Update src/generation/llm.py

src/generation/llm.py

@@ -100,7 +100,7 @@ class LLM:
             # Decode the generated tokens
             response = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
             print("Response generated successfully!")
-            return response
+            return response.strip()
         except Exception as e:
             raise RuntimeError(f"Failed to generate response: {str(e)}")