Update src/generation/llm.py

src/generation/llm.py

@@ -99,12 +99,8 @@ class LLM:
             )
             # Decode the generated tokens
             response = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
-            # Strip any system/user metadata
-            response = response.replace("system", "").replace("user", "").replace("assistant", "")
-            # Remove any extra whitespace or unwanted tokens
-            response = " ".join(response.split()).strip()
             print("Response generated successfully!")
-            return response.strip()
+            return response
         except Exception as e:
             raise RuntimeError(f"Failed to generate response: {str(e)}")