Update README.md

README.md

@@ -34,7 +34,8 @@ def generate_response(prompt: str, system_message: str, model_path: str) -> str:
     results = generator.generate_batch(
         [tokens],
         max_length=1024,
-        sampling_temperature=0.7
+        sampling_temperature=0.7,
+        include_prompt_in_result=False
     )
     response = tokenizer.decode(results[0].sequences_ids[0], skip_special_tokens=True)
     return response