Update superposed/llama/superposed_generation.py

superposed/llama/superposed_generation.py

@@ -72,7 +72,7 @@ class SuperposedLlama:
         # Set up superposed decoding
         model = SuperposedTransformer(model_args)
         model.load_state_dict(checkpoint, strict=False)
-        print(f"Loaded in {time.time() - start_time:.2f} seconds")
+        # print(f"Loaded in {time.time() - start_time:.2f} seconds")
         return SuperposedLlama(model, tokenizer, device)
 
     def __init__(self, model: SuperposedTransformer, tokenizer: Tokenizer, device):