{ "_name_or_path": "/workspace/restore/finetuning-subnet-user/gemma/eval_dataset_multinational_cleaned_/workspace/restore/finetuning-subnet-user/gemma/eval_dataset_expressing_cleaned_/workspace/restore/finetuning-subnet-user/gemma/eval_dataset_components_cleaned_/workspace/restore/finetuning-subnet-user/gemma/eval_dataset_biodiversity._cleaned_/workspace/restore/finetuning-subnet-user/merge_test27/output_merge4_OwOpeepeepoopoo_gemmerica_gemma_bio_m27m4_sftpt/output_final_weights_OwOpeepeepoopoo_gemmerica_gemma_components_m27m4_constlr/output_final_weights_OwOpeepeepoopoo_gemmerica_gemma_expressing_m27m4_constlr/output_final_weights_OwOpeepeepoopoo_gemmerica_gemma_multinational_m27m4_constlr/output_final_weights", "architectures": [ "GemmaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 204, "eos_token_id": 213, "head_dim": 256, "hidden_act": "gelu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 16384, "max_position_embeddings": 8192, "model_type": "gemma", "num_attention_heads": 8, "num_hidden_layers": 18, "num_key_value_heads": 1, "pad_token_id": 0, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "torch_dtype": "bfloat16", "transformers_version": "4.38.1", "use_cache": false, "vocab_size": 256000 }