| { | |
| "architectures": [ | |
| "LaminarNet" | |
| ], | |
| "model_type": "laminarnet", | |
| "vocab_size": 50257, | |
| "d_model": 320, | |
| "n_heads": 5, | |
| "n_layers": 10, | |
| "d_ff": 1200, | |
| "n_strata": 2, | |
| "strata_ratios": [ | |
| 1, | |
| 2, | |
| 4 | |
| ], | |
| "seq_len": 1024, | |
| "dropout": 0.1, | |
| "conv_kernel": 4, | |
| "rope_base": 10000.0, | |
| "total_params": 49420160, | |
| "best_val_loss": 3.788057290315628, | |
| "training_steps": 115500 | |
| } |