| { | |
| "patch_size": 32, | |
| "d_model": 768, | |
| "num_heads": 12, | |
| "mlp_hidden_dim": 2048, | |
| "block_schedule": [ | |
| "time", | |
| "time", | |
| "time", | |
| "time_variate", | |
| "time", | |
| "time", | |
| "time", | |
| "time_variate", | |
| "time", | |
| "time", | |
| "time", | |
| "time_variate", | |
| "time", | |
| "time", | |
| "time", | |
| "time_variate", | |
| "time", | |
| "time", | |
| "time", | |
| "time_variate", | |
| "time", | |
| "time", | |
| "time", | |
| "time_variate" | |
| ], | |
| "quantile_knots": [ | |
| 0.01, | |
| 0.05, | |
| 0.1, | |
| 0.15, | |
| 0.2, | |
| 0.25, | |
| 0.3, | |
| 0.35, | |
| 0.4, | |
| 0.45, | |
| 0.5, | |
| 0.55, | |
| 0.6, | |
| 0.65, | |
| 0.7, | |
| 0.75, | |
| 0.8, | |
| 0.85, | |
| 0.9, | |
| 0.95, | |
| 0.99 | |
| ], | |
| "block_size": 32, | |
| "context_length": 32768, | |
| "rope_theta": 10000.0, | |
| "rope_partial_factor": 0.5, | |
| "norm_eps": 1e-06, | |
| "attn_bias": false, | |
| "mlp_bias": false, | |
| "time_attn_gate": "sdpa_sigmoid", | |
| "variate_attn_gate": "sdpa_sigmoid", | |
| "minimum_scale": 1e-06, | |
| "use_asinh": true, | |
| "stabilize_with_global": false, | |
| "covariate_enabled": true, | |
| "split_context_horizon_attn": true, | |
| "attend_missing_patches": true, | |
| "quantile_width_factor": 3.0 | |
| } | |