Update inference_1.py

inference_1.py

@@ -92,6 +92,7 @@ def main():
     parser.add_argument("--mode", choices=["single", "chat", "batch"], default="single", help="Inference mode")
     parser.add_argument("--prompt", help="Prompt for single inference mode")
     parser.add_argument("--prompt_file", help="File containing prompts for batch mode (one per line)")
+    parser.add_argument("--output_file", help="Path to save JSON results (default: auto-generated)")
     args = parser.parse_args()
     
     # Initialize the model
@@ -132,7 +133,7 @@ def main():
         print(f"Running batch inference on {len(prompts)} prompts...")
         responses = batch_inference(llm, prompts)
         
-        with open("./test.json", "w") as final:
+        with open(args.output_file, "w") as final:
             json.dump(responses, final)
 
 if __name__ == "__main__":