quantlab.model.predefined.transformer.LocalformerRegressor

class quantlab.model.predefined.transformer.LocalformerRegressor(config)

Bases: TransformerRegressor

Qlib’s Localformer benchmark model on (bar, symbol) samples.

LocalformerNet trained like TransformerRegressor, with the same defaults (workflow_config_localformer_Alpha158.yaml keeps the model’s): window_bars (20), d_model (64), nhead (2), num_layers (2), dropout (0.0), batch_size (8192), lr (1e-4), weight_decay (1e-3), epochs (100) and early_stop (5).

Parameters:

configModelConfig

Factors, labels, dates and hyperparameters.

Examples

>>> LocalformerRegressor(config).collect().train().name
'LocalformerRegressor_total.pth'

net_cls

alias of LocalformerNet