| { | |
| "_name_or_path": "/content/Classifier", | |
| "architectures": [ | |
| "BertModel" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "classifier_dropout": null, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "input_layers": [ | |
| [ | |
| "agent_txt_inputids", | |
| 0, | |
| 0 | |
| ], | |
| [ | |
| "agent_txt_mask", | |
| 0, | |
| 0 | |
| ] | |
| ], | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-12, | |
| "layers": [ | |
| { | |
| "class_name": "InputLayer", | |
| "config": { | |
| "batch_input_shape": [ | |
| null, | |
| 512 | |
| ], | |
| "dtype": "int32", | |
| "name": "agent_txt_inputids", | |
| "ragged": false, | |
| "sparse": false | |
| }, | |
| "inbound_nodes": [], | |
| "name": "agent_txt_inputids" | |
| }, | |
| { | |
| "class_name": "InputLayer", | |
| "config": { | |
| "batch_input_shape": [ | |
| null, | |
| 512 | |
| ], | |
| "dtype": "int32", | |
| "name": "agent_txt_mask", | |
| "ragged": false, | |
| "sparse": false | |
| }, | |
| "inbound_nodes": [], | |
| "name": "agent_txt_mask" | |
| }, | |
| { | |
| "class_name": "Custom>TFBertMainLayer", | |
| "config": { | |
| "config": { | |
| "_name_or_path": "/content/drive/MyDrive/ARA-BERT-TF", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "BertForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "classifier_dropout": null, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 512, | |
| "min_length": 0, | |
| "model_type": "bert", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 12, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 12, | |
| "num_return_sequences": 1, | |
| "output_attentions": true, | |
| "output_hidden_states": true, | |
| "output_scores": false, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": null, | |
| "torchscript": false, | |
| "transformers_version": "4.33.2", | |
| "type_vocab_size": 2, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "vocab_size": 64000 | |
| }, | |
| "dtype": "float32", | |
| "name": "bert", | |
| "trainable": true | |
| }, | |
| "inbound_nodes": [ | |
| [ | |
| [ | |
| "agent_txt_inputids", | |
| 0, | |
| 0, | |
| { | |
| "attention_mask": [ | |
| "agent_txt_mask", | |
| 0, | |
| 0 | |
| ] | |
| } | |
| ] | |
| ] | |
| ], | |
| "name": "bert" | |
| }, | |
| { | |
| "class_name": "Sequential", | |
| "config": { | |
| "layers": [ | |
| { | |
| "class_name": "InputLayer", | |
| "config": { | |
| "batch_input_shape": [ | |
| null, | |
| 512, | |
| 768 | |
| ], | |
| "dtype": "float32", | |
| "name": "encoder_input", | |
| "ragged": false, | |
| "sparse": false | |
| } | |
| }, | |
| { | |
| "class_name": "Bidirectional", | |
| "config": { | |
| "dtype": "float32", | |
| "layer": { | |
| "class_name": "GRU", | |
| "config": { | |
| "activation": "tanh", | |
| "activity_regularizer": null, | |
| "bias_constraint": null, | |
| "bias_initializer": { | |
| "class_name": "Zeros", | |
| "config": {}, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "bias_regularizer": null, | |
| "dropout": 0.0, | |
| "dtype": "float32", | |
| "go_backwards": false, | |
| "implementation": 2, | |
| "kernel_constraint": null, | |
| "kernel_initializer": { | |
| "class_name": "GlorotUniform", | |
| "config": { | |
| "seed": null | |
| }, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "kernel_regularizer": null, | |
| "name": "gru_6", | |
| "recurrent_activation": "sigmoid", | |
| "recurrent_constraint": null, | |
| "recurrent_dropout": 0.0, | |
| "recurrent_initializer": { | |
| "class_name": "Orthogonal", | |
| "config": { | |
| "gain": 1.0, | |
| "seed": null | |
| }, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "recurrent_regularizer": null, | |
| "reset_after": true, | |
| "return_sequences": true, | |
| "return_state": false, | |
| "stateful": false, | |
| "time_major": false, | |
| "trainable": true, | |
| "units": 64, | |
| "unroll": false, | |
| "use_bias": true | |
| }, | |
| "module": "keras.layers", | |
| "registered_name": null | |
| }, | |
| "merge_mode": "concat", | |
| "name": "encoder", | |
| "trainable": true | |
| } | |
| }, | |
| { | |
| "class_name": "GlobalMaxPooling1D", | |
| "config": { | |
| "data_format": "channels_last", | |
| "dtype": "float32", | |
| "keepdims": false, | |
| "name": "global_max_pooling1d_6", | |
| "trainable": true | |
| } | |
| }, | |
| { | |
| "class_name": "Dense", | |
| "config": { | |
| "activation": "linear", | |
| "activity_regularizer": null, | |
| "bias_constraint": null, | |
| "bias_initializer": { | |
| "class_name": "Zeros", | |
| "config": {}, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "bias_regularizer": null, | |
| "dtype": "float32", | |
| "kernel_constraint": null, | |
| "kernel_initializer": { | |
| "class_name": "HeNormal", | |
| "config": { | |
| "seed": null | |
| }, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "kernel_regularizer": null, | |
| "name": "dense_6", | |
| "trainable": true, | |
| "units": 512, | |
| "use_bias": true | |
| } | |
| }, | |
| { | |
| "class_name": "BatchNormalization", | |
| "config": { | |
| "axis": [ | |
| 1 | |
| ], | |
| "beta_constraint": null, | |
| "beta_initializer": { | |
| "class_name": "Zeros", | |
| "config": {}, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "beta_regularizer": null, | |
| "center": true, | |
| "dtype": "float32", | |
| "epsilon": 0.001, | |
| "gamma_constraint": null, | |
| "gamma_initializer": { | |
| "class_name": "Ones", | |
| "config": {}, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "gamma_regularizer": null, | |
| "momentum": 0.99, | |
| "moving_mean_initializer": { | |
| "class_name": "Zeros", | |
| "config": {}, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "moving_variance_initializer": { | |
| "class_name": "Ones", | |
| "config": {}, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "name": "batch_norm", | |
| "scale": true, | |
| "trainable": true | |
| } | |
| }, | |
| { | |
| "class_name": "Activation", | |
| "config": { | |
| "activation": "elu", | |
| "dtype": "float32", | |
| "name": "activation_18", | |
| "trainable": true | |
| } | |
| }, | |
| { | |
| "class_name": "Dropout", | |
| "config": { | |
| "dtype": "float32", | |
| "name": "dropout", | |
| "noise_shape": null, | |
| "rate": 0.2, | |
| "seed": null, | |
| "trainable": true | |
| } | |
| } | |
| ], | |
| "name": "sequential_6" | |
| }, | |
| "inbound_nodes": [ | |
| [ | |
| [ | |
| "bert", | |
| 0, | |
| 23, | |
| {} | |
| ] | |
| ] | |
| ], | |
| "name": "sequential_6" | |
| }, | |
| { | |
| "class_name": "Dense", | |
| "config": { | |
| "activation": "linear", | |
| "activity_regularizer": null, | |
| "bias_constraint": null, | |
| "bias_initializer": { | |
| "class_name": "Zeros", | |
| "config": {}, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "bias_regularizer": null, | |
| "dtype": "float32", | |
| "kernel_constraint": null, | |
| "kernel_initializer": { | |
| "class_name": "HeNormal", | |
| "config": { | |
| "seed": null | |
| }, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "kernel_regularizer": null, | |
| "name": "fully_connected_1", | |
| "trainable": true, | |
| "units": 128, | |
| "use_bias": true | |
| }, | |
| "inbound_nodes": [ | |
| [ | |
| [ | |
| "sequential_6", | |
| 1, | |
| 0, | |
| {} | |
| ] | |
| ] | |
| ], | |
| "name": "fully_connected_1" | |
| }, | |
| { | |
| "class_name": "BatchNormalization", | |
| "config": { | |
| "axis": [ | |
| 1 | |
| ], | |
| "beta_constraint": null, | |
| "beta_initializer": { | |
| "class_name": "Zeros", | |
| "config": {}, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "beta_regularizer": null, | |
| "center": true, | |
| "dtype": "float32", | |
| "epsilon": 0.001, | |
| "gamma_constraint": null, | |
| "gamma_initializer": { | |
| "class_name": "Ones", | |
| "config": {}, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "gamma_regularizer": null, | |
| "momentum": 0.99, | |
| "moving_mean_initializer": { | |
| "class_name": "Zeros", | |
| "config": {}, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "moving_variance_initializer": { | |
| "class_name": "Ones", | |
| "config": {}, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "name": "batch_norm_1", | |
| "scale": true, | |
| "trainable": true | |
| }, | |
| "inbound_nodes": [ | |
| [ | |
| [ | |
| "fully_connected_1", | |
| 0, | |
| 0, | |
| {} | |
| ] | |
| ] | |
| ], | |
| "name": "batch_norm_1" | |
| }, | |
| { | |
| "class_name": "Activation", | |
| "config": { | |
| "activation": "elu", | |
| "dtype": "float32", | |
| "name": "activation_19", | |
| "trainable": true | |
| }, | |
| "inbound_nodes": [ | |
| [ | |
| [ | |
| "batch_norm_1", | |
| 0, | |
| 0, | |
| {} | |
| ] | |
| ] | |
| ], | |
| "name": "activation_19" | |
| }, | |
| { | |
| "class_name": "Dropout", | |
| "config": { | |
| "dtype": "float32", | |
| "name": "dropout_1", | |
| "noise_shape": null, | |
| "rate": 0.2, | |
| "seed": null, | |
| "trainable": true | |
| }, | |
| "inbound_nodes": [ | |
| [ | |
| [ | |
| "activation_19", | |
| 0, | |
| 0, | |
| {} | |
| ] | |
| ] | |
| ], | |
| "name": "dropout_1" | |
| }, | |
| { | |
| "class_name": "Dense", | |
| "config": { | |
| "activation": "linear", | |
| "activity_regularizer": null, | |
| "bias_constraint": null, | |
| "bias_initializer": { | |
| "class_name": "Zeros", | |
| "config": {}, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "bias_regularizer": null, | |
| "dtype": "float32", | |
| "kernel_constraint": null, | |
| "kernel_initializer": { | |
| "class_name": "HeNormal", | |
| "config": { | |
| "seed": null | |
| }, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "kernel_regularizer": null, | |
| "name": "fully_connected_1.1", | |
| "trainable": true, | |
| "units": 64, | |
| "use_bias": true | |
| }, | |
| "inbound_nodes": [ | |
| [ | |
| [ | |
| "dropout_1", | |
| 0, | |
| 0, | |
| {} | |
| ] | |
| ] | |
| ], | |
| "name": "fully_connected_1.1" | |
| }, | |
| { | |
| "class_name": "BatchNormalization", | |
| "config": { | |
| "axis": [ | |
| 1 | |
| ], | |
| "beta_constraint": null, | |
| "beta_initializer": { | |
| "class_name": "Zeros", | |
| "config": {}, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "beta_regularizer": null, | |
| "center": true, | |
| "dtype": "float32", | |
| "epsilon": 0.001, | |
| "gamma_constraint": null, | |
| "gamma_initializer": { | |
| "class_name": "Ones", | |
| "config": {}, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "gamma_regularizer": null, | |
| "momentum": 0.99, | |
| "moving_mean_initializer": { | |
| "class_name": "Zeros", | |
| "config": {}, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "moving_variance_initializer": { | |
| "class_name": "Ones", | |
| "config": {}, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "name": "batch_norm_1.1", | |
| "scale": true, | |
| "trainable": true | |
| }, | |
| "inbound_nodes": [ | |
| [ | |
| [ | |
| "fully_connected_1.1", | |
| 0, | |
| 0, | |
| {} | |
| ] | |
| ] | |
| ], | |
| "name": "batch_norm_1.1" | |
| }, | |
| { | |
| "class_name": "Activation", | |
| "config": { | |
| "activation": "elu", | |
| "dtype": "float32", | |
| "name": "activation_20", | |
| "trainable": true | |
| }, | |
| "inbound_nodes": [ | |
| [ | |
| [ | |
| "batch_norm_1.1", | |
| 0, | |
| 0, | |
| {} | |
| ] | |
| ] | |
| ], | |
| "name": "activation_20" | |
| }, | |
| { | |
| "class_name": "Dropout", | |
| "config": { | |
| "dtype": "float32", | |
| "name": "dropout_1.1", | |
| "noise_shape": null, | |
| "rate": 0.2, | |
| "seed": null, | |
| "trainable": true | |
| }, | |
| "inbound_nodes": [ | |
| [ | |
| [ | |
| "activation_20", | |
| 0, | |
| 0, | |
| {} | |
| ] | |
| ] | |
| ], | |
| "name": "dropout_1.1" | |
| }, | |
| { | |
| "class_name": "Dense", | |
| "config": { | |
| "activation": "softmax", | |
| "activity_regularizer": null, | |
| "bias_constraint": null, | |
| "bias_initializer": { | |
| "class_name": "Zeros", | |
| "config": {}, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "bias_regularizer": null, | |
| "dtype": "float32", | |
| "kernel_constraint": null, | |
| "kernel_initializer": { | |
| "class_name": "GlorotUniform", | |
| "config": { | |
| "seed": null | |
| }, | |
| "module": "keras.initializers", | |
| "registered_name": null | |
| }, | |
| "kernel_regularizer": null, | |
| "name": "output_layer", | |
| "trainable": true, | |
| "units": 49, | |
| "use_bias": true | |
| }, | |
| "inbound_nodes": [ | |
| [ | |
| [ | |
| "dropout_1.1", | |
| 0, | |
| 0, | |
| {} | |
| ] | |
| ] | |
| ], | |
| "name": "output_layer" | |
| } | |
| ], | |
| "max_position_embeddings": 512, | |
| "model_type": "bert", | |
| "name": "model_6", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "output_layers": [ | |
| [ | |
| "output_layer", | |
| 0, | |
| 0 | |
| ] | |
| ], | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "torch_dtype": "float32", | |
| "trainable": true, | |
| "transformers_version": "4.33.2", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 30522 | |
| } | |