "class_name": "Zeros", "config": {}, "registered_name": null}, "normalize_first": false}, "registered_name": "keras_hub>TransformerEncoder", "build_config": {"input_shape": [null, null, 256]}, "name": "transformer_encoder", "inbound_nodes": [{"args": [{"class_name": "__keras_tensor__", "config": {"shape": [null, null, 256], "dtype": "float32", "keras_history": ["token_and_position_embedding", 0, 0]}}], "kwargs": {}}]}, {"module": "keras.src.models.functional", "class_name": "Functional", "config": {"name": "functional", "trainable": true, "layers": [{"module": "keras.layers", "class_name": "InputLayer", "config": {"batch_shape": [null, null], "dtype": "int64", "sparse": false, "ragged": false, "name": "decoder_input"}, "registered_name": null, "shared_object_id": 135257918797968, "name": "decoder_input", "inbound_nodes": []}, {"module": "keras_hub.src.layers.modeling.token_and_position_embedding", "class_name": "TokenAndPositionEmbedding", "config": {"name": "token_and_position_embedding_1", "trainable": true, "dtype": {"module": "keras", "class_name": "DTypePolicy", "config": {"name": "float32"}, "registered_name": null, "shared_object_id": 135258055796560}, "vocabulary_size": 51212, "sequence_length": 210, "embedding_dim": 256, "embeddings_initializer": {"module": "keras.initializers", "class_name": "RandomUniform", "config": {"seed": null, "minval": -0.05, "maxval": 0.05}, "registered_name": null}, "tie_weights": true, "mask_zero": true}, "registered_name": "keras_hub>TokenAndPositionEmbedding", "build_config": {"input_shape": [null, null]}, "name": "token_and_position_embedding_1", "inbound_nodes": [{"args": [{"class_name": "__keras_tensor__", "config": {"shape": [null, null], "dtype": "int64", "keras_history": ["decoder_input", 0, 0]}}], "kwargs": {}}]}, {"module": "keras.layers", "class_name": "InputLayer", "config": {"batch_shape": [null, null, 256], "dtype": "float32", "sparse": false, "ragged": false, "name": "input_layer"}, "registered_name": null, "name": "input_layer", "inbound_nodes": []}, {"module": "keras_hub.src.layers.modeling.transformer_decoder", "class_name": "TransformerDecoder", "config": {"name": "transformer_decoder", "trainable": true, "dtype": {"module": "keras", "class_name": "DTypePolicy", "config": {"name": "float32"}, "registered_name": null, "shared_object_id": 135258055796560}, "intermediate_dim": 256, "num_heads": 8, "dropout": 0, "activation": "relu", "layer_norm_epsilon": 1e-05, "kernel_initializer": {"module": "keras.initializers", "class_name": "GlorotUniform", "config": {"seed": null}, "registered_name": null}, "bias_initializer": {"module": "keras.initializers", "class_name": "Zeros", "config": {}, "registered_name": null}, "normalize_first": false, "decoder_sequence_shape": [null, null, 256], "encoder_sequence_shape": [null, null, 256]}, "registered_name": "keras_hub>TransformerDecoder", "build_config": {"shapes_dict": {"decoder_sequence_shape": [null, null, 256], "encoder_sequence_shape": [null, null, 256]}}, "name": "transformer_decoder", "inbound_nodes": [{"args": [{"class_name": "__keras_tensor__", "config": {"shape": [null, null, 256], "dtype": "float32", "keras_history": ["token_and_position_embedding_1", 0, 0]}}, {"class_name": "__keras_tensor__", "config": {"shape": [null, null, 256], "dtype": "float32", "keras_history": ["input_layer", 0, 0]}}], "kwargs": {}}]}, {"module": "keras.layers", "class_name": "Dropout", "config": {"name": "dropout_3", "trainable": true, "dtype": {"module": "keras", "class_name": "DTypePolicy", "config": {"name": "float32"}, "registered_name": null, "shared_object_id": 135258055796560}, "rate": 0.4, "seed": null, "noise_shape": null}, "registered_name": null, "name": "dropout_3", "inbound_nodes": [{"args": [{"class_name": "__keras_tensor__", "config": {"shape": [null, null, 256], "dtype": "float32", "keras_history": ["transformer_decoder", 0, 0]}}], "kwargs": {"training": false}}]}, {"module": "keras.layers", "class_name": "Dense", "config": {"name": "dense", "trainable": true, "dtype": {"module": "keras", "class_name": "DTypePolicy", "config": {"name": "float32"}, "registered_name": null, "shared_object_id": 135258055796560}, "units": 51212, "activation": "softmax", "use_bias": true, "kernel_initializer": {"module": "keras.initializers", "class_name": "GlorotUniform", "config": {"seed": null}, "registered_name": null}, "bias_initializer": {"module": "keras.initializers", "class_name": "Zeros", "config": {}, "registered_name": null}, "kernel_regularizer": null, "bias_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "registered_name": null, "build_config": {"input_shape": [null, null, 256]}, "name": "dense", "inbound_nodes": [{"args": [{"class_name": "__keras_tensor__", "config": {"shape": [null, null, 256], "dtype": "float32", "keras_history": ["dropout_3", 0, 0]}}], "kwargs": {}}]}], "input_layers": [["decoder_input", 0, 0], ["input_layer", 0, 0]], "output_layers": [["dense", 0, 0]]}, "registered_name": "Functional", "build_config": {"input_shape": null}, "compile_config": {}, "name": "functional", "inbound_nodes": [{"args": [[{"class_name": "__keras_tensor__", "config": {"shape": [null, null], "dtype": "int64", "keras_history": ["decoder_input", 0, 0]}}, {"class_name": "__keras_tensor__", "config": {"shape": [null, null, 256], "dtype": "float32", "keras_history": ["transformer_encoder", 0, 0]}}]], "kwargs": {"mask": [null, null]}}]}], "input_layers": [["encoder_input", 0, 0], ["decoder_input", 0, 0]], "output_layers": [["functional", 1, 0]]}, "registered_name": "Functional", "build_config": {"input_shape": null}, "compile_config": {"optimizer": {"module": "keras.optimizers", "class_name": "Adam", "config": {"name": "adam", "learning_rate": 0.0010000000474974513, "weight_decay": null, "clipnorm": null, "global_clipnorm": null, "clipvalue": null, "use_ema": false, "ema_momentum": 0.99, "ema_overwrite_frequency": null, "loss_scale_factor": null, "gradient_accumulation_steps": null, "beta_1": 0.9, "beta_2": 0.999, "epsilon": 1e-07, "amsgrad": false}, "registered_name": null}, "loss": "sparse_categorical_crossentropy", "loss_weights": null, "metrics": ["accuracy"], "weighted_metrics": null, "run_eagerly": false, "steps_per_execution": 1, "jit_compile": true}} |