| { | |
| "architectures": [ | |
| "Gemma2ForCausalLM" | |
| ], | |
| "module": "keras_nlp.src.models.gemma.gemma_backbone", | |
| "class_name": "GemmaBackbone", | |
| "model_type": "gemma", | |
| "name": "gemma_backbone", | |
| "trainable": true, | |
| "vocabulary_size": 256000, | |
| "num_layers": 18, | |
| "num_query_heads": 8, | |
| "num_key_value_heads": 1, | |
| "hidden_dim": 2048, | |
| "intermediate_dim": 32768, | |
| "head_dim": 256, | |
| "layer_norm_epsilon": 1e-06, | |
| "dropout": 0, | |
| "query_head_dim_normalize": true, | |
| "use_post_ffw_norm": false, | |
| "use_post_attention_norm": false, | |
| "final_logit_soft_cap": null, | |
| "attention_logit_soft_cap": null, | |
| "sliding_window_size": 4096, | |
| "use_sliding_window_attention": false, | |
| "registered_name": "keras_nlp>GemmaBackbone" | |
| } |