Update modeling_quiet.py

modeling_quiet.py

@@ -1126,7 +1126,7 @@ class QuietForCausalLM(QuietPreTrainedModel, GenerationMixin):
 
         return generated_text
 
-  @torch.no_grad()
+    @torch.no_grad()
     def generate(self, input_ids: torch.LongTensor = torch.LongTensor(), attention_mask: Optional[torch.Tensor] = None, max_new_tokens: Optional[int] = None, temperature: float = 1.1, **kwargs):
         return self.generate_with_callback(input_ids, attention_mask, max_new_tokens, temperature, callback=None, **kwargs)