| { | |
| "module": "keras_hub.src.models.gemma.gemma_causal_lm", | |
| "class_name": "GemmaCausalLM", | |
| "config": { | |
| "backbone": { | |
| "module": "keras_hub.src.models.gemma.gemma_backbone", | |
| "class_name": "GemmaBackbone", | |
| "config": { | |
| "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_hub>GemmaBackbone" | |
| }, | |
| "preprocessor": { | |
| "module": "keras_hub.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": "bfloat16" | |
| }, | |
| "registered_name": null | |
| }, | |
| "tokenizer": { | |
| "module": "keras_hub.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 | |
| }, | |
| "config_file": "tokenizer.json", | |
| "proto": null, | |
| "sequence_length": null, | |
| "add_bos": false, | |
| "add_eos": false | |
| }, | |
| "registered_name": "keras_hub>GemmaTokenizer" | |
| }, | |
| "config_file": "preprocessor.json", | |
| "sequence_length": 1024, | |
| "add_start_token": true, | |
| "add_end_token": true | |
| }, | |
| "registered_name": "keras_hub>GemmaCausalLMPreprocessor" | |
| }, | |
| "name": "gemma_causal_lm" | |
| }, | |
| "registered_name": "keras_hub>GemmaCausalLM" | |
| } |