Update modeling_quiet.py

modeling_quiet.py

@@ -1174,7 +1174,7 @@ class QuietForCausalLM(QuietPreTrainedModel):
         self.model = QuietModel(config)
         self.vocab_size = config.vocab_size
         self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
-        self.router_aux_loss_coef = config.router_aux_loss_coef
+        # self.router_aux_loss_coef = config.router_aux_loss_coef
         self.num_experts = config.num_experts
         self.num_experts_per_tok = config.num_experts_per_tok
         self.max_thoughts = config.max_thoughts