| { | |
| "_name_or_path": "/workspace/restore/finetuning-subnet-user/merge_model_submit_mar5_clone_r9_foreshadowing_old/eval_dataset_foreshadowing_cleaned_/workspace/restore/finetuning-subnet-user/merge_model_submit_mar4_clone_rbm_old/eval_dataset_purchasing_cleaned_/workspace/restore/finetuning-subnet-user/merge_model_submit_mar4_clone_r6/eval_dataset_setting._cleaned_0x0dad0/nous_nb00_OwOpeepeepoopoo_gemmerica_r6/output_final_weights_OwOpeepeepoopoo_gemmerica_rbm_old/output_final_weights_OwOpeepeepoopoo_gemmerica_right2_4/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, | |
| "pretraining_tp": 1, | |
| "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 | |
| } | |