| { | |
| "patch_size": 64, | |
| "stride": 64, | |
| "embed_dim": 768, | |
| "num_layers": 12, | |
| "num_heads": 12, | |
| "mlp_hidden_dim": 3072, | |
| "dropout": 0.1, | |
| "spacewise_every_n_layers": 12, | |
| "scaler_cls": "<class 'model.scaler.CausalPatchStdMeanScaler'>", | |
| "output_distribution_classes": [ | |
| "<class 'model.distribution.MixtureOfStudentTsOutput'>" | |
| ], | |
| "spacewise_first": false, | |
| "output_distribution_kwargs": { | |
| "k_components": 24 | |
| }, | |
| "use_memory_efficient_attention": true, | |
| "stabilize_with_global": true, | |
| "scale_factor_exponent": 10.0 | |
| } |