[fix] reduce aux_loss_alpha

2025-12-05 23:08:29 +08:00 · 2025-12-05 23:08:29 +08:00 · ecd1ae1563
parent 5e1447b913
commit ecd1ae1563
1 changed files with 1 additions and 1 deletions
--- a/model/model_minimind.py
+++ b/model/model_minimind.py
@ -34,7 +34,7 @@ class MiniMindConfig(PretrainedConfig):
            n_routed_experts: int = 4,
            n_shared_experts: int = 1,
            scoring_func: str = 'softmax',
-            aux_loss_alpha: float = 0.1,
+            aux_loss_alpha: float = 0.01,
            seq_aux: bool = True,
            norm_topk_prob: bool = True,
            **kwargs