| {"module": "keras_nlp.src.models.gemma.gemma_causal_lm", "class_name": "GemmaCausalLM", "config": {"backbone": {"module": "keras_nlp.src.models.gemma.gemma_backbone", "class_name": "GemmaBackbone", "config": {"name": "gemma_backbone", "trainable": true, "vocabulary_size": 256000, "num_layers": 26, "num_query_heads": 8, "num_key_value_heads": 4, "hidden_dim": 2304, "intermediate_dim": 18432, "head_dim": 256, "layer_norm_epsilon": 1e-06, "dropout": 0, "query_head_dim_normalize": true, "use_post_ffw_norm": true, "use_post_attention_norm": true, "final_logit_soft_cap": 30.0, "attention_logit_soft_cap": 50.0, "sliding_window_size": 4096, "use_sliding_window_attention": true}, "registered_name": "keras_nlp>GemmaBackbone", "build_config": {"input_shape": null}}, "preprocessor": {"module": "keras_nlp.src.models.gemma.gemma_causal_lm_preprocessor", "class_name": "GemmaCausalLMPreprocessor", "config": {"name": "gemma_causal_lm_preprocessor", "trainable": true, "dtype": {"module": "keras", "class_name": "DTypePolicy", "config": {"name": "float32"}, "registered_name": null}, "tokenizer": {"module": "keras_nlp.src.models.gemma.gemma_tokenizer", "class_name": "GemmaTokenizer", "config": {"name": "gemma_tokenizer", "trainable": true, "dtype": {"module": "keras", "class_name": "DTypePolicy", "config": {"name": "int32"}, "registered_name": null}, "proto": null, "sequence_length": null, "add_bos": false, "add_eos": false}, "registered_name": "keras_nlp>GemmaTokenizer"}, "sequence_length": 512, "add_start_token": true, "add_end_token": true}, "registered_name": "keras_nlp>GemmaCausalLMPreprocessor"}, "name": "gemma_causal_lm"}, "registered_name": "keras_nlp>GemmaCausalLM", "build_config": {"input_shape": null}, "compile_config": {"optimizer": {"module": "keras.optimizers", "class_name": "Adam", "config": {"name": "adam", "learning_rate": 4.999999873689376e-05, "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": {"module": "keras.losses", "class_name": "SparseCategoricalCrossentropy", "config": {"name": "sparse_categorical_crossentropy", "reduction": "sum_over_batch_size", "from_logits": true, "ignore_class": null}, "registered_name": null}, "loss_weights": null, "metrics": null, "weighted_metrics": [{"module": "keras.metrics", "class_name": "SparseCategoricalAccuracy", "config": {"name": "sparse_categorical_accuracy", "dtype": "float32"}, "registered_name": null}], "run_eagerly": false, "steps_per_execution": 1, "jit_compile": true}} |